tesseract

Tesseract is a comprehensive Optical Character Recognition (OCR) package consisting of the `libtesseract` library and a `tesseract` command-line program. It supports Unicode (UTF-8) and can recognize over 100 languages out of the box, with the ability to be trained for additional languages. Key technical capabilities include: - OCR Engines: Features a modern neural network (LSTM) based engine focused on line recognition, while maintaining compatibility with the legacy character-pattern recognition engine (Tesseract 3). - Input Support: Compatible with various image formats including PNG, JPEG, and TIFF via the Leptonica library. - Output Formats: Supports multiple output types, including plain text, hOCR (HTML), PDF (including invisible-text-only), TSV, ALTO, and PAGE. - Developer Integration: Provides C and C++ APIs for building custom applications, with various wrappers available for other programming languages. Tesseract is a non-GUI tool; users requiring a graphical interface must use third-party applications. It is licensed under the Apache License 2.0.