watersink / ocrsegment
a deep learning model for page layout analysis / segmentation.
☆100Updated 5 years ago
Related projects ⓘ
Alternatives and complementary repositories for ocrsegment
- Image-based table cell detection: a new dataset and an improved detection method.☆55Updated 4 years ago
- This is an implementation of Show, Attend and Read with tensorflow☆86Updated last year
- keras implementation of PSENET☆79Updated 5 years ago
- Deep learning based page layout analysis☆195Updated 5 years ago
- ☆136Updated last year
- ☆69Updated 6 years ago
- [CVPR 2019] "Handwriting Recognition in Low-resource Scripts using Adversarial Learning ”, IEEE Conf. on Computer Vision and Pattern Reco…☆62Updated 5 years ago
- Keras implementation of Character Region Awareness for Text Detection (CRAFT)☆166Updated 5 years ago
- Implementation code for document layout analysis (Hackathon 2020 in Suzhou)☆81Updated 4 years ago
- icpr2018_ocr_papers about ocr☆62Updated 6 years ago
- The ICDAR 2019 cTDaR is to evaluate the performance of methods for table detection (TRACK A) and table recognition (TRACK B). For the fir…☆169Updated 2 years ago
- FOTS tensorflow implementation, Include train and test, EAST+Rotate+CRNN. FOTS: Fast Oriented Text Spotting with a Unified Network☆89Updated 5 years ago
- Tensorflow CTPN☆39Updated 6 years ago
- Simple OCR service using deep learning☆59Updated 4 years ago
- ☆102Updated 5 years ago
- Code for the paper "KISS: Keeping it Simple for Scene Text Recognition"☆110Updated last year
- Unofficial PyTorch implementation of 2D Attentional Irregular Scene Text Recognizer☆131Updated 4 years ago
- ☆72Updated 6 years ago
- Dataset Generation Code for: S.R. Qasim, H. Mahmood, and F. Shafait, Rethinking Table Parsing using Graph Neural Networks (2019)☆118Updated 4 years ago
- Optical table recognition - recognize tables in scan images using OpenCV☆110Updated 5 years ago
- Modified by icdar codes for OCR results evaluation(detection or end-to-end recognition results). For more details, please see my blog:☆140Updated 5 years ago
- ☆75Updated 2 years ago
- ocr, cnn+lstm+ctc, crnn, recognition model, tensorflow☆76Updated 5 years ago
- OCR detection for ICDAR2015, which is based on FOTS, the precision is 80.6%.☆129Updated 5 years ago
- AI_DocumentLayoutAnalysis☆38Updated 3 years ago
- Synthesize image dataset for Chinese text recognition☆68Updated 5 years ago
- An implementation of the Splitting and Merging table recognition method.☆77Updated 4 years ago