From d32eaf506b8e4da80793bf68e2a3ceab7f883984 Mon Sep 17 00:00:00 2001 From: suryaprakash4647 Date: Mon, 17 Aug 2026 14:34:56 +0530 Subject: [PATCH 1/3] Task(1048063):Change the title, description and heading in UG documentation of Smart data libraries. --- .../Data-Extraction/NET/Assemblies-required.md | 6 +++--- .../Data-Extraction/NET/Extract-Data-in-ASP-NET-Core.md | 6 +++--- .../Data-Extraction/NET/Extract-Data-in-ASP-NET-MVC.md | 6 +++--- .../Data-Extraction/NET/Extract-Data-in-Blazor.md | 6 +++--- .../Data-Extraction/NET/Extract-Data-in-Console.md | 6 +++--- .../Data-Extraction/NET/Extract-Data-in-MAUI.md | 6 +++--- .../Data-Extraction/NET/Extract-Data-in-WPF.md | 6 +++--- .../Data-Extraction/NET/Extract-Data-in-Windows-Forms.md | 6 +++--- .../Data-Extraction/NET/Nuget-packages-required.md | 6 +++--- .../Data-Extraction/NET/conversions/overview.md | 6 +++--- .../Data-Extraction/NET/conversions/pdf-to-json.md | 6 +++--- .../Data-Extraction/NET/conversions/pdf-to-markdown.md | 6 +++--- .../Data-Extraction/NET/data-extractor-overview.md | 6 +++--- .../Data-Extraction/NET/how-to-download-and-install.md | 6 +++--- Document-Processing/Data-Extraction/NET/ocr-overview.md | 6 +++--- .../Data-Extraction/NET/ocr-processor/AWS-Textract.md | 6 +++--- .../NET/ocr-processor/Amazon-Linux-EC2-Setup-Guide.md | 6 +++--- .../NET/ocr-processor/Assemblies-Required.md | 4 ++-- .../NET/ocr-processor/Azure-Kubernetes-Service.md | 6 +++--- .../Data-Extraction/NET/ocr-processor/Azure-Vision.md | 6 +++--- .../Data-Extraction/NET/ocr-processor/Console.md | 6 +++--- .../Data-Extraction/NET/ocr-processor/Docker.md | 6 +++--- .../Data-Extraction/NET/ocr-processor/Features.md | 6 +++--- .../NET/ocr-processor/Getting-started-overview.md | 6 +++--- .../Data-Extraction/NET/ocr-processor/Linux.md | 6 +++--- .../Data-Extraction/NET/ocr-processor/MAC.md | 6 +++--- .../NET/ocr-processor/NuGet-Packages-Required.md | 6 +++--- .../Data-Extraction/NET/ocr-processor/Troubleshooting.md | 6 +++--- .../Data-Extraction/NET/ocr-processor/WPF.md | 6 +++--- .../Data-Extraction/NET/ocr-processor/Web-API.md | 6 +++--- .../Data-Extraction/NET/ocr-processor/Windows-Forms.md | 6 +++--- .../Data-Extraction/NET/ocr-processor/aspnet-mvc.md | 6 +++--- .../Data-Extraction/NET/ocr-processor/azure.md | 7 +++---- .../Data-Extraction/NET/ocr-processor/blazor.md | 6 +++--- ...o-perform-ocr-for-a-pdf-document-using-cSharp-and-VB.md | 4 ++-- ...how-to-perform-ocr-for-a-pdf-document-using-net-Core.md | 4 ++-- .../Data-Extraction/NET/ocr-processor/net-core.md | 6 +++--- .../Data-Extraction/NET/ocr-processor/overview.md | 6 +++--- Document-Processing/Data-Extraction/NET/overview.md | 6 +++--- Document-Processing/Data-Extraction/NET/troubleshooting.md | 6 +++--- .../Data-Extraction/NET/working-with-data-extraction.md | 6 +++--- .../Data-Extraction/NET/working-with-form-recognition.md | 6 +++--- .../Data-Extraction/NET/working-with-table-extraction.md | 6 +++--- Document-Processing/Data-Extraction/overview.md | 6 +++--- Document-Processing/Telemetry.md | 6 +++--- 45 files changed, 132 insertions(+), 133 deletions(-) diff --git a/Document-Processing/Data-Extraction/NET/Assemblies-required.md b/Document-Processing/Data-Extraction/NET/Assemblies-required.md index 388abaea9a..7f2b714bd9 100644 --- a/Document-Processing/Data-Extraction/NET/Assemblies-required.md +++ b/Document-Processing/Data-Extraction/NET/Assemblies-required.md @@ -1,12 +1,12 @@ --- -title: Assemblies required for Data Extraction | Syncfusion -description: This section details the Syncfusion assemblies required to configure and run Data Extraction seamlessly in .NET projects. +title: Assemblies Required in .NET Smart Data Extractor | Syncfusion +description: This section describes the required Syncfusion assemblies needed to integrate and use the Smart Data Extractor effectively in your applications platform: document-processing control: DataExtraction documentation: UG keywords: Assemblies --- -# Assemblies required for Data Extraction +# Assemblies Required in Data Extraction ## Smart Data Extractor diff --git a/Document-Processing/Data-Extraction/NET/Extract-Data-in-ASP-NET-Core.md b/Document-Processing/Data-Extraction/NET/Extract-Data-in-ASP-NET-Core.md index 7a7ef89c15..34fed02c90 100644 --- a/Document-Processing/Data-Extraction/NET/Extract-Data-in-ASP-NET-Core.md +++ b/Document-Processing/Data-Extraction/NET/Extract-Data-in-ASP-NET-Core.md @@ -1,13 +1,13 @@ --- -title: Extract data in ASP.NET Core | Syncfusion +title: Getting Started with ASP.NET Core Smart Data Extractor | Syncfusion canonical_url: "https://www.syncfusioninternal.com/document-sdk/net-pdf-data-extraction" -description: Learn how to extract data from PDF in ASP.NET Core with step‑by‑step guidance using Syncfusion .NET Core Data extraction library. +description: Learn how to get started with the Syncfusion ASP.NET Core Smart Data Extractor. Explore setup, features, examples, and customization options. platform: document-processing control: SmartDataExtractor documentation: UG --- -# Extract Data in ASP.NET Core +# Getting Started with ASP.NET Core Smart Data Extractor The Syncfusion® Smart Data Extractor is a .NET library used to extract structured data and document elements from PDF and image files in ASP.NET Core applications. diff --git a/Document-Processing/Data-Extraction/NET/Extract-Data-in-ASP-NET-MVC.md b/Document-Processing/Data-Extraction/NET/Extract-Data-in-ASP-NET-MVC.md index 2842d58e65..7caa6aba4b 100644 --- a/Document-Processing/Data-Extraction/NET/Extract-Data-in-ASP-NET-MVC.md +++ b/Document-Processing/Data-Extraction/NET/Extract-Data-in-ASP-NET-MVC.md @@ -1,6 +1,6 @@ --- -title: Extract Data in ASP.NET MVC Application | Syncfusion -description: Learn how to extract data in an ASP.NET MVC application with step‑by‑step guidance using the Syncfusion Data Extraction library. +title: Getting Started with ASP.NET MVC Smart Data Extractor | Syncfusion +description: Learn how to get started with the Syncfusion ASP.NET MVC Smart Data Extractor. Explore setup, features, examples, and customization options. platform: document-processing control: SmartDataExtractor documentation: UG @@ -8,7 +8,7 @@ keywords: Assemblies --- -# Extract Data in ASP.NET MVC +# Getting Started with ASP.NET MVC Smart Data Extractor The Syncfusion® Smart Data Extractor is a .NET library used to extract structured data and document elements from PDFs and images in ASP.NET MVC applications. diff --git a/Document-Processing/Data-Extraction/NET/Extract-Data-in-Blazor.md b/Document-Processing/Data-Extraction/NET/Extract-Data-in-Blazor.md index 457f6403f4..ae16ae58d1 100644 --- a/Document-Processing/Data-Extraction/NET/Extract-Data-in-Blazor.md +++ b/Document-Processing/Data-Extraction/NET/Extract-Data-in-Blazor.md @@ -1,6 +1,6 @@ --- -title: Extract Data in Blazor Application | Syncfusion -description: Learn to extract tables, forms, text, and images from PDF documents and scanned images in Blazor using the Syncfusion® Smart Data Extractor .NET library. +title: Getting Started with Blazor Smart Data Extractor | Syncfusion +description: Learn how to get started with the Syncfusion Blazor Smart Data Extractor. Explore setup, features, examples, and customization options. platform: document-processing control: SmartDataExtractor documentation: UG @@ -8,7 +8,7 @@ keywords: Assemblies --- -# Extract Data from PDF in Blazor +# Getting Started with Blazor Smart Data Extractor The Syncfusion® Smart Data Extractor is a .NET library used to extract structured data and document elements from PDFs and images in Blazor applications. diff --git a/Document-Processing/Data-Extraction/NET/Extract-Data-in-Console.md b/Document-Processing/Data-Extraction/NET/Extract-Data-in-Console.md index 80d74979e2..7df17846bd 100644 --- a/Document-Processing/Data-Extraction/NET/Extract-Data-in-Console.md +++ b/Document-Processing/Data-Extraction/NET/Extract-Data-in-Console.md @@ -1,12 +1,12 @@ --- -title: Extract Data in Console Application | Syncfusion -description: Learn how to extract data in a Console Application by using the .NET Smart Data Extractor Library efficiently. +title: Getting Started with Console Smart Data Extractor | Syncfusion +description: Learn how to get started with the Syncfusion Console Smart Data Extractor. Explore setup, features, examples, and customization options. platform: document-processing control: SmartDataExtractor documentation: UG --- -# Extract Data from PDF in Console Application +# Getting Started with Console Smart Data Extractor The Syncfusion® Smart Data Extractor is a .NET library used to extract structured data and document elements from PDFs and images in Console applications. diff --git a/Document-Processing/Data-Extraction/NET/Extract-Data-in-MAUI.md b/Document-Processing/Data-Extraction/NET/Extract-Data-in-MAUI.md index 45b8d8db5b..e94e101217 100644 --- a/Document-Processing/Data-Extraction/NET/Extract-Data-in-MAUI.md +++ b/Document-Processing/Data-Extraction/NET/Extract-Data-in-MAUI.md @@ -1,6 +1,6 @@ --- -title: Extract Data in .NET MAUI | Syncfusion -description: Extract tables, forms, text, and images from PDF documents and scanned files in .NET MAUI using the Syncfusion® Smart Data Extractor. +title: Getting Started with .NET MAUI Smart Data Extractor| Syncfusion +description: Learn how to get started with the Syncfusion .NET MAUI Smart Data Extractor. Explore setup, features, examples, and customization options. platform: document-processing control: SmartDataExtractor documentation: UG @@ -8,7 +8,7 @@ keywords: Assemblies --- -# Extract Data from PDF in .NET MAUI +# Getting Started with .NET MAUI Smart Data Extractor The Syncfusion® Smart Data Extractor is a .NET library used to extract structured data and document elements from PDFs and images in .NET MAUI applications. diff --git a/Document-Processing/Data-Extraction/NET/Extract-Data-in-WPF.md b/Document-Processing/Data-Extraction/NET/Extract-Data-in-WPF.md index 91ef4e2c87..cf634560bc 100644 --- a/Document-Processing/Data-Extraction/NET/Extract-Data-in-WPF.md +++ b/Document-Processing/Data-Extraction/NET/Extract-Data-in-WPF.md @@ -1,6 +1,6 @@ --- -title: Extract Data in WPF Application | Syncfusion -description: Learn how to extract data in a WPF application with step‑by‑step guidance using the .NET Smart Data Extractor Library. +title: Getting Started with WPF Smart Data Extractor | Syncfusion +description: Learn how to get started with the Syncfusion WPF Smart Data Extractor. Explore setup, features, examples, and customization options. platform: document-processing control: SmartDataExtractor documentation: UG @@ -8,7 +8,7 @@ keywords: Assemblies --- -# Extract Data from PDF in WPF +# Getting Started with WPF Smart Data Extractor The Syncfusion® Smart Data Extractor is a .NET library used to extract structured data and document elements from PDFs and images in WPF applications. diff --git a/Document-Processing/Data-Extraction/NET/Extract-Data-in-Windows-Forms.md b/Document-Processing/Data-Extraction/NET/Extract-Data-in-Windows-Forms.md index 9df266bb1a..831605bcfd 100644 --- a/Document-Processing/Data-Extraction/NET/Extract-Data-in-Windows-Forms.md +++ b/Document-Processing/Data-Extraction/NET/Extract-Data-in-Windows-Forms.md @@ -1,13 +1,13 @@ --- -title: Extract Data from PDF in Windows Forms | Syncfusion -description: Extract tables, text, and form fields from PDF documents in Windows Forms using the .NET Smart Data Extractor Library. +title: Getting Started with Windows Forms Smart Data Extractor | Syncfusion +description: Learn how to get started with the Syncfusion Windows Forms Smart Data Extractor. Explore setup, features, examples, and customization options. platform: document-processing control: SmartDataExtractor documentation: UG --- -# Extract Data in Windows Forms +# Getting Started with Windows Forms Smart Data Extractor The Syncfusion® Smart Data Extractor is a .NET library used to extract structured data and document elements from PDFs and images in Windows Forms applications. diff --git a/Document-Processing/Data-Extraction/NET/Nuget-packages-required.md b/Document-Processing/Data-Extraction/NET/Nuget-packages-required.md index 4f72da15b0..cf95220a92 100644 --- a/Document-Processing/Data-Extraction/NET/Nuget-packages-required.md +++ b/Document-Processing/Data-Extraction/NET/Nuget-packages-required.md @@ -1,13 +1,13 @@ --- -title: NuGet Packages for Data Extraction | Syncfusion® -description: Learn the NuGet packages required to use Syncfusion® Data Extraction in various platforms and frameworks. +title: NuGet Packages required for .NET Smart Data Extractor | Syncfusion +description: Discover the NuGet packages required to integrate Smart Data Extractor across .NET platforms and frameworks platform: document-processing control: DataExtraction documentation: UG keywords: Assemblies --- -# NuGet Packages Required for Data Extraction +# NuGet Packages required for .NET Smart Data Extractor ## Smart Data Extractor diff --git a/Document-Processing/Data-Extraction/NET/conversions/overview.md b/Document-Processing/Data-Extraction/NET/conversions/overview.md index 8b4148e6f6..fd0f5ec63e 100644 --- a/Document-Processing/Data-Extraction/NET/conversions/overview.md +++ b/Document-Processing/Data-Extraction/NET/conversions/overview.md @@ -1,13 +1,13 @@ --- -title: Smart Data Extractor Library | Syncfusion -description: Smart Data Extractor converts PDF documents and images to structured formats like JSON, Markdown (MD), and PDF output. +title: About Document Conversions of .NET Smart Data Extractor | Syncfusion +description: Learn about overview of the document conversions supported by Syncfusion .NET Smart Data Extractor and more details. platform: document-processing control: SmartDataExtractor documentation: UG keywords: SmartDataExtractor, PDF to JSON, PDF to Markdown --- -# Welcome to Syncfusion® Smart Data Extractor Library +# About Document Conversions of .NET Smart Data Extractor Syncfusion® Smart Data Extractor Library extracts structured information from PDF documents and scanned images. It supports conversions such as **PDF to JSON**, **PDF to Markdown (MD)**, and generating **PDF output** by analyzing visual layout patterns like text blocks, tables, headers, and form fields. This helps developers easily integrate the extractor to achieve required data conversions while focusing on the core logic of their applications. diff --git a/Document-Processing/Data-Extraction/NET/conversions/pdf-to-json.md b/Document-Processing/Data-Extraction/NET/conversions/pdf-to-json.md index cdc6458ab3..d8ba6736f5 100644 --- a/Document-Processing/Data-Extraction/NET/conversions/pdf-to-json.md +++ b/Document-Processing/Data-Extraction/NET/conversions/pdf-to-json.md @@ -1,13 +1,13 @@ --- -title: Extract PDF to JSON in C# | Smart Data Extractor | Syncfusion -description: Learn how to extract structured data from PDF documents as JSON in C# using the Syncfusion® Smart Data Extractor library for .NET applications. +title: Convert PDF to JSON in .NET Smart Data Extractor | Syncfusion +description: Extract structured data from PDF documents as JSON using Smart Data Extractor. Convert PDF content into machine-readable JSON format seamlessly in .NET applications. platform: document-processing control: SmartDataExtractor documentation: UG keywords: Assemblies --- -# PDF to JSON Extraction +# Convert PDF to JSON in .NET Smart Data Extractor JavaScript Object Notation (JSON) is a lightweight data‑interchange format that is easy for humans to read and write, and simple for machines to parse and generate. The Syncfusion® Smart Data Extractor library extracts structured information from PDF documents and scanned images, and outputs the content as JSON. It analyzes text blocks, tables, headers, and form fields to preserve structure, enabling developers to integrate PDF to JSON extraction into their applications. diff --git a/Document-Processing/Data-Extraction/NET/conversions/pdf-to-markdown.md b/Document-Processing/Data-Extraction/NET/conversions/pdf-to-markdown.md index 061f4d88ef..40be68aaa6 100644 --- a/Document-Processing/Data-Extraction/NET/conversions/pdf-to-markdown.md +++ b/Document-Processing/Data-Extraction/NET/conversions/pdf-to-markdown.md @@ -1,13 +1,13 @@ --- -title: Extract PDF to Markdown in C# | Smart Data Extractor | Syncfusion -description: Extract PDF documents as Markdown (MD) in C# using Syncfusion® Smart Data Extractor library without Microsoft Office or Adobe dependencies +title: Convert PDF to Markdown in .NET Smart Data Extractor | Syncfusion +description: Extract PDF documents as Markdown using Smart Data Extractor. Convert PDF content into clean, structured Markdown content in .NET. platform: document-processing control: SmartDataExtractor documentation: UG keywords: Assemblies --- -# PDF to Markdown Extraction +# Convert PDF to Markdown in .NET Smart Data Extractor Markdown is a lightweight markup language that adds formatting elements to plain text documents. The Syncfusion® Smart Data Extractor library extracts structured information from PDF documents and scanned images, and outputs the content as Markdown (MD). It analyzes text blocks, tables, headers, and form fields to preserve layout and formatting. diff --git a/Document-Processing/Data-Extraction/NET/data-extractor-overview.md b/Document-Processing/Data-Extraction/NET/data-extractor-overview.md index fe20730c55..06fd8d96d3 100644 --- a/Document-Processing/Data-Extraction/NET/data-extractor-overview.md +++ b/Document-Processing/Data-Extraction/NET/data-extractor-overview.md @@ -1,14 +1,14 @@ --- -title: Data Extraction and Conversion in .NET | Syncfusion +title: About Syncfusion .NET Smart Data Extractor | Syncfusion canonical_url: "https://www.syncfusioninternal.com/document-sdk/net-pdf-data-extraction" -description: Syncfusion Data Extraction is a .NET library that extracts tables, forms, text, and images from PDF or image files, and outputs JSON or Markdown. +description: Learn about introduction of Syncfusion .NET Smart Data Extractor for extracting data from PDFs or scanned images and more details. platform: document-processing control: DataExtraction documentation: UG keywords: Assemblies --- -# Welcome to .NET Smart Data Extractor Library +# About Syncfusion .NET Smart Data Extractor {% doccards %} diff --git a/Document-Processing/Data-Extraction/NET/how-to-download-and-install.md b/Document-Processing/Data-Extraction/NET/how-to-download-and-install.md index 34ae9298cc..6a38f73313 100644 --- a/Document-Processing/Data-Extraction/NET/how-to-download-and-install.md +++ b/Document-Processing/Data-Extraction/NET/how-to-download-and-install.md @@ -1,14 +1,14 @@ --- layout: post -title: Installing Syncfusion Data Extraction - Syncfusion -description: Learn how to install the .NET Smart Data Extractor Library for extracting structured data from PDFs and images in .NET applications. +title: How to install .NET Smart Data Extractor Add-on | Syncfusion +description: Install the .NET Smart Data Extractor Add-on with this step-by-step guide platform: document-processing control: Installation and Deployment documentation: ug --- -# Download Syncfusion® Data Extraction Add-On +# How to install .NET Smart Data Extractor Add-on The Syncfusion® Data Extraction Add-On can be downloaded from the [Syncfusion download page](https://www.syncfusion.com/downloads). diff --git a/Document-Processing/Data-Extraction/NET/ocr-overview.md b/Document-Processing/Data-Extraction/NET/ocr-overview.md index 6db8069a8c..d0f27bd190 100644 --- a/Document-Processing/Data-Extraction/NET/ocr-overview.md +++ b/Document-Processing/Data-Extraction/NET/ocr-overview.md @@ -1,14 +1,14 @@ --- -title: Intro to OCR Processor | Syncfusion +title: About Syncfusion OCR Processing Library | Syncfusion canonical_url: "https://www.syncfusion.com/document-sdk/net-pdf-library/ocr-process" -description: This page introduces the Syncfusion OCR Processor, highlighting its purpose, main features, and how to begin optical character recognition in .NET apps. +description: Learn about introduction of Syncfusion OCR Processor for recognizing text from scanned images and more details. platform: document-processing control: OCRProcessor documentation: UG keywords: OCR, Optical Character Recognition, Text Recognition --- -# Welcome to Syncfusion OCR Processor Library +# About Syncfusion OCR Processing Library {% doccards %} diff --git a/Document-Processing/Data-Extraction/NET/ocr-processor/AWS-Textract.md b/Document-Processing/Data-Extraction/NET/ocr-processor/AWS-Textract.md index 7318c1edad..9b9c1b1fd4 100644 --- a/Document-Processing/Data-Extraction/NET/ocr-processor/AWS-Textract.md +++ b/Document-Processing/Data-Extraction/NET/ocr-processor/AWS-Textract.md @@ -1,13 +1,13 @@ --- -title: Perform OCR on PDF and image files in AWS Textract | Syncfusion -description: Learn how to perform OCR on scanned PDF documents and images in AWS Textract using Syncfusion .NET OCR library. +title: Getting Started with AWS Textract OCR Processor | Syncfusion +description: Learn how to get started with the Syncfusion AWS Textract OCR Processor. Explore setup, features, examples, and customization options. platform: document-processing control: PDF documentation: UG keywords: Assemblies --- -# Perform OCR with AWS Textract +# Getting Started with AWS Textract OCR Processor The [.NET OCR library](https://www.syncfusion.com/document-sdk/net-pdf-library/ocr-process) supports external OCR engines such as AWS Textract to process OCR on images and PDF documents. diff --git a/Document-Processing/Data-Extraction/NET/ocr-processor/Amazon-Linux-EC2-Setup-Guide.md b/Document-Processing/Data-Extraction/NET/ocr-processor/Amazon-Linux-EC2-Setup-Guide.md index fc60dadff3..f43a643ccf 100644 --- a/Document-Processing/Data-Extraction/NET/ocr-processor/Amazon-Linux-EC2-Setup-Guide.md +++ b/Document-Processing/Data-Extraction/NET/ocr-processor/Amazon-Linux-EC2-Setup-Guide.md @@ -1,13 +1,13 @@ --- -title: .NET 8 & Tesseract OCR on Amazon Linux 2023 EC2 | Syncfusion -description: Install & configure .NET 8, Tesseract OCR on Amazon Linux 2023 EC2 to perform OCR on PDFs & images using Syncfusion .NET OCR library. +title: Getting Started with Amazon Linux EC2 OCR Processor | Syncfusion +description: Learn how to get started with the Syncfusion Amazon Linux 2023 EC2 OCR Processor. Explore setup, features, examples, and customization options. platform: document-processing control: PDF documentation: UG keywords: Assemblies --- -# Perform OCR with Tesseract on Amazon Linux EC2 using .NET application +# Getting Started with Amazon Linux EC2 OCR Processor The [.NET OCR library](https://www.syncfusion.com/document-sdk/net-pdf-library/ocr-process) is used to extract text from scanned PDFs and images in Linux applications with the help of Google's [Tesseract](https://github.com/tesseract-ocr/tesseract) Optical Character Recognition engine. diff --git a/Document-Processing/Data-Extraction/NET/ocr-processor/Assemblies-Required.md b/Document-Processing/Data-Extraction/NET/ocr-processor/Assemblies-Required.md index 1bfee7e8c7..6e015164c5 100644 --- a/Document-Processing/Data-Extraction/NET/ocr-processor/Assemblies-Required.md +++ b/Document-Processing/Data-Extraction/NET/ocr-processor/Assemblies-Required.md @@ -1,12 +1,12 @@ --- -title: Assemblies Required for OCR | Syncfusion +title: Assemblies Required in .NET OCR Processor | Syncfusion description: This section describes the required Syncfusion assemblies needed to integrate and use the OCR Processor effectively in your applications platform: document-processing control: PDF documentation: UG keywords: Assemblies --- -# Assemblies Required to work with OCR processor +# Assemblies Required in .NET OCR Processor Get the following required assemblies by downloading the OCR library installer. Download and install the OCR library for Windows, Linux, and Mac respectively. Please refer to the advanced installation steps for more details. diff --git a/Document-Processing/Data-Extraction/NET/ocr-processor/Azure-Kubernetes-Service.md b/Document-Processing/Data-Extraction/NET/ocr-processor/Azure-Kubernetes-Service.md index c097b7f32c..16db1a8e26 100644 --- a/Document-Processing/Data-Extraction/NET/ocr-processor/Azure-Kubernetes-Service.md +++ b/Document-Processing/Data-Extraction/NET/ocr-processor/Azure-Kubernetes-Service.md @@ -1,13 +1,13 @@ --- -title: Deploy and manage with Azure Kubernetes Service | Syncfusion -description: Learn how to deploy, scale, and manage containerized applications in Azure using Azure Kubernetes Service +title: Getting Started with Azure Kubernetes Service OCR Processor| Syncfusion +description: Learn how to get started with the Syncfusion Azure Kubernetes Service OCR Processor. Explore setup, features, examples, and customization options. platform: document-processing control: PDF documentation: UG keywords: Assemblies --- -# Perform OCR with Azure Kubernetes Service +# Getting Started with Azure Kubernetes Service OCR Processor The [.NET OCR library](https://www.syncfusion.com/document-sdk/net-pdf-library/ocr-process) can be integrated with external OCR engines like Azure Computer Vision and deployed on Azure Kubernetes Service (AKS) to efficiently process OCR tasks on images and PDF documents at scale. diff --git a/Document-Processing/Data-Extraction/NET/ocr-processor/Azure-Vision.md b/Document-Processing/Data-Extraction/NET/ocr-processor/Azure-Vision.md index 8a2473ae35..b8a351ad55 100644 --- a/Document-Processing/Data-Extraction/NET/ocr-processor/Azure-Vision.md +++ b/Document-Processing/Data-Extraction/NET/ocr-processor/Azure-Vision.md @@ -1,13 +1,13 @@ --- -title: Perform OCR on PDF and image files in Azure Vision | Syncfusion -description: Learn how to perform OCR on scanned PDF documents and images in Azure Vision using Syncfusion .NET OCR library. +title: Getting Started with Azure Vision OCR Processor| Syncfusion +description: Learn how to get started with the Syncfusion Azure Vision OCR Processor. Explore setup, features, examples, and customization options. platform: document-processing control: PDF documentation: UG keywords: Assemblies --- -# Perform OCR with Azure Vision +# Getting Started with Azure Vision OCR Processor The [.NET OCR library](https://www.syncfusion.com/document-sdk/net-pdf-library/ocr-process) supports external OCR engines such as Azure Computer Vision to process OCR on images and PDF documents. diff --git a/Document-Processing/Data-Extraction/NET/ocr-processor/Console.md b/Document-Processing/Data-Extraction/NET/ocr-processor/Console.md index 135bc87bbd..9eb20f988e 100644 --- a/Document-Processing/Data-Extraction/NET/ocr-processor/Console.md +++ b/Document-Processing/Data-Extraction/NET/ocr-processor/Console.md @@ -1,12 +1,12 @@ --- -title: Perform OCR on PDF and image files in Console | Syncfusion -description: Learn how to perform OCR on scanned PDF documents and images with different tesseract versions in a Console App by using the Syncfusion PDF library efficiently +title: Getting Started with Console OCR Processor| Syncfusion +description: Learn how to get started with the Syncfusion Console OCR Processor. Explore setup, features, examples, and customization options. platform: document-processing control: PDF documentation: UG --- -# Perform OCR in Console Application +# Getting Started with Console OCR Processor The [.NET OCR library](https://www.syncfusion.com/document-sdk/net-pdf-library/ocr-process) is used to extract text from scanned PDFs and images in console applications with the help of Google's [Tesseract](https://github.com/tesseract-ocr/tesseract) Optical Character Recognition engine. diff --git a/Document-Processing/Data-Extraction/NET/ocr-processor/Docker.md b/Document-Processing/Data-Extraction/NET/ocr-processor/Docker.md index 5559110c21..f904fcf3e6 100644 --- a/Document-Processing/Data-Extraction/NET/ocr-processor/Docker.md +++ b/Document-Processing/Data-Extraction/NET/ocr-processor/Docker.md @@ -1,12 +1,12 @@ --- -title: Perform OCR on PDF and image files in Docker | Syncfusion -description: Learn how to perform OCR on scanned PDF documents and images in Docker with different tesseract versions using Syncfusion .NET OCR library. +title: Getting Started with Docker OCR Processor| Syncfusion +description: Learn how to get started with the Syncfusion Docker OCR Processor. Explore setup, features, examples, and customization options. platform: document-processing control: PDF documentation: UG keywords: Assemblies --- -# Perform OCR in Docker +# Getting Started with Docker OCR Processor The [.NET OCR library](https://www.syncfusion.com/document-sdk/net-pdf-library/ocr-process) is used to extract text from scanned PDFs and images in Docker applications with the help of Google's [Tesseract](https://github.com/tesseract-ocr/tesseract) Optical Character Recognition engine. diff --git a/Document-Processing/Data-Extraction/NET/ocr-processor/Features.md b/Document-Processing/Data-Extraction/NET/ocr-processor/Features.md index 0ab4d7de94..66e4c5301b 100644 --- a/Document-Processing/Data-Extraction/NET/ocr-processor/Features.md +++ b/Document-Processing/Data-Extraction/NET/ocr-processor/Features.md @@ -1,6 +1,6 @@ --- -title: Perform OCR on PDF and image files | Syncfusion -description: Learn how to perform OCR on scanned PDF documents and images with different tesseract version using Syncfusion .NET OCR library. +title: Perform OCR on PDF and image files in .NET | Syncfusion +description: Learn how to perform OCR on scanned PDF documents and images with different tesseract version using Syncfusion .NET OCR Processor. platform: document-processing control: PDF documentation: UG @@ -9,7 +9,7 @@ keywords: Assemblies # OCR Processor Features -## Performing OCR for an entire document +## Perform OCR on PDF and image files in .NET To perform OCR for an entire PDF document using [PerformOCR](https://help.syncfusion.com/cr/document-processing/Syncfusion.OCRProcessor.OCRProcessor.html#Syncfusion_OCRProcessor_OCRProcessor_PerformOCR_Syncfusion_Pdf_Parsing_PdfLoadedDocument_System_String_) method of the [OCRProcessor](https://help.syncfusion.com/cr/document-processing/Syncfusion.OCRProcessor.OCRProcessor.html) class. Refer to the following code example. diff --git a/Document-Processing/Data-Extraction/NET/ocr-processor/Getting-started-overview.md b/Document-Processing/Data-Extraction/NET/ocr-processor/Getting-started-overview.md index ebbef2f743..301253e7e0 100644 --- a/Document-Processing/Data-Extraction/NET/ocr-processor/Getting-started-overview.md +++ b/Document-Processing/Data-Extraction/NET/ocr-processor/Getting-started-overview.md @@ -1,12 +1,12 @@ --- -title: Getting started with OCR processor | Syncfusion +title: Getting Started with Syncfusion .NET OCR Processor | Syncfusion canonical_url: "https://www.syncfusion.com/document-sdk/net-pdf-library/ocr-process" -description: This section provides an introduction to getting started with the OCR processor and explains the basic concepts and workflow involved +description: Learn about how to getting started with Syncfusion .NET OCR Processor and more details. platform: document-processing control: PDF documentation: UG --- -# Getting started with OCR processor +# About Syncfusion .NET OCR Processor To quickly get started with extracting text from scanned PDF documents in .NET using the .NET OCR processor library, refer to this video tutorial: {% youtube "https://www.youtube.com/watch?v=VhN7ETn0vyA" %} diff --git a/Document-Processing/Data-Extraction/NET/ocr-processor/Linux.md b/Document-Processing/Data-Extraction/NET/ocr-processor/Linux.md index 3f4bece96c..ff3cfde77f 100644 --- a/Document-Processing/Data-Extraction/NET/ocr-processor/Linux.md +++ b/Document-Processing/Data-Extraction/NET/ocr-processor/Linux.md @@ -1,13 +1,13 @@ --- -title: Perform OCR on PDF and image files in Linux | Syncfusion -description: Learn how to perform OCR on scanned PDF documents and images in Linux with different tesseract versions using Syncfusion .NET OCR library. +title: Getting Started with Linux OCR Processor| Syncfusion +description: Learn how to get started with the Syncfusion Linux OCR Processor. Explore setup, features, examples, and customization options. platform: document-processing control: PDF documentation: UG keywords: Assemblies --- -# Perform OCR in Linux +# Getting Started with Linux OCR Processor The [.NET OCR library](https://www.syncfusion.com/document-sdk/net-pdf-library/ocr-process) is used to extract text from scanned PDFs and images in .NET console applications on Linux with the help of Google's [Tesseract](https://github.com/tesseract-ocr/tesseract) Optical Character Recognition engine. diff --git a/Document-Processing/Data-Extraction/NET/ocr-processor/MAC.md b/Document-Processing/Data-Extraction/NET/ocr-processor/MAC.md index 596fe3b556..99a24fbef7 100644 --- a/Document-Processing/Data-Extraction/NET/ocr-processor/MAC.md +++ b/Document-Processing/Data-Extraction/NET/ocr-processor/MAC.md @@ -1,13 +1,13 @@ --- -title: Perform OCR on PDF and Image Files in macOS | Syncfusion -description: Learn how to perform OCR on scanned PDF documents and images in macOS with different Tesseract versions using Syncfusion .NET OCR library. +title: Getting Started with macOS OCR Processor| Syncfusion +description: Learn how to get started with the Syncfusion macOS OCR Processor. Explore setup, features, examples, and customization options. platform: document-processing control: PDF documentation: UG keywords: Assemblies --- -# Perform OCR on macOS +# Getting Started with macOS OCR Processor The [.NET OCR library](https://www.syncfusion.com/document-sdk/net-pdf-library/ocr-process) is used to extract text from scanned PDFs and images in .NET console applications on macOS with the help of Google's [Tesseract](https://github.com/tesseract-ocr/tesseract) Optical Character Recognition engine. diff --git a/Document-Processing/Data-Extraction/NET/ocr-processor/NuGet-Packages-Required.md b/Document-Processing/Data-Extraction/NET/ocr-processor/NuGet-Packages-Required.md index ad6a495572..7fffed2332 100644 --- a/Document-Processing/Data-Extraction/NET/ocr-processor/NuGet-Packages-Required.md +++ b/Document-Processing/Data-Extraction/NET/ocr-processor/NuGet-Packages-Required.md @@ -1,11 +1,11 @@ --- -title: NuGet Packages for OCR | Syncfusion -description: This section illustrates the NuGet packages required to use .NET OCR processor library in various platforms and frameworks +title: NuGet Packages required in .NET OCR Processor | Syncfusion +description: Discover the NuGet packages required to use the Syncfusion .NET OCR Processor across various platforms and frameworks. platform: document-processing control: PDF documentation: UG --- -# NuGet Packages Required for OCR Processor +# NuGet Packages required in .NET OCR Processor To work with the OCR Processor, the following NuGet packages need to be installed in your application from [nuget.org](https://www.nuget.org/). diff --git a/Document-Processing/Data-Extraction/NET/ocr-processor/Troubleshooting.md b/Document-Processing/Data-Extraction/NET/ocr-processor/Troubleshooting.md index ae7f7dc6dc..f8fa42276a 100644 --- a/Document-Processing/Data-Extraction/NET/ocr-processor/Troubleshooting.md +++ b/Document-Processing/Data-Extraction/NET/ocr-processor/Troubleshooting.md @@ -1,13 +1,13 @@ --- -title: Troubleshooting PDF OCR failures | Syncfusion -description: Learn how to overcome OCR Processor failures using Syncfusion .NET OCR library with the help of Google's Tesseract Optical Character Recognition engine. +title: How to troubleshoot failures in .NET OCR Processor | Syncfusion +description: Troubleshoot and overcome OCR Processor failures using the Syncfusion .NET OCR library powered by Google's Tesseract OCR engine. platform: document-processing control: PDF documentation: UG keywords: Assemblies --- -# OCR Processor Troubleshooting +# How to troubleshoot failures in .NET OCR Processor ## Tesseract has not been initialized exception diff --git a/Document-Processing/Data-Extraction/NET/ocr-processor/WPF.md b/Document-Processing/Data-Extraction/NET/ocr-processor/WPF.md index 4d76456e0b..27f262d15f 100644 --- a/Document-Processing/Data-Extraction/NET/ocr-processor/WPF.md +++ b/Document-Processing/Data-Extraction/NET/ocr-processor/WPF.md @@ -1,13 +1,13 @@ --- -title: Perform OCR on PDF and image files in WPF | Syncfusion -description: Learn how to perform OCR on scanned PDF documents and images in WPF with different tesseract version using Syncfusion .NET OCR library. +title: Getting Started with WPF OCR Processor | Syncfusion +description: Learn how to get started with the Syncfusion WPF OCR Processor. Explore setup, features, examples, and customization options. platform: document-processing control: PDF documentation: UG keywords: Assemblies --- -# Perform OCR in WPF (Windows Presentation Foundation) +# Getting Started with WPF OCR Processor The [.NET OCR library](https://www.syncfusion.com/document-sdk/net-pdf-library/ocr-process) is used to extract text from scanned PDFs and images in WPF applications with the help of Google's [Tesseract](https://github.com/tesseract-ocr/tesseract) Optical Character Recognition engine. diff --git a/Document-Processing/Data-Extraction/NET/ocr-processor/Web-API.md b/Document-Processing/Data-Extraction/NET/ocr-processor/Web-API.md index 9ed2178860..1a4bb7d272 100644 --- a/Document-Processing/Data-Extraction/NET/ocr-processor/Web-API.md +++ b/Document-Processing/Data-Extraction/NET/ocr-processor/Web-API.md @@ -1,13 +1,13 @@ --- -title: Perform OCR on PDF and image files in Web API | Syncfusion -description: Learn how to perform OCR on scanned PDF documents and images with different tesseract versions in a Web API by using the Syncfusion PDF library efficiently +title: Getting Started with Web API OCR Processor| Syncfusion +description: Learn how to get started with the Syncfusion Web API OCR Processor. Explore setup, features, examples, and customization options. platform: document-processing control: PDF documentation: UG keywords: pdf, core, web api, csharp --- -# Perform OCR in ASP.NET Core Web API +# Getting Started with Web API OCR Processor The [.NET OCR library](https://www.syncfusion.com/document-sdk/net-pdf-library/ocr-process) is used to extract text from scanned PDFs and images in ASP.NET Core Web API applications with the help of Google's [Tesseract](https://github.com/tesseract-ocr/tesseract) Optical Character Recognition engine. diff --git a/Document-Processing/Data-Extraction/NET/ocr-processor/Windows-Forms.md b/Document-Processing/Data-Extraction/NET/ocr-processor/Windows-Forms.md index 3d6286c86b..5e1d838de1 100644 --- a/Document-Processing/Data-Extraction/NET/ocr-processor/Windows-Forms.md +++ b/Document-Processing/Data-Extraction/NET/ocr-processor/Windows-Forms.md @@ -1,12 +1,12 @@ --- -title: Perform OCR on PDF and image files in Windows Forms | Syncfusion -description: Learn how to perform OCR on scanned PDF documents and images in Windows Forms with different tesseract versions using Syncfusion .NET OCR library. +title: Getting Started with Windows Forms OCR Processor| Syncfusion +description: Learn how to get started with the Syncfusion Windows Forms OCR Processor. Explore setup, features, examples, and customization options. platform: document-processing documentation: UG keywords: Assemblies --- -# Perform OCR in Windows Forms +# Getting Started with Windows Forms OCR Processor The [.NET OCR library](https://www.syncfusion.com/document-sdk/net-pdf-library/ocr-process) is used to extract text from scanned PDFs and images in Windows Forms applications with the help of Google's [Tesseract](https://github.com/tesseract-ocr/tesseract) Optical Character Recognition engine. ## Prerequisites diff --git a/Document-Processing/Data-Extraction/NET/ocr-processor/aspnet-mvc.md b/Document-Processing/Data-Extraction/NET/ocr-processor/aspnet-mvc.md index 42297b05c7..96899ba79d 100644 --- a/Document-Processing/Data-Extraction/NET/ocr-processor/aspnet-mvc.md +++ b/Document-Processing/Data-Extraction/NET/ocr-processor/aspnet-mvc.md @@ -1,13 +1,13 @@ --- -title: Perform OCR on PDF and image files in ASP.NET MVC | Syncfusion -description: Learn how to perform OCR on scanned PDF documents and images with different tesseract versions in ASP.NET MVC using Syncfusion .NET OCR library. +title: Getting Started with ASP .NET MVC OCR Processor | Syncfusion +description: Learn how to get started with the Syncfusion ASP .NET MVC OCR Processor. Explore setup, features, examples, and customization options. platform: document-processing control: PDF documentation: UG keywords: Assemblies --- -# Perform OCR in ASP.NET MVC +# Getting Started with ASP.NET MVC OCR Processor The [.NET OCR library](https://www.syncfusion.com/document-sdk/net-pdf-library/ocr-process) is used to extract text from scanned PDFs and images in ASP.NET MVC applications with the help of Google's [Tesseract](https://github.com/tesseract-ocr/tesseract) Optical Character Recognition engine. diff --git a/Document-Processing/Data-Extraction/NET/ocr-processor/azure.md b/Document-Processing/Data-Extraction/NET/ocr-processor/azure.md index cdb911d3c2..c7c1b0e872 100644 --- a/Document-Processing/Data-Extraction/NET/ocr-processor/azure.md +++ b/Document-Processing/Data-Extraction/NET/ocr-processor/azure.md @@ -1,13 +1,12 @@ --- -title: Perform OCR on PDF and image files in Azure | Syncfusion -description: Learn how to perform OCR on scanned PDF documents and images with different tesseract versions in Azure using Syncfusion .NET OCR library. -platform: document-processing +title: Getting Started with Azure OCR Processor | Syncfusion +description: Learn how to get started with the Syncfusion Azure OCR Processor. Explore setup, features, examples, and customization options. control: PDF documentation: UG keywords: Assemblies --- -# Perform OCR in Azure using C# +# Getting Started with Azure OCR Processor The [.NET OCR library](https://www.syncfusion.com/document-sdk/net-pdf-library/ocr-process) is used to extract text from scanned PDFs and images in Azure with the help of Google's [Tesseract](https://github.com/tesseract-ocr/tesseract) Optical Character Recognition engine. diff --git a/Document-Processing/Data-Extraction/NET/ocr-processor/blazor.md b/Document-Processing/Data-Extraction/NET/ocr-processor/blazor.md index 6cf28ca849..1447dfa3a6 100644 --- a/Document-Processing/Data-Extraction/NET/ocr-processor/blazor.md +++ b/Document-Processing/Data-Extraction/NET/ocr-processor/blazor.md @@ -1,13 +1,13 @@ --- -title: Perform OCR on PDF and image files in Blazor | Syncfusion -description: Learn how to perform OCR on scanned PDF documents and images with different tesseract versions in Blazor using Syncfusion .NET OCR library. +title: Getting Started with Blazor OCR Processor| Syncfusion +description: Learn how to get started with the Syncfusion Blazor OCR Processor. Explore setup, features, examples, and customization options. platform: document-processing control: PDF documentation: UG keywords: Assemblies --- -# Perform OCR in Blazor +# Getting Started with Blazor OCR Processor The [.NET OCR library](https://www.syncfusion.com/document-sdk/net-pdf-library/ocr-process) is used to extract text from scanned PDFs and images in Blazor applications with the help of Google's [Tesseract](https://github.com/tesseract-ocr/tesseract) Optical Character Recognition engine. diff --git a/Document-Processing/Data-Extraction/NET/ocr-processor/how-to-perform-ocr-for-a-pdf-document-using-cSharp-and-VB.md b/Document-Processing/Data-Extraction/NET/ocr-processor/how-to-perform-ocr-for-a-pdf-document-using-cSharp-and-VB.md index 260f0f458b..b3305ae8e9 100644 --- a/Document-Processing/Data-Extraction/NET/ocr-processor/how-to-perform-ocr-for-a-pdf-document-using-cSharp-and-VB.md +++ b/Document-Processing/Data-Extraction/NET/ocr-processor/how-to-perform-ocr-for-a-pdf-document-using-cSharp-and-VB.md @@ -1,12 +1,12 @@ --- title: How to perform OCR for a PDF document using C# and VB.NET | Syncfusion -description: This section explains how to perform OCR for a PDF document using syncfusion .NET OCR library in C# and VB.NET. +description: This section explains how to perform OCR for a PDF document using Syncfusion .NET OCR Processor in C# and VB.NET. platform: document-processing control: PDF documentation: UG --- -# How to perform OCR for a PDF document using C# and VB.NET +# How to perform OCR on a PDF document using C# and VB.NET Essential® PDF provides support for Optical Character Recognition with the help of Google's [Tesseract](https://github.com/tesseract-ocr/tesseract) OCR engine. With a few lines of code, a scanned PDF document containing a raster image is converted into a searchable and selectable PDF document. diff --git a/Document-Processing/Data-Extraction/NET/ocr-processor/how-to-perform-ocr-for-a-pdf-document-using-net-Core.md b/Document-Processing/Data-Extraction/NET/ocr-processor/how-to-perform-ocr-for-a-pdf-document-using-net-Core.md index 09ab0f7fec..0ee5a6fb20 100644 --- a/Document-Processing/Data-Extraction/NET/ocr-processor/how-to-perform-ocr-for-a-pdf-document-using-net-Core.md +++ b/Document-Processing/Data-Extraction/NET/ocr-processor/how-to-perform-ocr-for-a-pdf-document-using-net-Core.md @@ -1,12 +1,12 @@ --- title: How to perform OCR on a PDF document using ASP.Net Core | Syncfusion -description: This section explains how to perform OCR on an entire PDF document using the Syncfusion .NET Core PDF library. +description: This section explains how to perform OCR on an entire PDF document using the Syncfusion .NET OCR Processor. platform: document-processing control: PDF documentation: UG --- -# How to Perform OCR on a PDF Document Using ASP.NET Core +# How to perform OCR on a PDF document using ASP.NET Core Optical Character Recognition (OCR) is a technology that converts scanned paper documents from PDF files or images into searchable and editable data. diff --git a/Document-Processing/Data-Extraction/NET/ocr-processor/net-core.md b/Document-Processing/Data-Extraction/NET/ocr-processor/net-core.md index 1a681f7410..70e378b59c 100644 --- a/Document-Processing/Data-Extraction/NET/ocr-processor/net-core.md +++ b/Document-Processing/Data-Extraction/NET/ocr-processor/net-core.md @@ -1,13 +1,13 @@ --- -title: Perform OCR on PDF and image files in ASP.NET Core | Syncfusion -description: Learn how to perform OCR on scanned PDF documents and images with different tesseract versions in ASP.NET Core using Syncfusion .NET OCR library. +title: Getting Started with ASP.NET Core OCR Processor| Syncfusion +description: Learn how to get started with the Syncfusion ASP .NET Core OCR Processor. Explore setup, features, examples, and customization options. platform: document-processing control: PDF documentation: UG keywords: Assemblies --- -# Perform OCR in ASP.NET Core +# Getting Started with ASP.NET Core OCR Processor The [.NET OCR library](https://www.syncfusion.com/document-sdk/net-pdf-library/ocr-process) is used to extract text from scanned PDFs and images in ASP.NET Core applications with the help of Google's [Tesseract](https://github.com/tesseract-ocr/tesseract) Optical Character Recognition engine. diff --git a/Document-Processing/Data-Extraction/NET/ocr-processor/overview.md b/Document-Processing/Data-Extraction/NET/ocr-processor/overview.md index 1a0c03fe27..4a514a728b 100644 --- a/Document-Processing/Data-Extraction/NET/ocr-processor/overview.md +++ b/Document-Processing/Data-Extraction/NET/ocr-processor/overview.md @@ -1,14 +1,14 @@ --- -title: Perform OCR on PDF features | Syncfusion +title: About Syncfusion .NET OCR Processor | Syncfusion canonical_url: "https://www.syncfusion.com/document-sdk/net-pdf-library/ocr-process" -description: Learn how to perform OCR on scanned PDF documents and images with different tesseract versions using Syncfusion .NET OCR library. +description: Learn about introduction of Syncfusion .NET OCR Processor for recognizing text from scanned images and more details. platform: document-processing control: PDF documentation: UG keywords: Assemblies --- -# Overview of Optical Character Recognition (OCR) +# About Syncfusion .NET OCR Processor Optical character recognition (OCR) is a technology used to convert scanned paper documents in the form of PDF files or images into searchable and editable data. diff --git a/Document-Processing/Data-Extraction/NET/overview.md b/Document-Processing/Data-Extraction/NET/overview.md index 9b942a6347..33202286ff 100644 --- a/Document-Processing/Data-Extraction/NET/overview.md +++ b/Document-Processing/Data-Extraction/NET/overview.md @@ -1,14 +1,14 @@ --- -title: Extract Structured Data in .NET | Syncfusion +title: About Syncfusion .NET Smart Data Extraction Library | Syncfusion canonical_url: "https://www.syncfusioninternal.com/document-sdk/net-pdf-data-extraction" -description: Syncfusion® Data Extraction is a .NET library that extracts tables, forms, text, and images from PDF documents. +description: Learn about introduction of Syncfusion .NET Smart Data Extraction library for extracting data from PDFs or scanned images and more details. platform: document-processing control: DataExtraction documentation: UG keywords: Assemblies --- -# Overview of Smart Data Extractor +# About Syncfusion .NET Smart Data Extraction Library .NET **Smart Data Extractor** is a high‑performance, deterministic C# library for extracting structured document content from **PDFs** and **images**. Tailored for modern .NET workflows, it interprets visual layout patterns—lines, boxes, labels, and alignment—to accurately identify and extract **tables**, **text elements**, **images**, **headers**, **footers**, and **form fields**. Each extracted element includes per‑field confidence scores, ensuring reliable validation, seamless export, and smooth integration into applications. diff --git a/Document-Processing/Data-Extraction/NET/troubleshooting.md b/Document-Processing/Data-Extraction/NET/troubleshooting.md index b0435428a6..22388b729c 100644 --- a/Document-Processing/Data-Extraction/NET/troubleshooting.md +++ b/Document-Processing/Data-Extraction/NET/troubleshooting.md @@ -1,12 +1,12 @@ --- -title: Troubleshoot SmartDataExtractor and SmartTableExtractor in DataExtractor | Syncfusion -description: Troubleshooting steps and FAQs for Syncfusion SmartDataExtractor and SmartTableExtractor to resolve common errors in .NET Framework projects. +title: How to troubleshoot in .NET Smart Data Extractor | Syncfusion +description: Find troubleshooting steps and FAQs for Syncfusion Smart Data Extractor in .NET platforms and frameworks. platform: document-processing control: SmartDataExtractor, SmartTableExtractor documentation: UG --- -# Troubleshooting and FAQ for Smart Data Extractor and Smart Table Extractor +# How to troubleshoot in .NET Smart Data Extractor ## ONNX file missing diff --git a/Document-Processing/Data-Extraction/NET/working-with-data-extraction.md b/Document-Processing/Data-Extraction/NET/working-with-data-extraction.md index de87dbc124..cd243fe57f 100644 --- a/Document-Processing/Data-Extraction/NET/working-with-data-extraction.md +++ b/Document-Processing/Data-Extraction/NET/working-with-data-extraction.md @@ -1,6 +1,6 @@ --- -title: Working with Data Extraction | Syncfusion -description: Syncfusion® Smart Data Extractor is a .NET library that extracts text, tables, forms, and images from PDF and image files with structured outputs. +title: Data Extraction in .NET Smart Data Extractor| Syncfusion +description: Extract text, tables, forms, and images from PDFs and images using Smart Data Extractor. Generate structured output for efficient data processing in .NET. platform: document-processing control: SmartDataExtractor documentation: UG @@ -8,7 +8,7 @@ keywords: Assemblies --- -# Working with Data Extraction +# Data Extraction in .NET Smart Data Extractor ## Extract Data as JSON from PDF or Image diff --git a/Document-Processing/Data-Extraction/NET/working-with-form-recognition.md b/Document-Processing/Data-Extraction/NET/working-with-form-recognition.md index 4b886379b7..e7f025c1e3 100644 --- a/Document-Processing/Data-Extraction/NET/working-with-form-recognition.md +++ b/Document-Processing/Data-Extraction/NET/working-with-form-recognition.md @@ -1,12 +1,12 @@ --- -title: Working with Form Recognition | Syncfusion® -description: Learn how to recognize forms and configure FormRecognizeOptions in Syncfusion® SmartFormRecognizer to detect and process form elements easily. +title: Form Recognition in .NET Smart Data Extractor | Syncfusion +description: Recognize and process form elements from PDF and image files using Smart Form Recognizer. Configure FormRecognizer to extract structured form data accurately in .NET. platform: document-processing control: SmartFormRecognizer documentation: UG --- -# Working with Form Recognition +# Form Recognition in .NET Smart Data Extractor The Syncfusion® Smart Form Recognizer is a C# library for .NET that reliably extracts form data from PDFs and scanned images. It detects text fields, checkboxes, radio buttons, and signature regions. To quickly get started with recognizing form data from PDF and image files using the Smart Form Recognizer library, refer to this video tutorial: diff --git a/Document-Processing/Data-Extraction/NET/working-with-table-extraction.md b/Document-Processing/Data-Extraction/NET/working-with-table-extraction.md index 12f4b2fca7..e4287a4c3f 100644 --- a/Document-Processing/Data-Extraction/NET/working-with-table-extraction.md +++ b/Document-Processing/Data-Extraction/NET/working-with-table-extraction.md @@ -1,13 +1,13 @@ --- -title: Working with Table Extraction | Syncfusion -description: Syncfusion® Smart Table Extractor is a .NET library that extracts structured table data from PDF and image files with confidence scoring. +title: Table Extraction in .NET Smart Data Extractor | Syncfusion +description: Extract structured table data from PDFs and images with Smart Table Extractor. Leverage confidence scoring for accurate and reliable table recognition in .NET. platform: document-processing control: SmartTableExtractor documentation: UG keywords: Table Extraction, PDF, Image, Smart Table Extractor, Assemblies, NuGet Packages --- -# Working with Table Extraction +# Table Extraction in .NET Smart Data Extractor The Syncfusion® Smart Table Extractor is a .NET library used to extract structured table data from PDF and image files. diff --git a/Document-Processing/Data-Extraction/overview.md b/Document-Processing/Data-Extraction/overview.md index fe5401585d..9eadd1dc19 100644 --- a/Document-Processing/Data-Extraction/overview.md +++ b/Document-Processing/Data-Extraction/overview.md @@ -1,13 +1,13 @@ --- -title: Extract Structured Data from PDF and Image Files in .NET | Syncfusion -description: Syncfusion® Smart Data Extractor is a .NET library that extracts tables, forms, text, and images from PDF documents. +title: About Syncfusion Smart Data Extraction Solutions | Syncfusion +description: Learn about introduction of Syncfusion Smart Data Extraction Solutions for extracting data from PDF, Image, Office documents and more details. platform: document-processing control: SmartDataExtractor documentation: UG keywords: Syncfusion.SmartDataExtractor, Syncfusion.SmartTableExtractor, Syncfusion.SmartFormRecognizer, Syncfusion.PDF.OCR --- -# Welcome to Syncfusion Data Extraction Library +# About Syncfusion Smart Data Extraction Solutions Syncfusion® **Smart Data Extractor** is a high‑performance, deterministic C# library for extracting complete document structures from PDFs and images. diff --git a/Document-Processing/Telemetry.md b/Document-Processing/Telemetry.md index 52b80b0c0d..73466bb418 100644 --- a/Document-Processing/Telemetry.md +++ b/Document-Processing/Telemetry.md @@ -1,12 +1,12 @@ --- -title: Telemetry in .NET | Syncfusion -description: Syncfusion® Telemetry collects anonymous usage data in .NET to improve product quality, track feature adoption, and guide product planning. +title: About Syncfusion .NET Telemetry | Syncfusion +description: Learn about introduction of Syncfusion Essential Studio .NET Telemetry and more details. platform: document-processing control: general documentation: UG --- -# Syncfusion® Telemetry +# About Syncfusion .NET Telemetry Syncfusion® Telemetry library collects **anonymous usage data** to improve product quality and user experience. This data helps us better understand product usage, feature adoption, usage trends, and make informed decisions about future product planning. From cbae11da413034c2b3e59f12244abebab70cf584 Mon Sep 17 00:00:00 2001 From: suryaprakash4647 Date: Tue, 18 Aug 2026 13:59:25 +0530 Subject: [PATCH 2/3] Reduced count --- .../NET/ocr-processor/Azure-Kubernetes-Service.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Document-Processing/Data-Extraction/NET/ocr-processor/Azure-Kubernetes-Service.md b/Document-Processing/Data-Extraction/NET/ocr-processor/Azure-Kubernetes-Service.md index 16db1a8e26..850dec45f5 100644 --- a/Document-Processing/Data-Extraction/NET/ocr-processor/Azure-Kubernetes-Service.md +++ b/Document-Processing/Data-Extraction/NET/ocr-processor/Azure-Kubernetes-Service.md @@ -1,5 +1,5 @@ --- -title: Getting Started with Azure Kubernetes Service OCR Processor| Syncfusion +title: Getting Started with Azure Kubernetes OCR Processor | Syncfusion description: Learn how to get started with the Syncfusion Azure Kubernetes Service OCR Processor. Explore setup, features, examples, and customization options. platform: document-processing control: PDF From e787f2bc8e1e164f131e3755b6aad96ab9cbb3db Mon Sep 17 00:00:00 2001 From: suryaprakash4647 Date: Tue, 18 Aug 2026 18:43:39 +0530 Subject: [PATCH 3/3] Resolved compilation error --- .../NET/conversions/pdf-to-json.md | 2 +- .../ocr-processor/Getting-started-overview.md | 2 +- ...-for-a-pdf-document-using-cSharp-and-VB.md | 153 ------------------ ...m-ocr-for-a-pdf-document-using-net-Core.md | 124 -------------- .../NET/working-with-form-recognition.md | 2 +- 5 files changed, 3 insertions(+), 280 deletions(-) delete mode 100644 Document-Processing/Data-Extraction/NET/ocr-processor/how-to-perform-ocr-for-a-pdf-document-using-cSharp-and-VB.md delete mode 100644 Document-Processing/Data-Extraction/NET/ocr-processor/how-to-perform-ocr-for-a-pdf-document-using-net-Core.md diff --git a/Document-Processing/Data-Extraction/NET/conversions/pdf-to-json.md b/Document-Processing/Data-Extraction/NET/conversions/pdf-to-json.md index d8ba6736f5..7c9cbfa71d 100644 --- a/Document-Processing/Data-Extraction/NET/conversions/pdf-to-json.md +++ b/Document-Processing/Data-Extraction/NET/conversions/pdf-to-json.md @@ -1,6 +1,6 @@ --- title: Convert PDF to JSON in .NET Smart Data Extractor | Syncfusion -description: Extract structured data from PDF documents as JSON using Smart Data Extractor. Convert PDF content into machine-readable JSON format seamlessly in .NET applications. +description: Extract structured data from PDF documents as JSON using Smart Data Extractor. platform: document-processing control: SmartDataExtractor documentation: UG diff --git a/Document-Processing/Data-Extraction/NET/ocr-processor/Getting-started-overview.md b/Document-Processing/Data-Extraction/NET/ocr-processor/Getting-started-overview.md index 301253e7e0..cdaac99498 100644 --- a/Document-Processing/Data-Extraction/NET/ocr-processor/Getting-started-overview.md +++ b/Document-Processing/Data-Extraction/NET/ocr-processor/Getting-started-overview.md @@ -6,7 +6,7 @@ platform: document-processing control: PDF documentation: UG --- -# About Syncfusion .NET OCR Processor +# About Syncfusion .NET OCR Processor Library To quickly get started with extracting text from scanned PDF documents in .NET using the .NET OCR processor library, refer to this video tutorial: {% youtube "https://www.youtube.com/watch?v=VhN7ETn0vyA" %} diff --git a/Document-Processing/Data-Extraction/NET/ocr-processor/how-to-perform-ocr-for-a-pdf-document-using-cSharp-and-VB.md b/Document-Processing/Data-Extraction/NET/ocr-processor/how-to-perform-ocr-for-a-pdf-document-using-cSharp-and-VB.md deleted file mode 100644 index b3305ae8e9..0000000000 --- a/Document-Processing/Data-Extraction/NET/ocr-processor/how-to-perform-ocr-for-a-pdf-document-using-cSharp-and-VB.md +++ /dev/null @@ -1,153 +0,0 @@ ---- -title: How to perform OCR for a PDF document using C# and VB.NET | Syncfusion -description: This section explains how to perform OCR for a PDF document using Syncfusion .NET OCR Processor in C# and VB.NET. -platform: document-processing -control: PDF -documentation: UG ---- - -# How to perform OCR on a PDF document using C# and VB.NET - -Essential® PDF provides support for Optical Character Recognition with the help of Google's [Tesseract](https://github.com/tesseract-ocr/tesseract) OCR engine. With a few lines of code, a scanned PDF document containing a raster image is converted into a searchable and selectable PDF document. - -N> Starting with v20.1.0.x, if you reference Syncfusion® OCR processor assemblies from trial setup or from the NuGet feed, you also have to include a license key in your projects. Please refer to this [link](https://help.syncfusion.com/common/essential-studio/licensing/overview) to know about registering Syncfusion® license key in your application to use our components. - -To use the .NET OCR processor library in your application, you need to add reference to the following set of assemblies. - -Syncfusion assemblies -1. Syncfusion.Compression.Base.dll -2. Syncfusion.Pdf.Base.dll -3. Syncfusion.OcrProcessor.Base.dll - -Tesseract assemblies -* Syncfusion.Tesseract.dll (Tesseract Engine Version 4.0) -* liblept168.dll (Leptonica image processing library used by Tesseract engine) - -## Steps to perform OCR on a entire PDF document programmatically - -1.Create a new C# Windows Forms application project. -WF sample creation step1 - -2.Install [Syncfusion.Pdf.OCR.WinForms](https://www.nuget.org/packages/Syncfusion.PDF.OCR.WinForms/) NuGet packages as reference to your .NET Framework application from [NuGet.org](https://www.nuget.org/). -Install NuGet - -3.Include the following namespaces in the Form1.cs file. - -{% tabs %} - -{% highlight c# tabtitle="C#" %} - -using Syncfusion.Pdf.Parsing; -using Syncfusion.OCRProcessor; - -{% endhighlight %} - -{% highlight c# tabtitle="VB.NET" %} - -Imports Syncfusion.Pdf.Parsing -Imports Syncfusion.OCRProcessor - -{% endhighlight %} - -{% endtabs %} - -4.Tesseract assemblies are not added as a reference. They must be kept in the local machine, and the location of the assemblies are passed as a parameter to the OCR processor. - -{% tabs %} - -{% highlight c# tabtitle="C#" %} - -OCRProcessor processor = new OCRProcessor(@"TesseractBinaries/") - -{% endhighlight %} - -{% highlight vb.net tabtitle="VB.NET" %} - -Dim processor As New OCRProcessor("TesseractBinaries/") - -{% endhighlight %} - -{% endtabs %} - -5.Place the Tesseract language data {E.g eng.traineddata} in the local system and provide a path to the OCR processor. - -{% tabs %} - -{% highlight c# tabtitle="C#" %} - -OCRProcessor processor = new OCRProcessor(@"TesseractBinaries/"); -processor.PerformOCR(lDoc, @"TessData/"); - -{% endhighlight %} - -{% highlight vb.net tabtitle="VB.NET" %} - -Dim processor As New OCRProcessor("TesseractBinaries/") -processor.PerformOCR(lDoc, "TessData/") - -{% endhighlight %} - -{% endtabs %} - -6.Use the following code snippet to process OCR on a entire PDF document. - -{% tabs %} - -{% highlight c# tabtitle="C#" %} - -//Initialize the OCR processor by providing the path of tesseract binaries(SyncfusionTesseract.dll and liblept168.dll) -using (OCRProcessor processor = new OCRProcessor("TesseractBinaries/4.0/x86/")) -{ - //Load the PDF document - PdfLoadedDocument loadedDocument = new PdfLoadedDocument("Input.pdf"); - - //Set OCR language to process - processor.Settings.Language = Languages.English; - - //Set the tesseract version - processor.Settings.TesseractVersion = TesseractVersion.Version4_0; - - //Process OCR by providing the PDF document and Tesseract data - processor.PerformOCR(loadedDocument, "Tessdata/"); - - //Save the OCR processed PDF document in the disk - loadedDocument.Save("Sample.pdf"); - loadedDocument.Close(true); -} - -{% endhighlight %} - -{% highlight vb.net tabtitle="VB.NET" %} - -'Initialize the OCR processor by providing the path of tesseract binaries(SyncfusionTesseract.dll and liblept168.dll) -Using processor As OCRProcessor = New OCRProcessor("TesseractBinaries/4.0/x86/") - - 'Load the PDF document - Dim loadedDocument As PdfLoadedDocument = New PdfLoadedDocument("Input.pdf") - - 'Set OCR language to process - processor.Settings.Language = Languages.English - - 'Set the tesseract version - processor.Settings.TesseractVersion = TesseractVersion.Version4_0 - - 'Process OCR by providing the PDF document and Tesseract data - processor.PerformOCR(loadedDocument, "Tessdata/") - - 'Save the OCR processed PDF document in the disk - loadedDocument.Save("Sample.pdf") - loadedDocument.Close(True) - -End Using - -{% endhighlight %} - -{% endtabs %} - -You can download a complete working sample from [GitHub](https://github.com/SyncfusionExamples/PDF-Examples/tree/master/OCR/.NET%20Framework/Windows%20Forms). - -By executing the program, you will get the PDF document (contains selectable text) as follows. -![output-pdf](OCR-Images/OCR-output-image.png) - - - diff --git a/Document-Processing/Data-Extraction/NET/ocr-processor/how-to-perform-ocr-for-a-pdf-document-using-net-Core.md b/Document-Processing/Data-Extraction/NET/ocr-processor/how-to-perform-ocr-for-a-pdf-document-using-net-Core.md deleted file mode 100644 index 0ee5a6fb20..0000000000 --- a/Document-Processing/Data-Extraction/NET/ocr-processor/how-to-perform-ocr-for-a-pdf-document-using-net-Core.md +++ /dev/null @@ -1,124 +0,0 @@ ---- -title: How to perform OCR on a PDF document using ASP.Net Core | Syncfusion -description: This section explains how to perform OCR on an entire PDF document using the Syncfusion .NET OCR Processor. -platform: document-processing -control: PDF -documentation: UG ---- - -# How to perform OCR on a PDF document using ASP.NET Core - -Optical Character Recognition (OCR) is a technology that converts scanned paper documents from PDF files or images into searchable and editable data. - -The [.NET OCR processor library](https://www.syncfusion.com/document-processing/pdf-framework/net/pdf-library/ocr-process) has extended support to process OCR on scanned PDF documents and other scanned images in the .NET Core platform with the help of the [Tesseract](https://github.com/tesseract-ocr/tesseract) OCR engine. - -## Steps to perform OCR on a PDF document programmatically - -1.Create a new C# ASP.NET Core Web application project. - .NET Core sample creation step1 - -2.In the project configuration window, name your project and select Next. - .NET Core sample creation step2 - .NET Core sample creation step3 - -3.Install the [Syncfusion.PDF.OCR.Net.Core](https://www.nuget.org/packages/Syncfusion.PDF.OCR.Net.Core/) NuGet package as a reference to your .NET Standard application from [nuget.org](https://www.nuget.org/). - Installation of .NET Core NuGet package - -4.Tesseract assemblies are not added as a reference. They must be kept in the local machine, and the location of the assemblies is passed as a parameter to the OCR processor. -{% tabs %} - -{% highlight c# tabtitle="C#" %} - -OCRProcessor processor = new OCRProcessor(@"TesseractBinaries\") - -{% endhighlight %} - -{% endtabs %} - -5.Place the Tesseract language data {E.g eng.traineddata} in the local system and provide a path to the OCR processor. Please use the OCR language data for other languages using the following link, -https://github.com/tesseract-ocr/tessdata - -{% tabs %} - -{% highlight c# tabtitle="C#" %} - -OCRProcessor processor = new OCRProcessor("Tesseractbinaries\"); -processor.PerformOCR(loadedDocument, "tessdata/"); - -{% endhighlight %} - -{% endtabs %} - -6.A default action method named Index will be present in HomeController.cs. Right-click on Index method and select Go to View, where you will be directed to its associated view page Index.cshtml. -7.Add a new button in the Index.cshtml as shown below. - -{% highlight c# tabtitle="C#" %} - -@{Html.BeginForm("PerformOCR", "Home", FormMethod.Get); - { -
- -
- } - Html.EndForm(); -} - -{% endhighlight %} - -8.A default controller with name HomeController.cs is added to the creation of ASP.NET Core project. Include the following namespaces in that HomeController.cs file. -{% tabs %} - -{% highlight c# tabtitle="C#" %} - -using Syncfusion.Pdf.Parsing; -using Syncfusion.OCRProcessor; -using System.Drawing; - -{% endhighlight %} - -{% endtabs %} - -10.Use the following code sample to perform OCR in the ASP.NET Core application. -{% tabs %} - -{% highlight c# tabtitle="C#" %} - -//Load PDF document as stream -string docPath = _hostingEnvironment.WebRootPath + "/Data/Input.pdf"; -FileStream docStream = new FileStream(docPath, FileMode.Open, FileAccess.Read); -//Load the PDF document -PdfLoadedDocument loadedDocument = new PdfLoadedDocument(docStream); -string tesseractPath = _hostingEnvironment.WebRootPath + "/Data/Tesseractbinaries/Windows"; -//Initialize the OCR processor by providing the path of tesseract binaries -using (OCRProcessor processor = new OCRProcessor(tesseractPath)) -{ - //Language to process the OCR - processor.Settings.Language = Languages.English; - - string tessdataPath = _hostingEnvironment.WebRootPath + "/Data/tessdata/"; - //Process OCR by providing loaded PDF document, Data dictionary and language - processor.PerformOCR(loadedDocument, tessdataPath); -} -//Saving the PDF to the MemoryStream -MemoryStream stream = new MemoryStream(); -loadedDocument.Save(stream); -//Close the PDF document -loadedDocument.Close(true); -//Set the position as '0' -stream.Position = 0; -//Download the PDF document in the browser -FileStreamResult fileStreamResult = new FileStreamResult(stream, "application/pdf"); -fileStreamResult.FileDownloadName = "Sample.pdf"; -return fileStreamResult; - -{% endhighlight %} - -{% endtabs %} - -A complete working sample can be downloaded from [GitHub](https://github.com/SyncfusionExamples/PDF-Examples/tree/master/OCR/.NET%20Core). - -By executing the program, you will get the text file (contains extracted text) as follows. -![output pdf](OCR-images/OCR-output-image.png) - - - diff --git a/Document-Processing/Data-Extraction/NET/working-with-form-recognition.md b/Document-Processing/Data-Extraction/NET/working-with-form-recognition.md index 31ffff7fd0..d3a535447d 100644 --- a/Document-Processing/Data-Extraction/NET/working-with-form-recognition.md +++ b/Document-Processing/Data-Extraction/NET/working-with-form-recognition.md @@ -1,6 +1,6 @@ --- title: Form Recognition in .NET Smart Data Extractor | Syncfusion -description: Recognize form elements from PDF and scanned images using Smart Form Recognizer. Configure FormRecognizer to extract structured form data accurately in .NET. +description: Recognize form elements from PDF and scanned images using Smart Form Recognizer. platform: document-processing control: SmartFormRecognizer documentation: UG