This is a pytorch-based implementation for paper Implicit Feature Alignment: Learn to Convert Text Recognizer to Text Spotter.
Due to the company's code confidentiality requirements, we only release the code of ExCTC on the IAM dataset.
Personally, I dont't think it is a thorough work, but I hope this idea is useful.
We re-crop the lines from IAM full-page images. This operation is to remove the edge phenomenon in the official line images.
These re-cropped images are used as training set.
Crop the training images (
data/crop_images.py) and modify the path in configuration files (
A simple demo: