> For the complete documentation index, see [llms.txt](https://docs.apryse.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.apryse.com/template-extraction/template-extraction/readme.md). # Template Extraction Library Harness the power of Apryse's Template Extraction SDK for .NET to classify and extract scanned documents effortlessly. Sign up for a free trial now! Apryse Template Extraction SDK on .NET uses intelli Apryse Template Extraction is a high-level .NET SDK that harnesses the power of Apryse's intelligently identifying document components and features that can be used to classify and extract scanned documents. The Template Extraction module can even be used to define recognition boxes for automatic extraction of any part of a template. **Template Extraction** **Library Benefits include:** * High level classes allow adding template classification with very little code. * Flexible automatic classification engine can be customized to use customized Barcode, OCR, line detection, and special object detection (such as logos, text blocks, and shapes). * Let's you define multi-page templates for classification and extraction. * Stores any number of pre-defined templates. * Classifies forms at both form and page level, so you can compare an image to any form page or compare a complete multi-page form to any predefined master form. * Classifies any number of regions or objects on a page. * Let's you define, include, and exclude regions of interest in the template. * Supports a variety of data fields such as: text, OMR, image, and Barcode. * Enables manual feature weighting for improved classification performance. * Generates comprehensive results and confidence level reports to assess performance. ## Get started [Sign up for a free trial license](https://apryse.com/capabilities/extraction/template-extraction#form-fill-te) [Create Template File](/template-extraction/template-extraction/create-template.md) Use the Template designer to create the templates. [Extract Templated Data](/template-extraction/template-extraction/extract-data.md) After classifying the associated template to a file, The Template Extraction SDK allows you to extract data from the input file based on the template, including support for different types of deformation for the data layout between the template and the input file. The extracted data is determined by the Fields inside the template. [Classify File Against Templates](/template-extraction/template-extraction/classify-file.md) The Template Extraction SDK allows you to classify an input file against group of templates. [Create Classification Cache](/template-extraction/template-extraction/create-classification-cache.md) To speed up the classification of an input file against many templates, the SDK provides a way to create a cache data that will be used if present to classify the correct template fast. [Use Classify Catalogue to Speed Up Classification](/template-extraction/template-extraction/classify-catalogue.md) If you have generated cache to optimize the classification speed, you can utilize it by calling \`EnableCacheLookup(true)\` for \`TemplateClassifier.Builder\`. [Template Designer Application Guide](/template-extraction/template-extraction/designer.md) This guide demonstrates how to create a new template, edit an existing one, and test classification with these templates using the Template Designer Sample Application. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.apryse.com/template-extraction/template-extraction/readme.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.