# zhubenfu/License-Plate-Detect-Recognition-via-Deep-Neural-Networks-accuracy-up-to-99.9

works in real-time with detection and recognition accuracy up to 99.8% for Chinese license plates: 100 ms/plate

Repository: https://github.com/zhubenfu/License-Plate-Detect-Recognition-via-Deep-Neural-Networks-accuracy-up-to-99.9
Canonical: https://ross.abutalabs.com/products/license-plate-detect-recognition-via-deep-neural-networks-accuracy-up-to-999
Language: C++
License Family: other
Last push: 2020-06-30T04:45:19+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": 2987, "days_push": 2255, "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 1384, forks 321 (observed 2026-08-28T04:04:34.723477+00:00)

## What it is
A C++ application that detects and recognizes Chinese license plates in real time using deep neural networks, claiming up to 99.8% accuracy at roughly 100 ms per plate. It bundles multiple detection approaches (haar+cascade, MTCNN, image processing) and recognition methods (CNN character classification, LSTM+CTC).

## Use cases
- recognize Chinese license plates from camera footage
- detect vehicle plates in real time video
- build an ANPR/LPR system for parking or tolling
- train a plate recognition model with real plate datasets
- compare haar cascade vs MTCNN vs YOLO for plate detection
- perform OCR on segmented license plate characters

## When to choose
- you need to detect and read Chinese license plates specifically
- you want a ready-made C++ pipeline with multiple detection/recognition backends
- you need a Windows/CUDA build for real-time plate recognition
- you want a large real-world Chinese plate dataset for training

## When to avoid
- you need plates from regions other than China
- you require a maintained project with a clear license for commercial use (no license is provided)
- you need cross-platform or Linux-first deployment out of the box
- you want a pip-installable or well-documented library rather than a Visual Studio project

## Facets
- artifact type: application
- maturity: maintenance
- function: computer-vision, ocr, image-processing, machine-learning, deep-learning
- domain: computer-vision, image-processing, artificial-intelligence, developer-tools
- platform: windows, cpp
- tags: license-plate-recognition, alpr, chinese-license-plates, mtcnn, haar-cascade, yolo, lstm-ctc, cnn, opencv, real-time, gpu

## Member repositories
- zhubenfu/License-Plate-Detect-Recognition-via-Deep-Neural-Networks-accuracy-up-to-99.9 (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:34.723477+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 2026-08-30T04:40:00.095650+00:00, confidence not recorded.
  - readme: https://github.com/zhubenfu/License-Plate-Detect-Recognition-via-Deep-Neural-Networks-accuracy-up-to-99.9 (fetched 2026-08-28T04:04:34.723477+00:00, sha 965b92da05d9)
- Data as of 2026-08-30T08:39:29.467469+00:00.