Your session will expire automatically in 0 seconds.
LEADER 00000cam 2200301 a 4500
005 20120817161044.0
008 120323s2012 nyua b 001 0 eng
010 2012008187
019 17224176
020 9781107011793 (hardback)
040 DLC|cDLC|dDLC
042 pcc
050 00 TA1634|b.P75 2012
100 1 Prince, Simon J. D.|q(Simon Jeremy Damion),|d1972-
245 10 Computer vision :|bmodels, learning, and inference /
|cSimon J.D. Prince.
260 New York :|bCambridge University Press,|c2012.
300 xviii, 580 p. :|bill. (some col.) ;|c26 cm.
504 Includes bibliographical references (p. 533-566) and
index.
505 8 Machine generated contents note: Part I. Probability: 1.
Introduction to probability; 2. Common probability
distributions; 3. Fitting probability models; 4. The
normal distribution; Part II. Machine Learning for Machine
Vision: 5. Learning and inference in vision; 6. Modeling
complex data densities; 7. Regression models; 8.
Classification models; Part III. Connecting Local Models:
9. Graphical models; 10. Models for chains and trees; 11.
Models for grids; Part IV. Preprocessing: 12. Image
preprocessing and feature extraction; Part V. Models for
Geometry: 13. The pinhole camera; 14. Models for
transformations; 15. Multiple cameras; Part VI. Models for
Vision: 16. Models for style and identity; 17. Temporal
models; 18. Models for visual words; Part VII. Appendices:
A. Optimization; B. Linear algebra; C. Algorithms.
520 "This modern treatment of computer vision focuses on
learning and inference in probabilistic models as a
unifying theme. It shows how to use training data to learn
the relationships between the observed image data and the
aspects of the world that we wish to estimate, such as the
3D structure or the object class, and how to exploit these
relationships to make new inferences about the world from
new image data. With minimal prerequisites, the book
starts from the basics of probability and model fitting
and works up to real examples that the reader can
implement and modify to build useful vision systems.
Primarily meant for advanced undergraduate and graduate
students, the detailed methodological presentation will
also be useful for practitioners of computer vision.
[bullet] Covers cutting-edge techniques, including graph
cuts, machine learning and multiple view geometry [bullet]
A unified approach shows the common basis for solutions of
important computer vision problems, such as camera
calibration, face recognition and object tracking [bullet]
More than 70 algorithms are described in sufficient detail
to implement [bullet] More than 350 full-color
illustrations amplify the text [bullet] The treatment is
self-contained, including all of the background
mathematics [bullet] Additional resources at
www.computervisionmodels.com"--|cProvided by publisher.
650 0 Computer vision
856 42 |3Cover image|uhttp://assets.cambridge.org/97811070/11793/
cover/9781107011793.jpg