Mode of access: World Wide Web.

System requirements: Adobe Acrobat Reader.

Part of: Synthesis digital library of engineering and computer science.

Includes bibliographical references (pages 77-98).

1. Visual patterns and texture -- 1.1 Patterns in nature -- 1.2 Big data patterns -- 1.3 Temporal patterns -- 1.4 Organization --

2. Textons in human and computer vision -- 2.1 Pre-attentive vision -- 2.2 Texton: the early definition -- 2.3 What are textons? Then and now --

3. Texture recognition -- 3.1 Traditional methods of texture recognition -- 3.2 From textons to deep learning for recognition -- 3.3 Texture recognition with deep learning -- 3.4 Material recognition vs. texture recognition --

4. Texture segmentation -- 4.1 Traditional methods of texture segmentation -- 4.1.1 Graph-based methods -- 4.1.2 Mean shift methods -- 4.1.3 Markov random fields -- 4.2 Segmentation with deep learning --

5. Texture synthesis -- 5.1 Traditional methods for texture synthesis -- 5.2 Texture synthesis with deep learning --

6. Texture style transfer -- 6.1 Traditional methods of style transfer -- 6.2 Texture style transfer with deep learning -- 6.3 Face style transfer --

7. Return of the pyramids -- 7.1 Advantages of pyramid methods --

8. Open issues in understanding visual patterns -- 8.1 Discovering unknown patterns -- 8.2 Detecting subtle change -- 8.3 Perceptual metrics --

9. Applications for texture and patterns -- 9.1 Medical imaging and quantitative dermatology -- 9.2 Texture matching in industry -- 9.3 E-commerce -- 9.4 Textured solar panels -- 9.5 Road analysis for automated driving --

10. Tools for mining patterns: cloud services and software libraries -- 10.1 Software libraries -- 10.2 Cloud services --

A. A concise description of deep learning -- A.1 Multilayer perceptron -- A.2 Convolutional neural networks -- A.3 Alexnet, Dense-Net, Res-Nets, and all that --

Bibliography -- Author's biography.

Abstract freely available; full-text restricted to subscribers or individual document purchasers.

Compendex

INSPEC

Google scholar

Google book search

Visual pattern analysis is a fundamental tool in mining data for knowledge. Computational representations for patterns and texture allow us to summarize, store, compare, and label in order to learn about the physical world. Our ability to capture visual imagery with cameras and sensors has resulted in vast amounts of raw data, but using this information effectively in a task-specific manner requires sophisticated computational representations. We enumerate specific desirable traits for these representations: (1) intraclass invariance--to support recognition; (2) illumination and geometric invariance for robustness to imaging conditions; (3) support for prediction and synthesis to use the model to infer continuation of the pattern; (4) support for change detection to detect anomalies and perturbations; and (5) support for physics-based interpretation to infer system properties from appearance. In recent years, computer vision has undergone a metamorphosis with classic algorithms adapting to new trends in deep learning. This text provides a tour of algorithm evolution including pattern recognition, segmentation and synthesis. We consider the general relevance and prominence of visual pattern analysis and applications that rely on computational models.

Also available in print.

Title from PDF title page (viewed on September 26, 2018).