Early Visual Learning

Early Visual Learning

5 (1 rating by Goodreads)
Edited by  , Edited by 

List price: US$45.00

Currently unavailable

Add to wishlist

AbeBooks may have this title (opens in new window).

Try AbeBooks


Featuring contributions from experts in the field of computer vision, this work focuses on learning techniques that are applied more or less directly to the signals provided by vision sensors. The emphasis is on low-level visual learning techniques that draw on results in the fields of statistics, pattern recognition and neural networks. This book should be of interest to researchers and has potential as a graduate level text in a visual learning course.show more

Product details

  • Hardback | 378 pages
  • 184.15 x 262.89 x 22.86mm | 848.21g
  • Oxford University Press Inc
  • New York, United States
  • English
  • halftones, line figures, tables, bibliography
  • 0195095227
  • 9780195095227

Table of contents

1: Shree Nayar & Tomaso Poggio: Early Visual Learning. 2: Jon Pauls, Emanuela Bricolo, & Nikos Logothetis: View Invariant Representations in Monkey Temporal Cortex: Position, Scale, and Rotational Invariance. 3: Tomaso Poggio & David Beymer: Regularization Networks for Visual Learning. 4: Arthur R. Pope & David G. Lowe: Learning Probabilistic Appearance Models for Object Recognition. 5: Baback Moghaddam & Alex Pentland: Probabilistic Visual Learning for Object Representation. 6: Shree K. Nayar, Hiroshi Murase, & Sameer A. Nene: Parametric Appearance Representation. 7: Dean Pomerieau: Neural Network Vision for Robot Driving. 8: John J. Weng: Cresceptron and SHOSLIF: Toward Comprehensive Visual Learning. 9: Randal C. Nelson: Memorization Learning for Object Recognition. 10: Usama M. Fayyad, Padhraic H. Smyth, Michael C. Burt, & Pietro Perona: Learning to Catalog Science Images. 11: Bir Bhanu, Xing Wu, & Sungkee Lee: Genetic Algorithms for Adaptive Image Segmentation. 12: Hayit Greenspan: Non-Parametric Texture Learning. 13: Marcos Salganicoff, Michele Rucci, & Ruzena Bajcsy: Unsupervised Visual-Tactile Learning for Control of Manipulationshow more

Review quote

"The book has a lot to offer to researchers interested in recognition. With few exceptions the assembled papers describe systems that learn to recognize.' In particular almost half of the book is devoted to view-centered, appearance-based techniques for object recognition. . . .The reader gets a good overview of representations, techniques and methods well established and tested mainly in pattern recognition systems that are directly applicable in vision." --BMVA Newsshow more

Rating details

1 ratings
5 out of 5 stars
5 100% (1)
4 0% (0)
3 0% (0)
2 0% (0)
1 0% (0)
Book ratings by Goodreads
Goodreads is the world's largest site for readers with over 50 million reviews. We're featuring millions of their reader ratings on our book pages to help you find your new favourite book. Close X