Computer Vision and Image Analysis

6.

Classical Object Recognition

6.1.

Template Matching

6.1.1.

Cross-correlation Methods

6.1.1.1.

Normalized Cross-correlation

6.1.1.2.

Phase Correlation

6.1.2.

Template Variations

6.1.2.1.

Multi-scale Templates

6.1.2.2.

Rotated Templates

6.1.2.3.

Deformable Templates

6.1.3.

Matching Metrics

6.1.3.1.

Sum of Squared Differences

6.1.3.2.

Sum of Absolute Differences

6.1.3.3.

Correlation Coefficient

6.2.

Sliding Window Detection

6.2.1.

6.2.1.1.

6.2.1.2.

6.2.1.3.

Stride Parameters

6.2.2.

Multi-scale Detection

6.2.2.1.

6.2.2.2.

Scale-space Search

6.2.2.3.

Computational Efficiency

6.2.3.

Non-maximum Suppression

6.2.3.1.

Overlap Criteria

6.2.3.2.

Score-based Selection

6.2.3.3.

Greedy Algorithms

6.3.

Bag of Visual Words

6.3.1.

Feature Extraction

6.3.1.1.

Local Feature Detection

6.3.1.2.

Descriptor Computation

6.3.1.3.

Feature Sampling

6.3.2.

Codebook Construction

6.3.2.1.

K-means Clustering

6.3.2.2.

Vocabulary Size Selection

6.3.2.3.

Hierarchical Vocabularies

6.3.3.

Image Representation

6.3.3.1.

Histogram Construction

6.3.3.2.

6.3.3.3.

Spatial Information

6.3.4.

6.3.4.1.

Support Vector Machines

6.3.4.2.

Nearest Neighbor Methods

6.3.4.3.

Ensemble Methods

6.4.

Viola-Jones Framework

6.4.1.

Haar-like Features

6.4.1.1.

Rectangle Features

6.4.1.2.

6.4.1.3.

Integral Image Computation

6.4.2.

AdaBoost Learning

6.4.2.1.

Weak Classifier Selection

6.4.2.2.

6.4.2.3.

Strong Classifier Construction

6.4.3.

Cascade Structure

6.4.3.1.

6.4.3.2.

Rejection Thresholds

6.4.3.3.

Computational Efficiency

6.4.4.

Detection Process

6.4.4.1.

Multi-scale Scanning

6.4.4.2.

Post-processing

6.4.4.3.

False Positive Reduction

Previous

5. Image Segmentation

Go to top

Next

7. Deep Learning for Computer Vision