Computer Vision / Image Processing

Foundational Topics

Introduction to Image Processing
- Image representation: pixels, channels
- Color models (RGB, HSV, Grayscale, etc.)
Image Filtering
- Convolution and kernels
- Gaussian blur, sharpening, edge detection (Sobel, Canny)
Histogram Processing
- Histogram equalization
- Contrast stretching
Image Transformations
- Scaling, rotation, translation
- Affine and perspective transformations
Thresholding and Binarization
- Global & adaptive thresholding
- Otsu’s method

Intermediate Topics

Feature Detection and Matching
- Harris corners, FAST, SIFT, SURF, ORB
Image Segmentation
- Region-based, edge-based, clustering (e.g., k-means)
- Watershed algorithm
Morphological Operations
- Erosion, dilation, opening, closing
Object Detection (Classical Methods)
- HOG + SVM
- Viola-Jones face detection
Geometric Vision
- Camera models, intrinsic/extrinsic parameters
- Epipolar geometry, triangulation

Deep Learning in Vision

Convolutional Neural Networks (CNNs)
- CNN layers and architectures (e.g., LeNet, VGG, ResNet)
Image Classification
- Using CNNs for multi-class classification
Object Detection
- R-CNN, Fast R-CNN, Faster R-CNN
- YOLO (You Only Look Once), SSD
Semantic and Instance Segmentation
- Fully Convolutional Networks (FCNs)
- U-Net, Mask R-CNN
Image Generation
- Autoencoders
- GANs (Generative Adversarial Networks)
Image Captioning
- Vision + NLP with encoder-decoder models

Advanced Topics & Applications

Practical Tools & Libraries