Hi everyone. Using the tesseract to recognize a racing number has been training.
However, an error occurs as follows: If I train any image. ------------------------------------- FAIL! APPLY_BOXES: boxfile line 1/7 ((69,48),(111,151)): FAILURE! Couldn't find a matching blob FAIL! APPLY_BOXES: boxfile line 2/1 ((129,48),(142,151)): FAILURE! Couldn't find a matching blob FAIL! APPLY_BOXES: boxfile line 3/4 ((160,48),(200,151)): FAILURE! Couldn't find a matching blob FAIL! APPLY_BOXES: boxfile line 4/5 ((205,48),(245,151)): FAILURE! Couldn't find a matching blob FAIL! APPLY_BOXES: boxfile line 5/6 ((248,48),(287,151)): FAILURE! Couldn't find a matching blob APPLY_BOXES: Boxes read from boxfile: 6 Boxes failed resegmentation: 5 Found 1 good blobs. Leaving 3 unlabelled blobs in 0 words. ------------------------------------- The following is a result of creating a box file for training the "G71456" from original.jpg file attached. ~ 7 0 300 225 0 I was modified as follows: G 10 48 60 151 0 7 69 48 111 151 0 1 129 48 142 151 0 4 160 48 200 151 0 5 205 48 245 151 0 6 248 48 287 151 0 Then, the above error when creating a tr file has occurred. Unusual is edit.jpg taken only at the "G71456" from original.jpg can successfully training. However, the traineddata can not recognize original.jpg. Why do this? I do not understand. Maybe because original.jpg are mixed are various characters? How to properly train is original.jpg? Any ideas? Thanks! -- 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 https://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/b7745b5e-2b2e-4b40-b53a-38189fd9b839%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
