# tianzhi0549/CTPN

Detecting Text in Natural Image with Connectionist Text Proposal Network (ECCV'16)

Repository: https://github.com/tianzhi0549/CTPN
Canonical: https://ross.abutalabs.com/products/ctpn
Homepage: http://textdet.com
Language: Jupyter Notebook
License: NOASSERTION
License Family: other
Topics: ocr, text-detection
Last push: 2021-10-15T05:17:41+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": 3596, "days_push": 1783, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1287, forks 528 (observed 2026-08-28T04:04:15.068904+00:00)

## What it is
Reference implementation of CTPN (Connectionist Text Proposal Network) for detecting text lines in natural images, from the ECCV 2016 paper. It ships with a trained Caffe model and demo scripts for scene text detection.

## Use cases
- detect text regions in natural scene images
- run scene text detection with a pretrained model
- locate text lines in photos before OCR
- reproduce CTPN results from the ECCV 2016 paper
- benchmark text detection models

## When to choose
- you need the original CTPN implementation for research or paper reproduction
- you work with Caffe and legacy Python 2.7 deep learning stacks
- you want a pretrained scene text detector to study or extend

## When to avoid
- you need a maintained, production-ready text detector
- you use modern frameworks like PyTorch or TensorFlow
- you cannot build legacy Caffe with CUDA 7.0 and Python 2.7
- you need side-refinement or end-to-end OCR

## Facets
- artifact type: library
- maturity: abandoned
- function: computer-vision, ocr, deep-learning, image-processing
- domain: computer-vision, deep-learning, image-processing
- platform: python
- tags: scene-text-detection, ctpn, caffe, eccv-2016, text-line-detection, ocr, linux, gpu

## Member repositories
- tianzhi0549/CTPN (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:15.068904+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 2026-08-30T04:56:06.943345+00:00, confidence not recorded.
  - readme: https://github.com/tianzhi0549/CTPN (fetched 2026-08-28T04:04:15.068904+00:00, sha 0aabefc3ae1e)
  - homepage: http://textdet.com (fetched 2026-08-29T12:12:07.975860+00:00, sha ba7eb1ba76b4)
- Data as of 2026-08-30T08:39:29.467469+00:00.