Free PDF version available on the website<br><blockquote type="cite" style="color:rgb(34,34,34);font-family:arial,sans-serif;font-size:13px;background-color:rgb(255,255,255)"><div dir="ltr"><div class="gmail_quote">---------- Forwarded message ----------<br>
From: <b class="gmail_sendername">Simon Prince</b> <span dir="ltr"><<a href="mailto:s.prince@cs.ucl.ac.uk" target="_blank" style="color:rgb(17,85,204)">s.prince@cs.ucl.ac.uk</a>></span><br>Date: Sat, Sep 1, 2012 at 5:57 PM<br>
Subject: [Imageworld] New vision textbook now available<br>To: <a href="mailto:imageworld@diku.dk" target="_blank" style="color:rgb(17,85,204)">imageworld@diku.dk</a><br><br><br>COMPUTER VISION: MODELS, LEARNING AND INFERENCE<br>
<br>Simon J.D. Prince<br><br><br>This new computer vision textbook from Cambridge University Press is now available from all good booksellers. The final electronic version has also been posted at the book website:<br><br>
<a href="http://www.computervisionmodels.com/" target="_blank" style="color:rgb(17,85,204)">http://www.computervisionmodels.com</a><br><br>This website also includes more than 1000 powerpoint slides to accompany the text as well as answers to the problems, and an algorithm booklet including pseudocode for more than 70 of the algorithms discussed in the book.<br>
<br>The book would be suitable for an advanced undergraduate or graduate course in computer vision or machine learning. It would also be useful for most computer vision MSc and PhD students in these areas.<br><br>The book is divided into six parts.<br>
<br><br>PART I: PROBABILITY<br><br>1. Introduction. 2. Joint, marginal, conditional probability, independence, expectation. 3. Probability distributions, conjugacy. 4. ML, MAP and Bayesian approaches. 5. The multivariate normal distribution.<br>
<br><br>PART II: MACHINE LEARNING<br><br>6. Introduction to machine learning, generative and discriminative models. 7. Hidden variables, MoG, t-distributions, factor analysis, EM algorithm. 8. Linear regression, non-linear regression, Gaussian process regression, relevance vector regression. 9. Logistic regression, Gaussian process classification, boosting, classification trees.<br>
<br><br>PART III: CONNECTING LOCAL MODELS<br><br>10. Conditional independence, directed and undirected graphical models, ancestral sampling, Gibbs sampling, contrastive divergence. 11. Hidden Markov models, dynamic programming, belief propagation. 12. Markov random fields, binary graph cuts, multi-label graph cuts, alpha-expansion algorithm.<br>
<br><br>PART IV: PREPROCESSING<br><br>13. Image preprocessing, filtering, edge and corner detectors, local binary patterns, SIFT, HoG, principal components analysis, k-means algorithm.<br><br><br>PART V: GEOMETRY<br><br>
14. Pinhole camera model, homogeneous coordinates, estimating camera pose, calibration, reconstruction. 15. Transformations, fitting transformations, estimating pose to planem, calibration from planes, homographies, RANSAC, PEaRL. 16. Epipolar geometry, essential and fundamental matrices, bundle adjustment, rectification, multi-view reconstruction.<br>
<br><br>PART VI: COMPUTER VISION MODELS<br><br>17. Snakes, shape template models, statistical shape models, active shape models, active appearance models, GPLVM, articulated models. 18. Identity recognition, subspace models, probabilistic linear discriminant analysis, bilinear models, multi-linear models, multi-factor GPLVM. 19. Kalman filter, extended Kalman filter, unscented Kalman filter, particle filters. 20. Bag of words, latent Dirichlet allocation, spatial extensions to BoW.<br>
<br><br>APPENDICES<br><br>A. Notation. B. Optimization. C. Linear algebra.<br><br>Each part contains illustrative applications including background subtraction, skin detection, body pose regression, face detection, pedestrian detection, segmentation, semantic segmentation, stereo vision, image denoising, image synthesis, shape from silhouette, structured light, augmented reality tracking, creating visual panoramas, multi-view reconstruction, 3D morphable models, face recognition, tracking objects in 2D and 3D, SLAM, and object recognition.<br>
<br><br><br>--<br><br>Dr. Simon J.D. Prince<br>Department of Computer Science<br>University College London<br>Gower Street<br>London, WC1E 6BT<br>Tel. 020 7679 3692<br>Fax. 020 7387 1397<br><br><a href="http://pvl.cs.ucl.ac.uk/" target="_blank" style="color:rgb(17,85,204)">http://pvl.cs.ucl.ac.uk</a></div>
</div></blockquote>