Skip to main content

All Questions

Filter by
Sorted by
Tagged with
1 vote
0 answers
59 views

Extract text from processed image

I'm trying to extract text from a croped image of any EU license plate. I've tried using easyocr but the results is to inaccurate for me to use. I have trained a YOLOV8 model to detect the license ...
Edward's user avatar
  • 25
1 vote
0 answers
671 views

OCR in pytorch/keras with LPRNet and CTCLoss doesn't converge

I implemented LPRNet from this paper in keras and then in pytorch. For pytorch was used this code as example. It didn't converge in any version. Loss starts at 30 and goes to 27 even after 150000 ...
Vadim's user avatar
  • 87
-1 votes
1 answer
234 views

How to differentiate 2 classes: digits and "other letters and noise" on an image?

I develop an image recognition algorithm that helps to find characters on dirty pannels from the real world. Actually the image is a car registering plate containing letters, digits and a mud. The ...
Andyrey's user avatar
  • 91