This program is early in development and should be considered in alpha stages.

An editor for generating and editing hOCR files from scanned documents.

The editor aims to provide a set of tools for convenient visual editing of automatically generated hOCR files that require some manual processing.

Some icons by Yusuke Kamiyamane. Licensed under a Creative Commons Attribution 3.0 License.

• An installation of Tesseract OCR is required. Installation instructions for Tesseract can be found here.