# clovaai/deep-text-recognition-benchmark

Text recognition (optical character recognition) with deep learning methods, ICCV 2019

Repository: https://github.com/clovaai/deep-text-recognition-benchmark
Canonical: https://ross.abutalabs.com/products/deep-text-recognition-benchmark
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: iccv2019, ocr, ocr-recognition, text-recognition, deep-learning, scene-text-recognition, recognition, scene-text, crnn, rare, r2am, grcnn, rosetta, star-net
Last push: 2024-03-04T10:24:54+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2709, "days_push": 912, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3942, forks 1132 (observed 2026-08-28T04:08:30.224717+00:00)

## What it is
Official PyTorch implementation of a four-stage scene text recognition (OCR) framework from an ICCV 2019 paper, with training and evaluation code for models like CRNN, RARE, and STAR-Net. It provides consistent datasets, pretrained models, and module-wise benchmarking for comparing STR models.

## Use cases
- recognize text in scene images with deep learning
- train an OCR text recognition model in PyTorch
- benchmark scene text recognition models fairly
- download pretrained scene text recognition models
- evaluate OCR accuracy on ICDAR benchmarks
- compare CRNN vs RARE vs STAR-Net performance

## When to choose
- you need a research-grade baseline for scene text recognition
- you want to reproduce or extend ICCV 2019 STR model comparisons
- you need pretrained text recognition models and standardized LMDB training data

## When to avoid
- you need a production-ready OCR service with layout analysis and document parsing
- you want a maintained library with frequent updates and broad API support
- you need handwriting or full-page document OCR rather than cropped word recognition

## Facets
- artifact type: library
- maturity: maintenance
- function: ocr, machine-learning, deep-learning, image-processing
- domain: computer-vision, image-processing, deep-learning, machine-learning
- platform: python, cross-platform
- tags: scene-text-recognition, pytorch, iccv-2019, crnn, research-code, text-recognition, gpu

## Member repositories
- clovaai/deep-text-recognition-benchmark (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:30.224717+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:24:36.851961+00:00, confidence not recorded.
  - readme: https://github.com/clovaai/deep-text-recognition-benchmark (fetched 2026-08-28T04:08:30.224717+00:00, sha 151dd82eb38f)
- Data as of 2026-08-30T08:39:29.467469+00:00.