Muutke küpsiste eelistusi

Content-Based Image Classification: Efficient Machine Learning Using Robust Feature Extraction Techniques [Kõva köide]

(Siemens Technology and Services Pvt. Ltd., Bengaluru)
  • Formaat: Hardback, 180 pages, kõrgus x laius: 234x156 mm, kaal: 435 g, 33 Tables, black and white; 91 Illustrations, black and white
  • Ilmumisaeg: 18-Dec-2020
  • Kirjastus: Chapman & Hall/CRC
  • ISBN-10: 036737160X
  • ISBN-13: 9780367371609
Teised raamatud teemal:
Content-Based Image Classification: Efficient Machine Learning Using Robust Feature Extraction TechniquesSuurem pilt
  • Formaat: Hardback, 180 pages, kõrgus x laius: 234x156 mm, kaal: 435 g, 33 Tables, black and white; 91 Illustrations, black and white
  • Ilmumisaeg: 18-Dec-2020
  • Kirjastus: Chapman & Hall/CRC
  • ISBN-10: 036737160X
  • ISBN-13: 9780367371609
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9780367371609.html
Märksõnad:
Content-Based Image Classification: Efficient Machine Learning Using Robust Feature Extraction Techniques is a comprehensive guide to research with invaluable image data. Social Science Research Network has revealed that 65% of people are visual learners. Research data provided by Hyerle (2000) has clearly shown 90% of information in the human brain is visual. Thus, it is no wonder that visual information processing in the brain is 60,000 times faster than text-based information (3M Corporation, 2001). Recently, we have witnessed a significant surge in conversing with images due to the popularity of social networking platforms. The other reason for embracing usage of image data is the mass availability of high-resolution cellphone cameras. Wide usage of image data in diversified application areas including medical science, media, sports, remote sensing, and so on, has spurred the need for further research in optimizing archival, maintenance, and retrieval of appropriate image content to leverage data-driven decision-making. This book demonstrates several techniques of image processing to represent image data in a desired format for information identification. It discusses the application of machine learning and deep learning for identifying and categorizing appropriate image data helpful in designing automated decision support systems.

The book offers comprehensive coverage of the most essential topics, including:











Image feature extraction with novel handcrafted techniques (traditional feature extraction)





Image feature extraction with automated techniques (representation learning with CNNs)





Significance of fusion-based approaches in enhancing classification accuracy





MATLAB® codes for implementing the techniques





Use of the Open Access data mining tool WEKA for multiple tasks

The book is intended for budding researchers, technocrats, engineering students, and machine learning/deep learning enthusiasts who are willing to start their computer vision journey with content-based image recognition. The readers will get a clear picture of the essentials for transforming the image data into valuable means for insight generation. Readers will learn coding techniques necessary to propose novel mechanisms and disruptive approaches. The WEKA guide provided is beneficial for those uncomfortable coding for machine learning algorithms. The WEKA tool assists the learner in implementing machine learning algorithms with the click of a button. Thus, this book will be a stepping-stone for your machine learning journey.

Please visit the author's website for any further guidance at https://www.rikdas.com/
Preface xiii
Author xv
1 Introduction to Content-Based Image Classification
1(14)
1.1 Prelude
1(2)
1.2 Metrics
3(1)
1.2.1 Precision
3(1)
1.2.2 True Positive (TP) Rate/Recall
3(1)
1.2.3 Misclassification Rate (MR)
3(1)
1.2.4 Fl-Score
3(1)
1.2.5 Accuracy
4(1)
1.2.6 False Positive (FP) Rate
4(1)
1.2.7 True Negative (TN) Rate
4(1)
1.2.8 False Negative (FN) Rate
4(1)
1.3 Classifiers
4(4)
1.3.1 KNN Classifier
5(1)
1.3.2 Random Forest Classifier
5(1)
1.3.3 ANN Classifier
6(1)
1.3.4 SVM Classifier
7(1)
1.4 Datasets Used
8(3)
1.4.1 Wang Dataset
8(1)
1.4.2 Caltech Dataset
8(1)
1.4.3 Corel Dataset
9(1)
1.4.4 Oliva Torralba (OT-Scene) Dataset
9(2)
1.5 Organization of the Book
11(1)
Chapter Summary
12(1)
References
12(3)
2 A Review of Handcrafted Feature Extraction Techniques for Content-Based Image Classification
15(24)
2.1 Prelude
15(1)
2.2 Extraction of Features with Color Contents
15(1)
2.3 Extraction of Features with Image Binarization
16(2)
2.4 Extraction of Features with Image Transforms
18(1)
2.5 Extraction of Features with Morphological Processing
19(2)
2.6 Extraction of Features with Texture Content
21(1)
2.7 Fusion of Features Extracted with Multiple Techniques
22(2)
2.8 Techniques of Classification
24(1)
2.9 Logic-Based Algorithms
24(5)
2.9.1 Decision Trees
24(1)
2.9.2 Learning a Set of Rules
25(2)
2.9.3 Perceptron-Based Techniques
27(1)
2.9.3.1 Single-Layer Perceptrons
27(1)
2.9.3.2 Multilayer Perceptrons
27(1)
2.9.4 Statistical Learning Algorithm
28(1)
2.9.5 Support Vector Machine
28(1)
Chapter Summary
29(1)
References
30(9)
3 Content-Based Feature Extraction: Color Averaging
39(22)
3.1 Prelude
39(1)
3.2 Block Truncation Coding
40(1)
3.3 Feature Extraction Using Block Truncation Coding with Color Clumps
40(2)
3.4 Code Example (MATLAB®)
42(2)
3.5 Coding Exercise
44(2)
3.6 Feature Extraction Using Sorted Block Truncation Coding for Content-Based Image Classification
46(2)
3.7 Code Example (MATLAB)
48(1)
3.8 Coding Exercise
49(3)
3.9 Comparison of Proposed Techniques
52(1)
3.10 Comparison with Existing Techniques
53(1)
3.11 Statistical Significance
54(3)
Chapter Summary
57(1)
References
58(3)
4 Content-Based Feature Extraction: Image Binarization
61(32)
4.1 Prelude
61(1)
4.2 Feature Extraction Using Mean Threshold Selection
62(2)
4.2.1 Feature Extraction with Multilevel Mean Threshold Selection
62(2)
4.3 Code Example (MATLAB®)
64(1)
4.4 Coding Exercise
65(1)
4.5 Feature Extraction from Significant Bit Planes Using Mean Threshold Selection
66(3)
4.6 Code Example (MATLAB)
69(1)
4.7 Coding Exercise
70(1)
4.8 Feature Extraction from Even and Odd Image Varieties Using Mean Threshold Selection
70(2)
4.9 Code Example (MATLAB)
72(1)
4.10 Coding Exercise
73(1)
4.11 Feature Extraction with Static and Dynamic Ternary Image Maps Using Mean Threshold Selection
73(3)
4.12 Code Example (MATLAB)
76(2)
4.13 Feature Extraction Using Local Threshold Selection
78(1)
4.14 Code Example (MATLAB)
79(1)
4.15 Coding Exercise
80(1)
4.16 Comparing the Discussed Techniques for Performance Evaluation
80(1)
4.17 Comparison with Existing Techniques
80(5)
4.18 Statistical Significance
85(6)
Chapter Summary
91(1)
References
91(2)
5 Content-Based Feature Extraction: Image Transforms
93(24)
5.1 Prelude
93(1)
5.2 Generating Partial Energy Coefficient from Transformed Images
94(1)
5.3 Code Example (MATLAB®)
95(1)
5.4 Coding Exercise
96(1)
5.5 Computational Complexity for the Image Transforms
96(1)
5.6 Feature Extraction with Partial Energy Coefficient
97(11)
5.6.1 Discrete Cosine Transform
97(1)
5.6.2 Walsh Transform
98(4)
5.6.3 Kekre Transform
102(3)
5.6.4 Discrete Sine Transform
105(1)
5.6.5 Discrete Hartley Transform
106(2)
5.7 Evaluation of the Proposed Techniques
108(1)
5.8 Comparison with Existing Techniques
109(1)
5.9 Statistical Significance
110(4)
Chapter Summary
114(1)
References
115(2)
6 Content-Based Feature Extraction: Morphological Operators
117(16)
6.1 Prelude
117(1)
6.2 Top-Hat Transform
118(2)
6.3 Code Example (MATLAB*)
120(1)
6.4 Coding Exercise
120(1)
6.5 Bottom-Hat Transform
121(2)
6.6 Code Example (MATLAB)
123(1)
6.7 Coding Exercise
123(1)
6.8 Comparison of Proposed Techniques
124(3)
6.9 Comparison with Existing Methods
127(1)
6.10 Statistical Significance
128(2)
Chapter Summary
130(1)
References
130(3)
7 Content-Based Feature Extraction: Texture Components
133(14)
7.1 Prelude
133(1)
7.2 Feature Extraction by Vector Quantization Codebook Representation Using Linde-Buzo-Grey (LBG) Algorithm
134(2)
7.3 Code Example (MATLAB®)
136(1)
7.4 Coding Exercise
137(1)
7.5 Feature Extraction by Gray Level Co-occurrence Matrix (GLCM)
137(2)
7.6 Code Example (MATLAB)
139(1)
7.7 Coding Exercise
139(1)
7.8 Evaluation of Proposed Techniques
140(1)
7.9 Comparison with Existing Methods
141(2)
7.10 Statistical Significance
143(2)
Chapter Summary
145(1)
References
146(1)
8 Fusion-Based Classification: A Comparison of Early Fusion and Late Fusion Architecture for Content-Based Features
147(14)
8.1 Prelude
147(1)
8.2 Image Preprocessing
148(1)
8.3 Feature Extraction with Image Binarization
149(3)
8.4 Feature Extraction Applying Discrete Cosine Transform (DCT)
152(1)
8.5 Classification Framework
153(5)
8.5.1 Method 1
153(3)
8.5.2 Method 2
156(2)
8.6 Classification Results
158(2)
Chapter Summary
160(1)
References
160(1)
9 Future Directions: A Journey from Handcrafted Techniques to Representation Learning
161(10)
9.1 Prelude
161(1)
9.2 Representation Learning-Based Feature Extraction
162(1)
9.3 Code Example (MATLAB")
163(1)
9.4 Image Color Averaging Techniques
164(1)
9.5 Binarization Techniques
165(1)
9.6 Image Transforms
166(1)
9.7 Morphological Operations
166(1)
9.8 Texture Analysis
167(1)
9.9 Multitechnique Feature Extraction for Decision Fusion-Based Classification
167(1)
9.10 Comparison of Cross Domain Feature Extraction Techniques
168(1)
9.11 Future Work
168(1)
References
169(2)
10 WEKA: Beginners' Tutorial
171(6)
10.1 Prelude
171(1)
10.2 Getting Started with WEKA
171(6)
References 177(2)
Index 179
Rik Das is a PhD (Tech.) and M.Tech. in Information Technology from the University of Calcutta, India. He is also a B.E. in Information Technology from the University of Burdwan, India. Rik has filed and published two Indian patents consecutively during the year 2018 and 2019 and has over 40 International publications till date. He has collaborated with professionals from leading multinational software companies and with Professors and researchers of Universities in India and abroad for research work in the domain of content based image classification. Rik has over 16 years of experience in research and academia and is currently an Assistant Professor for the Program of Information Technology at Xavier Institute of Social Service (XISS), Ranchi, India.

Rik is appointed as a Distinguished Speaker of the Association of Computing Machinery (ACM), New York, USA. He is featured in uLektz Wall of Fame as one of the "Top 50 Tech Savvy Academicians in Higher Education across India" for the year 2019. He is also a Member of International Advisory Committee of AI-Forum, UK. Rik has founded a YouTube channel named 'Curious Neuron' to disseminate knowledge and information to larger communities in the domain of machine learning, research and development and open source programming languages.