By 苏剑林 | June 26, 2016
File Description:
1. image.py — Image processing functions, primarily feature extraction;
2. model_training.py — Training the CNN single-character recognition model (requires a high-performance server, preferably with GPU acceleration, otherwise it is incredibly slow);
3. ocr.py — Recognition functions, including single-character segmentation, recognition using the previously trained model, and dynamic programming to enhance results;
4. main.py — Main file, used to call files 1 and 3;
5. Characters included in our model.txt (UTF-8 encoded)
File 1: image.py
File 2: model_training.py
File 3: ocr.py
File 4: main.py
If you found this article helpful, you are welcome to share or donate to this article. Donations are not for profit, but to know how much sincere attention Scientific Space has received from its readers. Of course, if you ignore this, it will not affect your reading. Welcome and thank you again!