it’s all OCR. all of it can be trained.
tesseract is generally lagging behind the state of the art and the competition (easyocr, paddle, …). at least, I judge that by how successful people are with anything non-trivial they need to read.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| OCR on stylish number plates | 0 | 302 | July 20, 2022 | |
| Obtain only text and numbers | 0 | 910 | April 10, 2021 | |
| Trying to detect USA License plate | 1 | 276 | September 22, 2022 | |
| Optical Character Recognition | 1 | 471 | May 23, 2022 | |
| Improving Quality of PyTesseract OCR Output | 2 | 9652 | June 8, 2022 |