search

Apex95 / tesseract-preprocessing-convolution-poc

Ipynb POC for Convolutional Preprocessor used to enhance Tesseract's Accuracy
3 stars 5 forks source link

about load images #1

Open kobrafarshidi opened 1 year ago

kobrafarshidi commented 1 year ago

Hi, Mr Sporici I want to run your great source code about Tessearct but I can't do it. my problem is in dataset form images in line code of
img = Image.open(str(i+1) + '.jpg') how to load dataset of images where is them? I'd appreciate it if you could help me very much and give me a guidance. Best regard

Apex95 commented 1 year ago

Hi,

The images are from the Brno Mobile OCR Dataset. The PoC used the already segmented lines of text (i.e., "Cropped text lines with transcriptions") and the "Easy" version of the dataset. I hope this helps.

kobrafarshidi commented 1 year ago

hi, Thank you so much for your guide. I'll use that. best regard,