Computer Vision (CV) is a field of Artificial Intelligence (AI) that enables computers to interpret and process visual data (images and videos) similarly to how humans do. It involves techniques for image recognition, object detection, segmentation, and more.
Week-1. Introduction to Computer Vision
History, Applications, Challenges
Week-2. Image Processing Basics
OpenCV, NumPy, Image Filters, Transformations
Week-3. Feature Detection & Extraction
HOG, SIFT, SURF, ORB
Week-4. Color Spaces & Edge Detection
Histogram Equalization, Canny Edge Detection
Week-5. Introduction to CNNs
Convolution, Pooling, Fully Connected Layers
Week-6. Pretrained Models & Transfer Learning
VGG, ResNet, MobileNet
Week-7. Object Detection & Tracking
YOLO, Faster R-CNN, SSD
Week-8. Segmentation Techniques
Semantic & Instance Segmentation, U-Net, Mask R-CNN
Week-9. Vision Transformers (ViTs)
Self-Attention for Vision, Applications
Week-10.Generative Models for Vision
GANs, Stable Diffusion, VAEs
Week-11. 3D Vision & Depth Estimation
LIDAR, Structure from Motion, Stereo Vision
Week-12. Multimodal AI
Vision-Language Models, CLIP, DINO, Image Captioning
Week-13. Deploying Computer Vision Models
ONNX, TensorFlow Lite, Edge AI
Week-14. Cloud Deployment & APIs
AWS Rekognition, Google Vision API, Hugging Face
Week-15. Capstone Project – Part 1
Dataset Collection, Model Selection
Week-16. Capstone Project – Part 2
Fine-Tuning, Optimization, Deployment