i am using a tesseract wrapper for c# (from charls, prerelease virsion), and it uses tesseract 4. Somehow the picture i am passing is clean, but it's giving wrong results in case of letter 'S', wrongly detects it as '5' or sometimes 'S5' i am using following configurations data used - tessdata-best following flags- load_system_dawg F load_freq_dawg F user_words_suffix user-words user_patterns_suffix user-patterns PSM mode - SingleWord EngineMode - default i can go for training the tesseract but seems my usecase is not that difficult to detect following are the images and corresponding wrong text
[image: first.jpg] wrong text detected -W22754 [image: sec.jpg] wrong text detected -W21351-2 [image: third.jpg] wrong text detected -226S51 i guess these pictures are of fine quality using 300 dpi, still getting wrong results please help if anyone find any flaw in cofig or something else. thanks in advance. -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To unsubscribe from this group and stop receiving emails from it, send an email to tesseract-ocr+unsubscr...@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/c0de11f6-0b46-490b-b5f2-f96ab777f09en%40googlegroups.com.