Hi there, I am using Tesseract 3.01 under Linux.
I can successfully create traineddata from one *.tif file. But combining different tif / box files give me an exception: What are the steps: Let's say I want to create a traineddata from two tif files: 01.tif and 02.tif 1. tesseract 01.tif 01 batch.nochop makebox 2. tesseract 02.tif 02 batch.nochop makebox 3. I check the two box files using jTessBoxEditor 4. tesseract 01.tif 01 nobatch box.train 5. tesseract 02.tif 02 nobatch box.train 6. As described under http://wiki.ubuntuusers.de/tesseract-ocr/tesseract-ocr_trainieren (sorry: it is on German, but the commands are the same) I create the *.tr files: 7. mftraining 01.tr 02.tr But this results in error: Reading 01.tr ...01 has no defined properties. !"Missing font_properties entry is a fatal error!":Error:Assert failed:in file mftraining.cpp, line 287 Segmentation fault Also trying to create unicharset with unicharset_extractor 01.box 02.box works successfully, but mftraining -U ./unicharset 01.tr 02.tr fails with the same error. Somebody has an idea what I am doing wrong. Also using the group e.g. with the search word "combine" did not result in any fitting solution. Thanks for any advice, Holm from Germany -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To post to this group, send email to tesseract-ocr@googlegroups.com To unsubscribe from this group, send email to tesseract-ocr+unsubscr...@googlegroups.com For more options, visit this group at http://groups.google.com/group/tesseract-ocr?hl=en
