Strength of Dictionary in Tesseract 3

匿名 (未验证) 提交于 2019-12-03 08:39:56

问题:

How do I increase/decrease the strength of the dictionary in tesseract 3 ?

In the FAQ it says I need to change the value of "NON_WERD" and "GARBAGE_STRING" but they do not exist in Tesseract 3.

回答1:

According to http://code.google.com/p/tesseract-ocr/wiki/FAQ, you change these variables:

enable_new_segsearch    1 language_model_penalty_non_freq_dict_word 0.2 language_model_penalty_non_dict_word 0.3 

Increase their values to make Tesseract more biased to dictionary words.

Note: You must set enable_new_segsearch, otherwise they'll have no effect.



回答2:

To turn tesseract's language-knowing abilities entirely, run each of these:

tess.setTessVariable("load_system_dawg", "false"); tess.setTessVariable("load_freq_dawg", "false"); tess.setTessVariable("load_punc_dawg", "false"); tess.setTessVariable("load_number_dawg", "false"); tess.setTessVariable("load_unambig_dawg", "false"); tess.setTessVariable("load_bigram_dawg", "false"); tess.setTessVariable("load_fixed_length_dawgs", "false"); 

Or, for finer control, just some of them. (I don't know of a place explaining well what they all do, but the names are pretty explanatory) This is code from my current project, using Tess4J, but you can easily translate them to c++ or a config file or whatever else you need.



标签
易学教程内所有资源均来自网络或用户发布的内容,如有违反法律规定的内容欢迎反馈
该文章没有解决你所遇到的问题?点击提问,说说你的问题,让更多的人一起探讨吧!