I added language_model_penalty_non_dict_word 3.00 to my config file. No changes in x_wconf values.
On Thursday, May 1, 2014 10:14:22 AM UTC-4, Donald Winston wrote: > > I added "user_words_suffix user-words" to "configs/hocr" where > tessdata/eng.user-words contains some "extra" words to try and increase the > x_wconf values that are reported. > > This did not improve the x_wconf values. They remained the same. Can > someone give me a short explanation as to why? (I'm assuming the user-words > technique is working. Maybe not?) > > These are some of the words: > Triethyleneglycol > Monolauryl > Sorbitari > Polysorbate > oxides (for some reason this had a relatively low conf value) > mixed (for some reason this had a relatively low conf value) > Polyethoxyethanol > octylphenoxy > > Are these x_wconf values not sensitive to merely word matching? > -- 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 [email protected]. To post to this group, send email to [email protected]. Visit this group at http://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/8ba59ab4-f0e2-4115-b11d-46242d7681cd%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
