jenly1314/WeChatQRCode

⛄ 基于OpenCV开源的微信二维码引擎移植的二维码扫码识别库

What it solves

This project provides a high-performance QR code recognition library for Android, specifically porting and encapsulating the WeChat QR code engine based on OpenCV. It aims to offer a faster and more efficient alternative to traditional QR scanning libraries, enabling developers to easily integrate QR detection and decoding into their mobile applications.

How it works

The library leverages OpenCV's open-source QR code detection capabilities. It is structured into several modules:

  • Detection Engines: It provides two main detectors: WeChatQRCodeDetector (based on the WeChat engine, which is faster and supports multi-code recognition) and OpenCVQRCodeDetector (based on standard OpenCV, which which is noted for more precise positioning).
  • Scanning Framework: The wechat-qrcode-scanning and opencv-qrcode-scanning modules provide ready-made UI components (Activities and Fragments) that handle the camera feed and integrate the detection engines.
  • Architecture: It uses a base library called CameraScan to manage the scanning process and ViewfinderView for the visual scanning animations.

Who it’s for

Android developers who need to implement QR code scanning functionality with high performance, support for multiple QR codes in a single frame, or the require the specific efficiency of the WeChat QR engine.

Highlights

  • Dual Engine Support: Includes both the WeChat QR engine for speed and the standard OpenCV engine for precision.
  • Multi-Code Recognition: The WeChat engine can identify multiple QR codes simultaneously.
  • Ready-to-Use UI: Provides base activities and fragments to quickly implement a scanning interface.
  • Positioning Data: Ability to return the exact vertex points (coordinates) of the detected QR codes within an image.
  • Comprehensive ABI Support: Includes pre-compiled OpenCV binaries for armv7a, arm64-v8a, x86, and x86_64 architectures.

Related

  • Project
    Yuliang-Liu/MultimodalOCR

    A collection of benchmarks (MDPBench, OCRBench v2, and OCRBench) designed to evaluate the OCR and document parsing capabilities of Large Multimodal Models across multiple languages and real-world scenarios.

  • Project
    om-ai-lab/VLX-Seek

    VLX‑Seek is an open‑source vision‑language model that performs fine‑grained perception for edge‑device agents. It generates region proposals, encodes each region as a special token, and lets the language model answer by selecting those tokens—producing compact, parsable outputs for detection, referring‑expression comprehension, OCR, counting, and VQA. The repo ships inference code, a Python API, and the 10 B checkpoint (weights hosted on Hugging Face).

  • Project
    alephpi/Texo

    A minimalist, open-source LaTeX OCR model with only 20M parameters that converts mathematical formula images into LaTeX code.

  • Project
    microsoft/farmvibes-ai

    A multi-modal geospatial machine learning framework for agriculture and sustainability that fuses satellite imagery, weather data, and elevation maps to generate robust agricultural insights.