Member Avatar for Nova6112

Hi All,

I am new to Android developement now i need to develop a OCR application. in that i need to get Retailer name and Total from Expense receipts. for example Costo / Walmart using their Logo in top of the receipt. i need to Train tesseract to understand that Logo as Costco / Walmart. for that i am working on Tesseract Training but i am getting this error screenshot is attached please help me anyone how can i solve this.

I am following this steps : https://blog.cedric.ws/how-to-train-tesseract-301

Thanks in Advance

  • 1 Contributor
  • 1 Reply
  • 249 Views
  • 1 Minute Discussion Span
  • Latest Post Latest Post by Nova6112
Member Avatar for Nova6112

C:\Program Files (x86)\Tesseract-OCR>tesseract E:\walmart.jpg walmart -psm 7 batch.nochop makebox

C:\Program Files (x86)\Tesseract-OCR>tesseract E:\walmart.jpg eng.walmart.exp0.box nobatch box.train

C:\Program Files (x86)\Tesseract-OCR>unicharset_extractor eng.walmart.exp0.box

C:\Program Files (x86)\Tesseract-OCR>echo "walmart 1 0 0 0 0" > font_properties

these commands worksfine but the following command throws error

C:\Program Files (x86)\Tesseract-OCR>mftraining -F font_properties -U unicharset -O eng.unicharset eng.walmart.exp0.box.tr

this is my commandline code, following is error throwing.
Warning: No shape table file present: shapetable
Reading eng.walmart.exp0.box.tr ...
Font id = -1/0, class id = 1/11 on sample 0
font_id >= 0 && font_id < font_idmap.SparseSize():Error:Assert failed:in file
....\classify\trainingsampleset.cpp, line 622

attached Screenshot also please check. if anything needed please tell me i'll explain

searched a google lot they all mentioned something about font_properties but i can't understand it would be better someone can explain with examples

Be a part of the DaniWeb community

We're a friendly, industry-focused community of developers, IT pros, digital marketers, and technology enthusiasts meeting, networking, learning, and sharing knowledge.