deep-text-recognition-benchmark and awesome-deep-text-detection-recognition
The first tool provides an implementation of deep learning methods for text recognition, while the second offers a curated list of resources for text detection and recognition, making them complements where the list can guide users towards using or understanding theall aspects of the first tool.
About deep-text-recognition-benchmark
clovaai/deep-text-recognition-benchmark
Text recognition (optical character recognition) with deep learning methods, ICCV 2019
Implements a modular four-stage STR (Scene Text Recognition) framework—Transformation, Feature Extraction, Sequence Modeling, and Prediction—enabling controlled benchmarking of component contributions across accuracy, speed, and memory. Built on PyTorch with support for diverse architectures (TPS/ResNet/BiLSTM/Attention), CTC loss, and standardized LMDB datasets across seven evaluation benchmarks (IIIT5K, SVT, IC03-15, SVTP, CUTE80). Provides pretrained models and comprehensive ablation analysis to isolate performance gains from individual architectural modules rather than conflating improvements across multiple simultaneous changes.
About awesome-deep-text-detection-recognition
hwalsuklee/awesome-deep-text-detection-recognition
A curated list of resources for text detection/recognition (optical character recognition ) with deep learning methods.
Scores updated daily from GitHub, PyPI, and npm data. How scores work