# detectRecog/CCPD

[ECCV 2018] CCPD: a diverse and well-annotated dataset for license plate detection and recognition

Repository: https://github.com/detectRecog/CCPD
Canonical: https://ross.abutalabs.com/products/ccpd
Language: Python
License: MIT
License Family: permissive
Topics: plate-detection, ccpd, dataset, detection, recognition, large-scale
Last push: 2024-02-15T22:34:00+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3075, "days_push": 930, "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 2646, forks 584 (observed 2026-08-28T04:07:06.779406+00:00)

## What it is
CCPD is a large-scale, well-annotated dataset of over 300k images for license plate detection and recognition, published at ECCV 2018. It includes multiple challenging subsets (blur, rotation, tilt, distance, challenge, green energy plates) plus baseline detection and recognition benchmarks.

## Use cases
- train a license plate detection model
- benchmark license plate recognition algorithms
- evaluate object detectors on blurred and rotated plates
- get annotated Chinese license plate images for OCR research
- compare YOLO SSD and Faster-RCNN on plate detection
- train a model to recognize green energy vehicle plates

## When to choose
- you need a large annotated dataset for license plate detection or recognition
- you want a standard benchmark with challenging subsets for plate OCR
- you work on Chinese license plates including new energy vehicle plates

## When to avoid
- you need license plates from countries other than China
- you need a ready-to-deploy production recognition system rather than data
- you cannot download large multi-gigabyte image archives

## Facets
- artifact type: dataset
- maturity: stable
- function: computer-vision, image-processing, ocr, machine-learning
- domain: computer-vision, image-processing, artificial-intelligence
- platform: python, cross-platform
- tags: license-plate-detection, license-plate-recognition, ccpd, benchmark, object-detection, chinese-license-plates

## Member repositories
- detectRecog/CCPD (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:06.779406+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 2026-08-30T02:18:58.348511+00:00, confidence not recorded.
  - readme: https://github.com/detectRecog/CCPD (fetched 2026-08-28T04:07:06.779406+00:00, sha af7992b38ba1)
- Data as of 2026-08-30T08:39:29.467469+00:00.