I'm using two traineddata files in tesseract in order to recognize two languages. But because the accuracy wasn't good enough, I trained tesseract and produce a new traineddata file which I want to merge it with one of the two language files I use. So my question is: How can it be possible to merge the new traineddata file with one of the files that is found here: https://code.google.com/p/tesseract-ocr/downloads/list .Any help?
可以将文章内容翻译成中文,广告屏蔽插件可能会导致该功能失效(如失效,请关闭广告屏蔽插件后再试):
问题:
回答1:
You can unpack the existing .traineddata
and merge the components separately; however, I'm not sure that's going to work. You can create your ell1.traineddata
and specify it together with the existing one at the command line, such as:
tesseract image output -l ell+ell1