OCR开源代码以及OCR公开训练测试数据集汇总

1 OCR开源代码网址汇总

1.1 OCRE(OCR Easy), http://lem.eui.upm.es/ocre.html

1.2 Clara OCR,http://directory.fsf.org/claraocr.html

1.3 OCRAD,http://directory.fsf.org/ocrad.html

1.4 JOCR,http://sourceforge.net/projects/jocr

1.5 OCR-CHIE,http://http.cs.berkeley.edu/~fateman/kathey/ocrchie.html

1.6 TESSERACT-OCR,http://code.google.com/p/tesseract-ocr/

1.7 OCR,http://www.ocrspace.com/ocr-download.html



2 OCR公开训练测试数据集合网址汇总



2.1 ICDAR(International Conference on Document Analysis and Recognition) 2011 - About Robust Reading Competition

Reading Text in Born-Digital Images (Web and Email)

http://www.cvc.uab.es/icdar2011competition/



Reading Text in Scene Images

http://robustreading.opendfki.de/wiki/SceneText



2.2 ICDAR 2013 - About Robust Reading Competition

Reading Text in Born-Digital Images (Web and Email)

http://dag.cvc.uab.es/icdar2013competition/?ch=1&com=downloads



Reading Text in Scene Images

http://dag.cvc.uab.es/icdar2013competition/?ch=2&com=downloads



Reading Text in videos

http://dag.cvc.uab.es/icdar2013competition/?ch=3&com=downloads



2.3 UCI - Letter Recognition (Database of character image features; try to identify the letter)

http://archive.ics.uci.edu/ml/datasets/Letter+Recognition



2.4 MNIST - Data Base

http://yann.lecun.com/exdb/mnist/



2.5 USPS - Handwritten digit data

http://www.gaussianprocess.org/gpml/data/