ComputerVisionLab

ComputerVisionLab is a web-based platform built with Django and OpenCV that provides an interactive interface for various computer vision algorithms. It allows users to upload images or provide URLs to process them using techniques like face detection, edge detection, and image segmentation.

📋 Table of Contents

• Features
• Architecture
• Technology Stack
• Installation
• Usage
• Algorithms Implemented
• Detailed Algorithm Guide
• Authors

---

✨ Features

• Face Detection: Uses Haar Cascades to identify and locate faces in images.
• Edge Detection: Implements Canny edge detection with adjustable thresholds.
• Image Segmentation: Utilizes the Watershed algorithm for object separation.
• Keypoint Detection: Employs ORB (Oriented FAST and Rotated BRIEF) for finding interest points.
• Coin Counting: Automatically detects and counts coins in an image using contour analysis.
• Real-time Camera Processing: Browser-based face and color tracking using tracking.js.
• Thresholding: Interactive global and adaptive thresholding.

---

🏗 Architecture

The project follows the standard Django Model-View-Template (MVT) architecture, integrated with OpenCV for backend image processing and tracking.js for frontend real-time tasks.

graph TD
    User((User)) -->|Upload Image/URL| WebBrowser[Web Browser]
    WebBrowser -->|HTTP Request| Django[Django Backend]
    Django -->|Image Data| OpenCV[OpenCV Engine]
    OpenCV -->|Processed Image/Data| Django
    Django -->|Rendered Result| WebBrowser
    WebBrowser -->|Real-time Tracking| TrackingJS[tracking.js]
    TrackingJS -->|Camera Stream| WebBrowser

Loading

---

🛠 Technology Stack

Category	Tools/Technologies
Backend	Django 4.1, Python 3.x
CV Library	OpenCV (cv2)
Frontend	HTML5, CSS3, JavaScript, tracking.js
Data Science	NumPy, Pillow
Database	SQLite (Default)

---

🚀 Installation

Prerequisites

• Python 3.8+
• pip

Steps

1. Clone the repository:

   git clone https://github.com/your-username/ComputerVisionLab.git
   cd ComputerVisionLab

2. Create and activate a virtual environment:

   python -m venv venv
   source venv/bin/activate  # On Windows: venv\Scripts\activate

3. Install dependencies:

   pip install -r requirements.txt

4. Run migrations:

   python manage.py migrate

5. Start the development server:

   python manage.py runServer

   Open http://127.0.0.1:8000 in your browser.

---

💡 Usage

Local Image Processing

1. Navigate to a specific algorithm (e.g., Face Detection).
2. Upload a local image or paste an image URL.
3. View the processed result with highlighted features.

Real-time Camera Detection

1. Select "Camera Detection" from the menu.
2. Grant camera permissions to the browser.
3. The application will track faces or colors in real-time using your webcam.

---

🔬 Algorithms Implemented

1. Face Detection

Uses the Viola-Jones framework with Haar Cascades.

detector = cv2.CascadeClassifier(FACE_DETECTOR_PATH)
rects = detector.detectMultiScale(image, scaleFactor=1.1, minNeighbors=5)

2. Canny Edge Detection

A multi-stage algorithm to detect a wide range of edges in images.

edges = cv2.Canny(image, threshold1, threshold2)

3. ORB Keypoints

An efficient alternative to SIFT or SURF for keypoint detection and description.

orb = cv2.ORB_create()
keypoints = orb.detect(gray_image, None)

---

📸 Screenshots

Note: You can add actual screenshots of the application here to demonstrate the UI and output.

Algorithm	Sample Result
Face Detection
Canny Edges
Watershed

---

👥 Authors

• Artur - Initial work

---

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.