MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understanding
arXiv:2108.06543
Abstract
We present MMOCR-an open-source toolbox which provides a comprehensive pipeline for text detection and recognition, as well as their downstream tasks such as named entity recognition and key information extraction. MMOCR implements 14 state-of-the-art algorithms, which is significantly more than all the existing open-source OCR projects we are aware of to date. To facilitate future research and industrial applications of text recognition-related problems, we also provide a large number of trained models and detailed benchmarks to give insights into the performance of text detection, recognition and understanding. MMOCR is publicly released at https://github.com/open-mmlab/mmocr.
arXiv commentAccepted to ACM MM (Open Source Competition Track)
References in corpus (16)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- YOLOv3: An Incremental Improvement
- Rosetta: Large scale system for text detection and recognition in images
- Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes
- Joint Extraction of Entities and Relations Based on a Novel Tagging Scheme
- A Single-Shot Arbitrarily-Shaped Text Detector based on Context Attended Multi-Task Learning
- Towards Accurate Scene Text Recognition with Semantic Reasoning Networks
- Pyramid Mask Text Detector
- CLUENER2020: Fine-grained Named Entity Recognition Dataset and Benchmark for Chinese
- Fourier Contour Embedding for Arbitrary-Shaped Text Detection
- Symmetry-constrained Rectification Network for Scene Text Recognition
- Spatial Dual-Modality Graph Reasoning for Key Information Extraction
- Chargrid: Towards Understanding 2D Documents
- Geometry Normalization Networks for Accurate Scene Text Detection
- Boosting up Scene Text Detectors with Guided CNN
- PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network