Learning and Example Selection for Object and Pattern Detection

Item

Title: en_US Learning and Example Selection for Object and Pattern Detection
Creator: en_US Sung, Kah-Kay
Date: 2004-10-20T14:45:19Z
Date Available: 2004-10-20T14:45:19Z
Date Issued: en_US 1996-03-13
Identifier: en_US AITR-1572
uri: http://hdl.handle.net/1721.1/6774
Abstract: en_US This thesis presents a learning based approach for detecting classes of objects and patterns with variable image appearance but highly predictable image boundaries. It consists of two parts. In part one, we introduce our object and pattern detection approach using a concrete human face detection example. The approach first builds a distribution-based model of the target pattern class in an appropriate feature space to describe the target's variable image appearance. It then learns from examples a similarity measure for matching new patterns against the distribution-based target model. The approach makes few assumptions about the target pattern class and should therefore be fairly general, as long as the target class has predictable image boundaries. Because our object and pattern detection approach is very much learning-based, how well a system eventually performs depends heavily on the quality of training examples it receives. The second part of this thesis looks at how one can select high quality examples for function approximation learning tasks. We propose an {em active learning} formulation for function approximation, and show for three specific approximation function classes, that the active example selection strategy learns its target with fewer data samples than random sampling. We then simplify the original active learning formulation, and show how it leads to a tractable example selection paradigm, suitable for use in many object and pattern detection problems.
Extent: en_US 195 p.; 20467529 bytes; 2831164 bytes
Format: application/postscript; application/pdf
Language: en_US
Relation: en_US AITR-1572
Subject: en_US AI; en_US MIT; en_US Artificial Intelligence; en_US Computer Vision; en_US Face Detection; en_US Object Detection; en_US Example-based Learning; en_US Active Learning

Item sets: AI Technical Reports (1964 - 2004)