Caltech Library System

About | Browse | Search | Caltech Student Instructions

Type of Document	Dissertation
Author	Holub, Alex David
URN	etd-05312007-204007
Persistent URL	http://resolver.caltech.edu/CaltechETD:etd-05312007-204007
Title	Discriminative vs. generative object recognition : objects, faces, and the web
Degree	PhD
Option	Computation and Neural Systems
Advisory Committee	Advisor Name Title Pietro Perona Committee Chair Max Welling Committee Member Michael Burl Committee Member Shin Shimojo Committee Member Yaser Abu-Mostafa Committee Member
Keywords	statistical learning computer vision machine learning object recognition
Date of Defense	2007-04-30
Availability	restricted
Abstract The ability to automatically identify and recognize objects in images remains one of the most challenging and potentially useful problems in computer vision. Despite significant progress over the past decade computers are not yet close to matching human performance. This thesis develops various machine learning approaches for improving the ability of computers to recognize object categories. In particular, it focuses on approaches which are able to distinguish between object categories which are visually similar to one another. Examples of similar visual object categories are motorcycles and bicycles, and lions and cougars. Distinguishing between similar object categories may require different algorithms than distinguishing between different categories. We explore two common machine learning paradigms, generative and discriminative learning, and analyze their respective abilities to distinguish between different sets of object categories. One set of object categories which we are exposed to on a daily basis are face images, and a significant portion of this thesis is spent analyzing different methods for accurately representing and discriminating between faces. We also address a key issue related to the discriminative learning paradigms, namely how to collect the large training set of images necessary to accurately learn discriminative models. In particular, we suggest a novel active learning which intelligently chooses the most informative image to label and thus drastically reduces (up to 10x) the time required to collect a training set. We validate and analyze our algorithms on large data-sets collected from the web and show how using hybrid generative-discriminative techniques can drastically outperform previous algorithms. In addition, we show how to use our techniques in practical applications such as finding similar-looking individuals within large data-sets of faces, discriminating between large sets of visual categories, and increasing the efficiency and speed of web-image searchi
Files	Filename       Size       Approximate Download Time (Hours:Minutes:Seconds)     28.8 Modem   56K Modem   ISDN (64 Kb)   ISDN (128 Kb)   Higher-speed Access  holub_thesis.pdf 17.40 Mb 01:20:34 00:41:26 00:36:15 00:18:07 00:01:32 indicates that a file or directory is accessible from the campus network only and must not be distributed to non-campus persons.