Computer Vision

Resources and examples of application in Computer Vision Systems.

Introduction to Computer Vision

Overview of computer vision and its applications

Image representation and color models

Image formation and camera models

Image acquisition and preprocessing

Image Filtering and Enhancement

Spatial and frequency domain filtering techniques

Image enhancement methods (contrast enhancement, histogram equalization, etc.)

Noise removal and image restoration techniques

Image Transformations and Feature Extraction

Geometric transformations (rotation, scaling, translation, etc.)

Feature extraction techniques (edges, corners, texture features)

Scale-invariant feature transform (SIFT) and other feature descriptors

Deep Learning for Computer Vision

Introduction to deep learning and neural networks for vision

Convolutional Neural Networks (CNN) for image classification

Transfer learning and fine-tuning pre-trained models

Generative Adversarial Networks (GAN) for image synthesis

Object Detection and Localization

Object detection techniques (Haar cascades, R-CNN, SSD, YOLO)

Single-shot object detection and real-time detection

Evaluation metrics for object detection

Image Segmentation

Thresholding and region-based segmentation

Edge detection and boundary-based segmentation

Clustering-based segmentation (K-means, Mean Shift)

Semantic segmentation and instance segmentation

Deep Learning for Image Segmentation

Fully Convolutional Networks (FCN) for semantic segmentation

U-Net and other architectures for biomedical image segmentation

Mask R-CNN for instance segmentation

Evaluation metrics for image segmentation

Video Analysis and Processing

Video representation and motion estimation

Object tracking and multiple object tracking

Action recognition and activity analysis

Video surveillance and anomaly detection

Evaluation and Performance Metrics

Performance evaluation metrics for computer vision tasks

Precision, recall, F1-score, and mAP

Confusion matrices and error analysis

Experimental design and statistical analysis for computer vision

The best Computer Vision books

1. Computer Vision: Algorithms and Applications
2. Concise Computer Vision: An Introduction into Theory and Algorithms
3. Computer Vision: Principles, Algorithms, Applications, Learning
4. Computer Vision: Models, Learning, and Inference
5. Deep Learning for Vision Systems
6. Modern Computer Vision with PyTorch
7. Multiple View Geometry in Computer Vision
8. Dive into Deep Learning
9. Learning OpenCV 4 Computer Vision with Python 3
10. Computer Vision Metrics: Survey, Taxonomy, and Analysis