OCR, CNN+LSTM (CTPN) for image text detection, tensorflow
CNN+LSTM (CTPN) for image text detection
To run this repo:
1, python databasenormalize.py # to normalize the pre-normalized background images
2, python data_generator.py 0 # to generate validation data
3, python data_generator.py 1 # to generate training data
4, python script_detect.py # to train and validate
By 1, the pre-normalized images will firstly be rescaled if not of size 800x600, then 800x600 rects will be cropped from the rescaled images. The 800x600 images will be stored in a newly-maked directory, ./images_base.
By 2 and 3, validation data and training data will be generated. These will be store in the newly-maked directories, ./datavalid and ./datatrain, respectively.
By 4, the model will be trained and validated. The validation results will be stored in ./datavalid/results. The ckpt files will be stored in a newly-maked directory, ./modeldetect.
The model is mainly based on the method described in the article:
Detecting Text in Natural Image with Connectionist Text Proposal Network
Zhi Tian, Weilin Huang, Tong He, Pan He, Yu Qiao