kennethleungty / OCR-Metrics-CER-WERLinks
Sample implementation of OCR metrics (CER, WER) calculation with TesseractOCR and fastwer
☆29Updated 4 years ago
Alternatives and similar repositories for OCR-Metrics-CER-WER
Users that are interested in OCR-Metrics-CER-WER are comparing it to the libraries listed below
Sorting:
- Detect handwritten words (neural network based).☆71Updated 3 years ago
- CVPR 2022: Table Structure Recognition☆40Updated 3 years ago
- CDeC-Net: Composite Deformable Cascade Network for Table Detection in Document Images☆133Updated 7 months ago
- TableNet Implementation on Pytorch☆148Updated 2 years ago
- Detect textlines in document images☆93Updated last year
- ICDAR 2019: MaskRCNN on PubLayNet datasets. Paragraph detection, table detection, figure detection,...☆182Updated 4 years ago
- Handwritten text recognition using transformers.☆157Updated last year
- Detectron2 for Document Layout Analysis☆188Updated last year
- Pytorch Implementation of TableNet☆67Updated 4 years ago
- Code for the ICDAR2021 paper "Visual FUDGE: Form Understanding via Dynamic Graph Editing"☆33Updated 3 years ago
- The scripts for training Detectron2-based Layout Models on popular layout analysis datasets☆213Updated last year
- A deep learning toolkit specialized for handwritten document analysis☆243Updated last year
- Research papers and code on information extraction from image/pdf☆97Updated 2 years ago
- ICIP 2022: Adaptive Radial Projection on Fourier Magnitude Spectrum for Document Image Skew Estimation☆142Updated 3 months ago
- Detect handwritten words (classic image processing based method).☆273Updated 2 years ago
- Page to PAGE Layout Analysis Tool☆191Updated 3 years ago
- convert PubLayNet data into METS/PAGE-XML☆10Updated 5 years ago
- ICDAR 2019 Robust Reading Challenge on Scanned Receipts OCR and Information Extraction☆401Updated 5 years ago
- Code for my ICDAR paper "Deep Visual Template-Free Form Parsing"☆88Updated 3 years ago
- OCR & Ground Truth Resources☆76Updated 3 years ago
- Packaged, Pytorch-based, easy to use, cross-platform version of the CRAFT text detector☆265Updated 3 years ago
- Library used to deskew a scanned document☆478Updated this week
- ☆18Updated last year
- ☆137Updated 2 years ago
- ☆16Updated 4 years ago
- Form images from U.S. National Archives annotated with text bounding boxes, classes, relationships, and transcription.☆38Updated 3 years ago
- DocILE: Document Information Localization and Extraction Benchmark☆135Updated last year
- Handwritten Text Recognition using TensorFlow☆281Updated last year
- ☆131Updated 2 years ago
- Document Image Binarization☆78Updated 10 months ago