Useful Links
Computer Science
Computer Vision
Computer Vision and Image Analysis
1. Foundations of Computer Vision
2. Image Formation and Representation
3. Fundamental Image Processing
4. Feature Detection and Description
5. Image Segmentation
6. Classical Object Recognition
7. Deep Learning for Computer Vision
8. Motion and Video Analysis
9. 3D Computer Vision
10. Computer Vision Applications
Image Segmentation
Segmentation Fundamentals
Problem Definition
Segmentation Criteria
Evaluation Metrics
Ground Truth Issues
Thresholding Methods
Global Thresholding
Manual Threshold Selection
Histogram-based Methods
Otsu's Method
Triangle Method
Local Thresholding
Adaptive Methods
Local Statistics
Niblack's Method
Sauvola's Method
Multi-level Thresholding
Multiple Threshold Selection
Recursive Thresholding
Region-based Methods
Region Growing
Seed Point Selection
Homogeneity Criteria
Growing Strategies
Stopping Criteria
Region Splitting and Merging
Quadtree Representation
Split Criteria
Merge Criteria
Hierarchical Segmentation
Watershed Segmentation
Topographic Interpretation
Marker-based Watershed
Gradient Watershed
Over-segmentation Issues
Edge-based Methods
Edge Linking
Local Processing
Global Processing
Hough Transform
Active Contours
Snake Models
Energy Minimization
Gradient Vector Flow
Level Set Methods
Curve Evolution
Implicit Representation
Geometric Active Contours
Clustering Methods
K-means Clustering
Algorithm Steps
Initialization Methods
Feature Space Selection
Convergence Criteria
Mean Shift Clustering
Kernel Density Estimation
Mode Seeking
Bandwidth Selection
Fuzzy C-means
Fuzzy Membership
Objective Function
Algorithm Convergence
Graph-based Methods
Graph Construction
Node Definition
Edge Weights
Neighborhood Graphs
Graph Cuts
Min-cut Problem
Max-flow Algorithms
Energy Minimization
Interactive Segmentation
Normalized Cuts
Spectral Clustering
Eigenvalue Problems
Recursive Partitioning
Previous
4. Feature Detection and Description
Go to top
Next
6. Classical Object Recognition