Hi. I'm working on my bachelor thesis about 'Handwritten math formula recognition'. I need to create an Android app which will be used to recognize math formulas from captured images. I have training data <https://www.kaggle.com/xainano/handwrittenmathsymbols> (about 100.000 (45x45) images of handwritten math symbols) from Kaggle. I think I need to create something similar to this <https://webdemo.myscript.com/views/math.html> (I understand that there is much work to be done. Maybe performance can be worse or some symbols can be not recognized).
I read topic <https://github.com/tesseract-ocr/tesseract/wiki/Training-Tesseract-3.03%E2%80%933.05#training-procedure> about training Tesseract and I still a little bit confused. I wonder is it possible to use my training data by creating TIFF files? Or is there a way to fine-tune already existing equ.traineddata <https://github.com/tesseract-ocr/tesseract/wiki/Data-Files#special-data-files> by adding those new handwritten symbols (from images)? 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 [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/0e6562d5-a2ed-44ac-883b-1a89532b887e%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
