This project implements a QR code detection pipeline using Python and classical computer vision techniques. The system processes input images, applies preprocessing and feature analysis, and detects QR codes using OpenCV-based image processing methods.
The project demonstrates practical skills in image analysis, algorithmic problem solving, and computer vision workflows, and was developed in a Google Colab environment.
QR codes are widely used for data encoding in real-world applications. Detecting them reliably under varying image conditions requires effective preprocessing and robust detection techniques.
This project focuses on:
- Image preprocessing and enhancement
- Feature extraction using computer vision
- QR code detection using OpenCV
- Visualization of detection results
- Image preprocessing (grayscale conversion, resizing, filtering)
- Thresholding and edge detection
- Contour analysis
- Classical computer vision techniques
- Visualization of intermediate and final results
- Modular code design (logic separated from UI)
- Web-based interaction using Streamlit
- Python
- OpenCV (cv2)
- NumPy
- Matplotlib
- Google Colab / Jupyter Notebook
- Pillow (PIL)
- Streamlit
The Streamlit web app provides an intuitive interface for detecting QR codes without running notebooks or scripts manually.
- Image upload (PNG / JPG)
- Automatic QR detection
- Visual bounding box around detected QR codes
- Display of decoded QR content
- Clean, modern UI design
