OCR-Form-Tools

microsoft/OCR-Form-Tools is ranked 17,429 among these 8 peers; opendilab/CleanS2S is ranked 17,431.

Form OCR Testing Tool Help us improve Form Recognizer. Features Preview An open source labeling tool for Form Recognizer, part of the Form OCR Test Toolset (FOTT). It contains all the newest features available. This is **NOT** the most stable version since this is a preview. The purpose of this repo is to allow customers to test the tools available when working with Microsoft Forms and OCR services. Currently, Labeling tool is the first tool we present here. Users could

provide feedback, and make customer-specific changes to meet their unique needs. Microsoft Azure Form Recognizer team will update the source code periodically. If you would like to contribute, please check the contributing section. **If you want to checkout our latest GA version, please go to Form-Recognizer-Toolkit, or use Form Recognizer Studio. 1 GA version of the tool, please follow this link. 0 GA version of the tool, please follow this link. ** ___ FOTT's Labeling Tool is a React

+ Redux Web application, written in TypeScript. This project was bootstrapped with Create React App. Current Features of Labeling Tool: (you can view a short demo here) **Label** forms in PDF, JPEG or TIFF formats. **Train** model with labeled data through Form Recognizer **Predict/Analyze** a single form with the trained model, to extract key-value predictions/analyses for the form. Getting Started Build and run from source Form Labeling Tool requires NodeJS (>= 10. x, Dubnium) and NPM Set up this

tool with Docker Please see instructions here, and view our docker hub repository here for the latest container image info. docker image tags track the general availability releases of FOTT. , docker image tags track the preview releases of FOTT. , docker image tags track the private preview releases of FOTT. Run as web application Using a modern Web browser, FOTT can be run directly at: **Note: these web app are for testing purpose only. HTTPS is required, unless it's for localhost

. ** Run as desktop application FOTT can be run as a desktop application after initial set up. The desktop application has additional features, such as: Support for local file system as provider storage Support for cross-domain resource requests Release as desktop application FOTT can be released as a distributable desktop application. The distributable will saved in the releases folder of the cloned repository. Using labeling tool Set up input data To go thru a complete label-train-analyze scenario, you

need a set of at least six forms of the same type. You will label five forms to train a model and one form to test the model. You could upload the sample files to the root of a blob storage container in an Azure Storage account. You can use Azure Storage Explorer to upload data. For advanced scenarios where there are forms in quite different formats, you could organize them into subfolders based on similar format. When you set

up your project to train a model from one format, you need to specify a subfolder in the project setting