Muutke küpsiste eelistusi

E-raamat: Cognitive and Neural Modelling for Visual Information Representation and Memorization [Taylor & Francis e-raamat]

  • Formaat: 249 pages, 21 Tables, black and white; 46 Line drawings, black and white; 44 Halftones, black and white; 90 Illustrations, black and white
  • Ilmumisaeg: 25-Apr-2022
  • Kirjastus: CRC Press
  • ISBN-13: 9781003281641
Teised raamatud teemal:
  • Taylor & Francis e-raamat
  • Hind: 124,64 €*
  • * hind, mis tagab piiramatu üheaegsete kasutajate arvuga ligipääsu piiramatuks ajaks
  • Tavahind: 178,05 €
  • Säästad 30%
Cognitive and Neural Modelling for Visual Information Representation and MemorizationSuurem pilt
  • Formaat: 249 pages, 21 Tables, black and white; 46 Line drawings, black and white; 44 Halftones, black and white; 90 Illustrations, black and white
  • Ilmumisaeg: 25-Apr-2022
  • Kirjastus: CRC Press
  • ISBN-13: 9781003281641
Teised raamatud teemal:
Taylor & Francis e-raamatudRohkem infot Taylor & Francis e-raamatute kohta
Raamatu kodulehekülg: https://www.taylorfrancis.com/books/9781003281641
"Focusing on how visual information is represented, stored and extracted in the human brain, this book uses cognitive neural modeling in order to show how visual information is represented and memorized in the brain. Breaking through traditional visual information processing methods, the author combines our understanding of perception and memory from the human brain with computer vision technology, and provides a new approach for image recognition and classification. While biological visual cognition models and human brain memory models are established, applications such as pest recognition and carrot detection are also involved in this book. Given the range of topics covered, this book is a valuable resource for students, researchers and practitioners interested in the rapidly evolving field of neurocomputing, computer vision and machine learning"--

Focusing on how visual information is represented, stored and extracted in the human brain, this book uses cognitive neural modeling in order to show how visual information is represented and memorized in the brain.
Chapter 1 Introduction
1(22)
1.1 Background
1(2)
1.2 Research Status Of The Subject
3(10)
1.2.1 Review of biological visual perception
3(5)
1.2.2 Review of brain memory model
8(3)
1.2.3 Review of Bayesian brain and free energy theory
11(2)
1.3 Main Content
13(2)
1.4 Conclusions
15(1)
References
15(8)
Chapter 2 Methods of visual perception and memory modelling
23(22)
2.1 Introduction
23(1)
2.2 Mechanism And Model Of Biological Visual Perception
24(3)
2.2.1 Physiological basis of biological visual perception
24(1)
2.2.2 HMAX model
25(2)
2.3 Convolutional Neural Networks
27(3)
2.4 Neural Mechanism Of Memory
30(3)
2.5 Method Of Memory Modelling
33(9)
2.5.1 Memory model based on cognitive psychology
33(4)
2.5.2 Memory model based on cognitive neurology
37(2)
2.5.3 Association-based memory model
39(3)
2.6 Conclusions
42(1)
References
42(3)
Chapter 3 Bio-inspired model for object recognition based on histogram of oriented gradients
45(16)
3.1 Introduction
45(1)
3.2 Related Work
46(1)
3.2.1 Hmax model
46(1)
3.2.2 Hog algorithm
46(1)
3.3 Hog-Hmax Model
46(4)
3.3.1 S1 layer
47(1)
3.3.2 C2 layer
48(1)
3.3.3 S2 layer
49(1)
3.3.4 C2 layer
50(1)
3.3.5 Prototypes learning stage
50(1)
3.4 Results
50(7)
3.4.1 Caltech5 dataset
50(4)
3.4.2 Caltech 101 dataset
54(2)
3.4.3 Caltech 256 dataset
56(1)
3.5 Conclusions
57(1)
References
58(3)
Chapter 4 Modelling object recognition in visual cortex using multiple firing K-means and non-negative sparse coding
61(34)
4.1 Introduction
61(2)
4.2 Related Work
63(2)
4.2.1 The HMAX model
63(2)
4.2.2 Non-negative sparse coding (NNSC)
65(1)
4.3 Overview Of The Proposed Sparse-Hmax Model
65(4)
4.3.1 Structure of the proposed method
65(3)
4.3.2 Template selection method
68(1)
4.4 Results And Discussion
69(11)
4.4.1 Caltech 101 database
69(7)
4.4.2 Caltech 256 database
76(3)
4.4.3 GRAZ-01 database
79(1)
4.4.4 Template selection method
80(1)
4.5 Conclusions
80(3)
References
83(3)
Appendix
86(9)
Chapter 5 Biological modelling of the human visual system using GLoP filters and sparse coding on multi-manifolds
95(30)
5.1 Introduction
95(3)
5.2 Method
98(9)
5.2.1 HMAX model
98(1)
5.2.2 The proposed model
99(8)
5.3 Experimental Results
107(10)
5.3.1 Effectiveness analysis of GLoP niters, SIFT features, SCMM, and DLMM
107(2)
5.3.2 Evaluation of local rotation
109(1)
5.3.3 GRAZ-01 dataset
110(3)
5.3.4 CGTL-20 dataset
113(3)
5.3.5 Scene 13 dataset
116(1)
5.4 Discussion
117(3)
5.4.1 Computer vision perspective on the E-HMAX
117(2)
5.4.2 Invariance of local rotation
119(1)
5.4.3 Limitations and possible improvement
119(1)
5.5 Conclusions
120(1)
References
120(5)
Chapter 6 Increment learning and rapid retrieval of visual information based on pattern association memory
125(30)
6.1 Introduction
125(2)
6.2 Pattern Association Memory
127(2)
6.3 Increment Pattern Association Memory Model (Ipamm)
129(4)
6.3.1 Feature extraction
129(2)
6.3.2 Increment learning
131(1)
6.3.3 Recall
132(1)
6.4 Experimental Results
133(6)
6.4.1 Caltech 5 dataset
134(4)
6.4.2 Caltech 256 dataset
138(1)
6.4.3 Scene 15 dataset
138(1)
6.5 Discussion
139(1)
6.5.1 Capacity
139(1)
6.5.2 Speed
139(1)
6.5.3 Future work
140(1)
6.6 Conclusions
140(1)
References
141(3)
Appendix
144(11)
Chapter 7 Memory modelling based on free energy theory and the restricted Boltzmann machine
155(50)
7.1 Introduction
155(1)
7.2 Theory Of Free Energy
156(3)
7.3 Restricted Boltzmann Machines
159(4)
7.3.1 RBM model
160(1)
7.3.2 Classification restricted Boltzmann machine
161(2)
7.4 Memory Model Based On Free Energy Theory And Classification Constrained Boltzmann Machine
163(7)
7.4.1 Definition of free energy function
163(2)
7.4.2 Model learning
165(4)
7.4.3 Recall
169(1)
7.5 Experimental Results
170(6)
7.5.1 Experimental setup
170(1)
7.5.2 Corel-1000 dataset
170(4)
7.5.3 UIUC Sports dataset
174(2)
7.6 Conclusions
176(1)
References
176(1)
Appendix
177(28)
Chapter 8 Research on insect pest image detection and recognition based on bio-inspired methods
205(20)
8.1 Introduction
205(2)
8.2 Materials And Methods
207(8)
8.2.1 Materials
207(1)
8.2.2 Methods
207(8)
8.3 Experimental Results
215(5)
8.3.1 Effectiveness analysis of template number
216(1)
8.3.2 Results of object detection
217(1)
8.3.3 Performance evaluation
217(3)
8.4 Discussion
220(1)
8.5 Conclusions
221(1)
References
221(2)
Appendix
223(2)
Chapter 9 Carrot defect detection and grading based on computer vision and deep learning
225(22)
9.1 Introduction
225(2)
9.2 Material And Methods
227(8)
9.2.1 Materials
227(1)
9.2.2 Image acquisition and dataset collection
227(1)
9.2.3 Carrot defect detection model based on deep learning
228(3)
9.2.4 Grading methods based on MBR fitting and convex polygon approximation
231(2)
9.2.5 Algorithm of defect detection and grading
233(1)
9.2.6 Evaluation standards
234(1)
9.3 Results And Discussion
235(9)
9.3.1 Effects of model parameters on CDDNet
235(1)
9.3.2 Performance of CDDNet to detect defective carrots
236(5)
9.3.3 Evaluation of carrot grading method
241(2)
9.3.4 Practicability of the proposed approach
243(1)
9.4 Conclusions
244(1)
References
244(3)
Conclusions 247(1)
Summary 247(2)
Future Work 249
Limiao Deng is currently working as an associate professor in Qingdao Agriculture University, China. She received the Ph.D. degree in Control Theory and Control Engineering from China University of Petroleum in 2018. Her areas of research include computer vision, machine learning and pattern recognition. She is also a regular reviewer of journals of repute namely IEEE, Springer, Elsevier, etc.
Püsilink: https://www.kriso.ee/db/9781003281641_pe.html
Märksõnad: