Introduction to Computer Vision and its applications. Image formation, image sensing, sampling, quantization, and digital image representation. Image enhancement techniques: histogram processing, interpolation, spatial filtering, smoothing, sharpening, and noise reduction. Image quality assessment and evaluation metrics. Image transformations: Fourier Transform, Discrete Cosine Transform (DCT), and overview of wavelet transforms. Image restoration, frequency-domain filtering, and mathematical morphology.
Image segmentation techniques: thresholding, edge detection, region-based segmentation, watershed algorithm, and evaluation metrics. Image representation and feature extraction techniques. Color models, texture analysis, and feature descriptors including SIFT, SURF, ORB, and HOG. Feature matching and object recognition using classical computer vision approaches. Applications of image analysis in healthcare, autonomous systems, agriculture, and surveillance.
Introduction to deep learning-based computer vision. Convolutional Neural Networks (CNNs), convolution operations, pooling, feature learning, and image classification. Transfer learning and pretrained models. Attention mechanisms and Vision Transformers (ViT). Self-supervised learning and vision foundation models. Video representation and analysis: optical flow, object detection, object tracking, pose estimation, and human activity recognition. Multimodal vision systems: image captioning, Vision-Language Models, Segment Anything Models (SAM), and Edge AI-based vision applications. Case studies on intelligent vision systems.