szad670401/end-to-end-for-chinese-plate-recognition

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1117 stars · 516 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

An end-to-end Chinese license plate recognition model based on MXnet, using multi-label classification. It was trained on ~500k synthetic rendered plate samples and is the predecessor of the HyperLPR system.

Use cases

• recognize Chinese license plates from images
• train an end-to-end plate recognition model with MXnet
• generate synthetic license plate training samples
• OCR for vehicle plates without separate character segmentation

When to choose

• you need a lightweight research baseline for Chinese plate recognition on CPU
• you want to study multi-label end-to-end OCR approaches in MXnet

When to avoid

• you need a production-grade or maintained plate recognizer (use HyperLPR instead)
• you require a permissive license (no license is provided)
• your stack is not MXnet-based

Facets

library · maturity abandoned

machine-learning deep-learning computer-vision ocr image-processing computer-vision image-processing deep-learning python cross-platform license-plate-recognition chinese-plate mxnet multi-label-classification end-to-end-ocr natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="szad670401/end-to-end-for-chinese-plate-recognition")