🧠 Computer Vision: Image & Video Processing — Syllabus

Welcome to your journey into Computer Vision! This syllabus is divided into modules, each linking to its own detailed wiki page.

📅 Duration: 8–10 Weeks (Flexible Pace)

---

📘 Module 1: Introduction to Computer Vision

• What is computer vision?
• Applications in industry and research
• Image formation basics
• Cameras, sensors, and pixels

🖼️ Module 2: Digital Image Fundamentals

• Image representation: Grayscale, RGB, etc.
• Color spaces (RGB, HSV, YCrCb)
• Sampling and quantization
• Image histograms and enhancement

🎛️ Module 3: Image Filtering and Convolution

• Convolution and correlation
• Smoothing filters (Gaussian, box)
• Edge detection (Sobel, Canny)
• Sharpening and gradient operators

✂️ Module 4: Image Segmentation

• Thresholding (global, adaptive, Otsu)
• Region growing, watershed
• Contours and connected components
• Superpixels

📌 Module 5: Feature Detection and Matching

• Corner detectors (Harris, Shi-Tomasi)
• Keypoints and descriptors (SIFT, SURF, ORB)
• Feature matching (Brute-force, FLANN)
• Homographies and transformations

🎞️ Module 6: Motion and Video Analysis

• Optical flow (Lucas-Kanade, Farneback)
• Background subtraction
• Object tracking (Kalman filters, Mean-shift, CamShift)
• Video stabilization

🎯 Module 7: Object Detection & Recognition

• HOG + SVM
• Viola-Jones face detector
• Deep learning-based methods (YOLO, SSD, Faster R-CNN)
• Pretrained models and transfer learning

🤖 Module 8: Deep Learning in Computer Vision

• CNN architecture basics
• Image classification with CNNs
• Semantic and instance segmentation (U-Net, Mask R-CNN)
• Applications: OCR, face recognition, medical imaging

🛠️ Module 9: Project and Applications

• Choose a mini-project (e.g., real-time object tracker)
• Dataset selection and preparation
• Model training, testing, evaluation
• Deployment tips

---

✅ Prerequisites

• Basic Python
• Numpy, Matplotlib
• OpenCV
• (Optional) PyTorch or TensorFlow

---

Stay curious and keep building! 🧑‍💻✨