Halcon字符识别专题

先开个篇,后期逐步加入

1、注重识别准确率的,用cnn。

对应案例及关键代码

do_ocr_word_cnn (CharRegion, CharImage, OCRHandleCNN, '[a-z.]', 3, 2, ClassRead, Confidence, ClassCorrectedReadCNN, Score)

do_ocr_single_class_cnn (ObjectSelected, ImageInvert, OCRHandle, 1, Class, Confidence)

*创建候选字符
create_lexicon ('label', ['BEST','BEFORE','END'], LexiconHandle)
*识别结果会从候选字符中选取最相似的作为结果
do_ocr_word_cnn (Word, ImageOCR, OCRHandle, '<label>', 1, 5, Class, Confidence, WordText, WordScore)

do_ocr_word_cnn (SortedDate, ImageOCR, OCRHandle, '^([0-2][0-9]|30|31)/(0[1-9]|10|11|12)/0[0-5]$', 10, 5, Class, Confidence, DateText, DateScore)

 

posted @ 2022-08-12 17:27  夕西行  阅读(285)  评论(0编辑  收藏  举报