对开源OCR做一个简单的调研，网上找到的关于OCR的一些资料：
国内参考资料：
最好的开源或开放API的ocr引擎是什么？
https://www.zhihu.com/question/22417946
列举了4中OCR
目录：
1. Tesseract-OCR (Google)
2. Azure (Microsoft)
3. ABBYY Real-Time Recognition SDK
4. ocr space
OCR：几大开源库
http://blog.csdn.net/qianliheshan/article/details/48974927
OCR 中文识别用哪种软件识别率比较高？
https://www.zhihu.com/question/19593313
OCR识别的开源分析
http://blog.csdn.net/luojun2007/article/details/51614133
国外资料：
What are the best open source OCR libraries?
https://www.quora.com/What-are-the-best-open-source-OCR-libraries
Are you looking for programming libraries or even OCR software works for you ?
OCR libraries
1) Python pyocr and tesseract ocr over python
2) Using R language ( Extracting Text from PDFs; Doing OCR; all within R )
Free OCR Softwares
1. Google’s & HP’s Tesseract
2. Google’s Keep
3. Microsoft Document Imaging ( MODI ) ( assuming majority of us would be having a windows OS )
4. Microsoft One Note
5. Microsoft Oxford Project API ( This API is free until some time )
6. FreeOCR ( This is based on Tesseract engine again )
There are lot more but these are the best and out of all these, if you are looking for accuracy , Microsoft Document Imaging does better job. And if you are looking for hand written text ocr conversion then Google’s Keep does better job.
Commercial Products
1. Adobe Acrobat Pro ( RTF file format gives you best result )
2. Captiva
3. Abbyy
4. Informatica ( Not sure which module within Informatica )
5. IBM Datacapture (Datacap) (IBM Watson)
If accuracy is only your main constraint, there is something like Unprecedented Data Access at your Service( captricity ) which boasts of 99% accuracy since they crowd source people and make them convert hand written text without compromising security.
关于Tesseract-OCR (Google)
支持100多种语言，自带的库识别率不高，但是关键是可以自己训练来改善识别率。提供支持 C 和 C++ 的API。目前使用的最多。
关于安装、使用、训练等详细说明可以参见GitHub：https://github.com/tesseract-ocr/
