hoangtuanvu / conformer_ocrLinks
Transformer OCR is a Optical Character Recognition tookit built for researchers working on both OCR for both Vietnamese and English. This project only focused on variants of vanilla Transformer (Conformer) and Feature Extraction (CNN-based approach).
☆10Updated 3 years ago
Alternatives and similar repositories for conformer_ocr
Users that are interested in conformer_ocr are comparing it to the libraries listed below
Sorting:
- Dictionary-guided Scene Text Recognition (CVPR-2021)☆149Updated 11 months ago
- [WIP] A Pytorch implementation of DB-Text - Real-time Scene Text Detection with Differentiable Binarization☆38Updated 3 years ago
- Multimodal Semi-Supervised Learning for Text Recognition (SemiMTR)☆83Updated last year
- Scene Text Recognition (STR) methods trained with fewer real labels (CVPR 2021)☆180Updated last year
- swin-transformer custom for OCR☆114Updated last year
- ☆40Updated 11 months ago
- Official PyTorch implementation for Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features …☆69Updated 2 years ago
- time-series row column classification☆13Updated 3 years ago
- Image transformations designed for Scene Text Recognition (STR) data augmentation. Published at ICCV 2021 Workshop on Interactive Labelin…☆259Updated last year
- Unofficial implementation of CVPR 2020 paper "SCATTER: Selective Context Attentional Scene Text Recognizer"☆66Updated 3 years ago
- Vietnamese handwritten text recognition system☆17Updated 4 years ago
- Geometric Rectification of Document Images using Adversarial Gated Unwarping Network☆25Updated 5 years ago
- ☆62Updated last year
- ☆3Updated 2 weeks ago
- ☆18Updated 2 years ago
- ☆24Updated last year
- Synthesize distorted document image and control points.☆48Updated 2 years ago
- ICDAR 2019 Robust Reading Challenge on Scanned Receipts OCR and Information Extraction☆32Updated 2 years ago
- A PyTorch implementation of "From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network" (ICCV2021)☆107Updated 3 years ago
- ☆1Updated last week
- Code for CVPR21 paper A Multiplexed Network for End-to-End, Multilingual OCR☆80Updated 2 years ago
- It's the code for the paper Pushing the Performance Limit of Scene Text Recognizer without Human Annotation, CVPR 2022.☆28Updated 2 years ago
- ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting☆84Updated 2 years ago
- Key information extraction from invoice document with Graph Convolution Network☆56Updated 2 years ago
- This dataset contains re-annotations of 4 popular Latin/English scene text recognition datasets.☆50Updated 5 years ago
- Official Tensorflow Implementation of SATRN (CVPR Workshop WTDDLE 2020)☆159Updated 4 years ago
- useful text recognition algorithms, CRNN and SVTR text recognition☆29Updated 2 years ago
- My personal implementation of SVTR model for handwritten OCR☆13Updated last year
- Improved Text recognition algorithms on different text domains like scene text, handwritten, document, Chinese/English, even ancient book…☆79Updated 2 years ago
- Implementation of Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition published in AAAI 2019 in PyTorch☆71Updated 4 years ago