Folks, I found training portion of tesseract quite challenging. In order to simplify it I have created an application to get bounding boxes for an arbitrary text and fonts.
<https://lh3.googleusercontent.com/-EsN1E4eYWwI/WcV3PUN5Q7I/AAAAAAAATlE/4csnDXQP614RokbD-I6BYvx8_3Q_rz3CwCLcBGAs/s1600/Screen%2BShot%2B2017-09-22%2Bat%2B1.48.48%2BPM.png> In essence it is IOS FontTrainer application that runs in XCode with IPad simulator. <https://lh3.googleusercontent.com/-p-Ptw3reFec/WcV3e1soi4I/AAAAAAAATlI/SrslD_perMMwfcvwBhJQD-EDXW_-xeasACLcBGAs/s1600/Screen%2BShot%2B2017-09-22%2Bat%2B1.49.43%2BPM.png> Font trainer allows font selection, new fonts could be downloaded and added as well. Setting screen allows to selected desired fonts and font sizes, drag and drop a training text and initiate a measurement flow. The tool generates bunch of artifacts - with extensions - txt, tif, box, font_properties. I use the tool to create a training set and found it useful. I wonder would it be useful for others ? In case if it is something other folks want to explore I will publish it. 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/3e87d992-fcbe-416d-848b-71ff595b9ac4%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
