sakarika / kanjitomo-ocr

Java library for identifying Japanese characters from images
Other
188 stars 22 forks source link

kanjitomo-ocr

Introduction

KanjiTomo OCR is a Java library for identifying Japanese characters from images. The algorithm used in this library is custom made, originally used with KanjiTomo program: https://www.kanjitomo.net/ Description of the algorithm is here.

This library is intented to be used with interactive programs where user can point to individual words with a mouse. Batch-processing whole pages is not supported.

Installation

Usage

Example

KanjiTomo tomo = new KanjiTomo();
tomo.loadData();
BufferedImage image = ImageIO.read(new File("file.png"));
tomo.setTargetImage(image);
OCRResults results = tomo.runOCR(new Point(80,40));
System.out.println(results);

License

KanjiTomo is free to use for non-commercial purposes. License file is here

Credits

KanjiTomo has been created by Sakari Kääriäinen. You can contact me at kanjitomo(at)gmail.com

Acknowledgements

EDICT, ENAMDICT and KANJIDIC dictionaries are the property of the Electronic Dictionary Research and Development Group, and are used in conformance with the Group's licence.
https://www.edrdg.org/jmdict/edict.html

imgscalr library by Riyad Kalla
https://github.com/rkalla/imgscalr

Unsharp Mask code by Romain Guy
http://www.java2s.com/Code/Java/Advanced-Graphics/UnsharpMaskDemo.htm

Kryo library by EsotericSoftware
https://github.com/EsotericSoftware/kryo