i have to create a major project based on past question paper
for data collection im converting the photos of question paper into text using ocr and having issues for cleaning data and having no idea how does the model work !!!
i have to create a major project based on past question paper
for data collection im converting the photos of question paper into text using ocr and having issues for cleaning data and having no idea how does the model work !!!
Hi @Uday_jit
For cleaning your OCR-generated text, focus on correcting misrecognized characters and removing unnecessary whitespace. You can read a couple of articles about how OCRs work and feel free to ask if you need assistance.
Hope it helps!