ImageEn Forum

Profile Join Active Topics Forum FAQ

All Forums

OCR ZONAL

Note: You must be registered in order to post a reply.
To register, click here. Registration is FREE!

View

UserName:

Password:

Format

Message

Check here to include your profile signature.
Check here to subscribe to this topic.

T O P I C R E V I E W
AndNit	Posted - May 14 2026 : 06:46:00 I'm experimenting with zonal OCR, but I've noticed that the OCR tends to interpret many non-existent characters, especially in marked areas where the text ends before the predefined marking. I thought about combining some ImageEn functions to try and solve this. See if this is a good approach, and if you could provide an example, I would be grateful. I was thinking of converting the selected area to black and white to improve OCR reading, then sending only the selected area (already in black and white) to detectTexts, and then generating the OCR on the detected text. Do you think this is a good approach? Could you contribute some ideas and an example? Thank you.
1 L A T E S T R E P L I E S (Newest First)
xequte	Posted - May 14 2026 : 17:57:55 Certainly, limiting the OCR to a specified zone markedly improves the result, but the problem is finding a way to make the process automated. I think you would be best to review the Tesseract (IEVision uses Tesseract 5) forums to see what advice they offer. Nigel Xequte Software www.imageen.com