Robust computer vision : theory and applications / by Nicu Sebe and Michael S. Lew.
From the foreword by Thomas Huang: "During the past decade, researchers in computer vision have found that probabilistic machine learning methods are extremely powerful. This book describes some of these methods. In addition to the Maximum Likelihood framework, Bayesian Networks, and Hidden Mar...
Saved in:
| Online Access: |
Full Text (via Springer) |
|---|---|
| Main Author: | |
| Other Authors: | |
| Format: | eBook |
| Language: | English |
| Published: |
Dordrecht ; Boston :
Kluwer Academic,
[2003]
|
| Series: | Computational imaging and vision ;
v. 26. |
| Subjects: |
MARC
| LEADER | 00000cam a2200000xi 4500 | ||
|---|---|---|---|
| 001 | b8016747 | ||
| 006 | m o d | ||
| 007 | cr ||||||||||| | ||
| 008 | 131029s2003 ne a ob 001 0 eng d | ||
| 005 | 20240418150257.3 | ||
| 020 | |a 9789401702959 |q (electronic bk.) | ||
| 020 | |a 9401702950 |q (electronic bk.) | ||
| 020 | |z 1402012934 | ||
| 020 | |z 9781402012938 | ||
| 024 | 7 | |a 10.1007/978-94-017-0295-9 | |
| 035 | |a (OCoLC)spr861706053 | ||
| 035 | |a (OCoLC)861706053 | ||
| 037 | |a spr978-94-017-0295-9 | ||
| 040 | |a GW5XE |b eng |e rda |e pn |c GW5XE |d OCLCQ |d UAB |d COO |d OCLCQ |d UKAHL |d OCLCO |d OCLCQ | ||
| 049 | |a GWRE | ||
| 050 | 4 | |a TA1634 |b .S42 2003eb | |
| 100 | 1 | |a Sebe, Nicu. |0 http://id.loc.gov/authorities/names/n2002014312 |1 http://isni.org/isni/0000000116692599. | |
| 245 | 1 | 0 | |a Robust computer vision : |b theory and applications / |c by Nicu Sebe and Michael S. Lew. |
| 264 | 1 | |a Dordrecht ; |a Boston : |b Kluwer Academic, |c [2003] | |
| 264 | 4 | |c ©2003. | |
| 300 | |a 1 online resource (xv, 215 pages) : |b illustrations. | ||
| 336 | |a text |b txt |2 rdacontent. | ||
| 337 | |a computer |b c |2 rdamedia. | ||
| 338 | |a online resource |b cr |2 rdacarrier. | ||
| 490 | 1 | |a Computational imaging and vision ; |v volume 26. | |
| 504 | |a Includes bibliographical references (pages 199-209) and index. | ||
| 505 | 0 | 0 | |g 1 |t Visual Similarity |g 2 -- |g 1.1 |t Color |g 4 -- |g 1.2 |t Texture |g 7 -- |g 1.3 |t Shape |g 9 -- |g 1.4 |t Stereo |g 11 -- |g 1.5 |t Motion |g 13 -- |g 1.6 |t Facial expression |g 13 -- |g 2 |t Evaluation of Computer Vision Algorithms |g 16 -- |g 2. |t Maximum Likelihood Framework |g 25 -- |g 2 |t Statistical Distributions |g 26 -- |g 2.1 |t Gaussian Distribution |g 27 -- |g 2.2 |t Exponential Distribution |g 38 -- |g 2.3 |t Cauchy Distribution |g 41 -- |g 3 |t Robust Statistics |g 43 -- |g 3.1 |t Outliers |g 44 -- |g 4 |t Maximum Likelihood Estimators |g 45 -- |g 5 |t Maximum Likelihood in Relation to Other Approaches |g 47 -- |g 6 |t Our Maximum Likelihood Approach |g 50 -- |g 6.1 |t Scale Parameter Estimation in a Cauchy Distribution |g 54 -- |g 7 |t Experimental Setup |g 57 -- |g 3. |t Color Based Retrieval |g 61 -- |g 2 |t Colorimetry |g 64 -- |g 3 |t Color Models |g 64 -- |g 3.1 |t RGB Color System |g 65 -- |g 3.2 |t HSV Color System |g 66 -- |g 3.3 |t l[subscript 1]l[subscript 2]l[subscript 3] Color System |g 67 -- |g 4 |t Color Based Retrieval |g 68 -- |g 4.1 |t Color Indexing |g 69 -- |g 5 |t Experiments with the Corel Database |g 73 -- |g 5.1 |t Early Experiments |g 73 -- |g 5.2 |t Usability Issues |g 74 -- |g 5.3 |t Printer-Scanner Noise Experiments |g 75 -- |g 5.4 |t Color Model |g 76 -- |g 5.5 |t Quantization |g 76 -- |g 5.6 |t Distribution Analysis |g 77 -- |g 6 |t Experiments with the Objects Database |g 79 -- |g 4. |t Robust Texture Analysis |g 83 -- |g 2 |t Human Perception of Texture |g 86 -- |g 3 |t Texture Features |g 87 -- |g 3.1 |t Texture Distribution Models |g 88 -- |g 3.1.1 |t Gray-level differences |g 89 -- |g 3.1.2 |t Laws' texture energy measures |g 89 -- |g 3.1.3 |t Center-symmetric covariance measures |g 89 -- |g 3.1.4 |t Local binary patterns and trigrams |g 91 -- |g 3.1.5 |t Complementary feature pairs |g 91 -- |g 3.2 |t Gabor and Wavelet Models |g 92 -- |g 4 |t Texture Classification Experiments |g 95 -- |g 4.2 |t Distribution Analysis |g 97 -- |g 4.3 |t Misdetection Rates |g 99 -- |g 5 |t Texture Retrieval Experiments |g 104 -- |g 5.1 |t Texture Features |g 105 -- |g 5.2 |t Experiments Setup |g 106 -- |g 5.3 |t Similarity Noise for QMF-Wavelet Transform |g 106 -- |g 5.4 |t Similarity Noise for Gabor Wavelet Transform |g 108 -- |g 5. |t Shape Based Retrieval |g 111 -- |g 2 |t Human Perception of Visual Form |g 113 -- |g 3 |t Active Contours |g 118 -- |g 3.1 |t Behavior of Traditional Active Contours |g 120 -- |g 3.2 |t Generalized Force Balance Equations |g 124 -- |g 3.3 |t Gradient Vector Flow |g 125 -- |g 4 |t Invariant Moments |g 130 -- |g 5 |t Experiments |g 131 -- |g 6. |t Robust Stereo Matching and Motion Tracking |g 135 -- |g 1.1 |t Stereoscopic Vision |g 137 -- |g 2 |t Stereo Matching |g 138 -- |g 3 |t Stereo Matching Algorithms |g 144 -- |g 3.1 |t Template Based Algorithm |g 144 -- |g 3.2 |t Multiple Windows Algorithm |g 146 -- |g 3.3 |t Cox' Maximum Likelihood Algorithm |g 147 -- |g 4 |t Stereo Matching Experiments |g 150 -- |g 4.1 |t Stereo Sets |g 151 -- |g 4.2 |t Stereo Matching Results |g 151 -- |g 5 |t Motion Tracking Experiments |g 157 -- |g 7. |t Facial Expression Recognition |g 163 -- |g 2 |t Emotion Recognition |g 166 -- |g 2.1 |t Judgment Studies |g 167 -- |g 2.2 |t Review of Facial Expression Recognition |g 167 -- |g 3 |t Face Tracking and Feature Extraction |g 171 -- |g 4 |t The Static Approach: Bayesian Network Classifiers |g 173 -- |g 4.1 |t Continuous Naive-Bayes: Gaussian and Cauchy Naive Bayes Classifiers |g 175 -- |g 4.2 |t Beyond the Naive-Bayes Assumption: Finding Dependencies among Features Using a Gaussian TAN Classifier |g 176 -- |g 5 |t The Dynamic Approach: Expression Recognition Using Multi-level HMMs |g 179 -- |g 5.1 |t Hidden Markov Models |g 182 -- |g 5.2 |t Expression Recognition Using Emotion-Specific HMMs |g 183 -- |g 5.3 |t Automatic Segmentation and Recognition of Emotions Using Multi-level HMM |g 184 -- |g 6 |t Experiments |g 187 -- |g 6.1 |t Results Using the Chen Database |g 191 -- |g 6.1.1 |t Person-Dependent Tests |g 191 -- |g 6.1.2 |t Person-Independent Tests |g 193 -- |g 6.2 |t Results Using the Cohn-Kanade Database |g 194. |
| 520 | |a From the foreword by Thomas Huang: "During the past decade, researchers in computer vision have found that probabilistic machine learning methods are extremely powerful. This book describes some of these methods. In addition to the Maximum Likelihood framework, Bayesian Networks, and Hidden Markov models are also used. Three aspects are stressed: features, similarity metric, and models. Many interesting and important new results, based on research by the authors and their collaborators, are presented. Although this book contains many new results, it is written in a style that suits both experts and novices in computer vision." | ||
| 588 | 0 | |a Print version record. | |
| 650 | 0 | |a Computer vision. |0 http://id.loc.gov/authorities/subjects/sh85029549. | |
| 650 | 7 | |a Computer vision. |2 fast |0 (OCoLC)fst00872687. | |
| 700 | 1 | |a Lew, Michael S., |d 1965- |0 http://id.loc.gov/authorities/names/n00005441 |1 http://isni.org/isni/0000000114766208. | |
| 776 | 0 | 8 | |i Print version: |a Sebe, Nicu. |t Robust computer vision |z 1402012934 |w (DLC) 2003049630 |w (OCoLC)51912629. |
| 830 | 0 | |a Computational imaging and vision ; |v v. 26. |0 http://id.loc.gov/authorities/names/n94071648. | |
| 856 | 4 | 0 | |u https://colorado.idm.oclc.org/login?url=https://link.springer.com/10.1007/978-94-017-0295-9 |z Full Text (via Springer) |
| 907 | |a .b80167470 |b 02-01-22 |c 06-02-15 | ||
| 998 | |a web |b 01-31-22 |c b |d b |e - |f eng |g ne |h 0 |i 1 | ||
| 907 | |a .b80167470 |b 01-31-22 |c 06-02-15 | ||
| 944 | |a MARS - RDA ENRICHED | ||
| 956 | |a Computer Science | ||
| 915 | |a - | ||
| 956 | |a Springer e-books: Archive | ||
| 956 | |a Springer e-books | ||
| 956 | |b Springer Nature - Springer Book Archive - Springer Computer Science | ||
| 999 | f | f | |i 1f678790-a743-5356-800f-9afc16a7ab5f |s 9d251378-f3c0-564b-9efa-c3ed04871679 |
| 952 | f | f | |p Can circulate |a University of Colorado Boulder |b Online |c Online |d Online |e TA1634 .S42 2003eb |h Library of Congress classification |i Ebooks, Prospector |n 1 |