Probabilistic Modeling of Local Appearance and Spatial Relationships for Object Recognition - Robotics Institute Carnegie Mellon University

Probabilistic Modeling of Local Appearance and Spatial Relationships for Object Recognition

Conference Paper, Proceedings of (CVPR) Computer Vision and Pattern Recognition, pp. 45 - 51, June, 1998

Abstract

In this paper, we describe an algorithm for object recognition that explicitly models and estimates the posterior probability function, P(object|image). We have chosen a functional form of the posterior probability function that captures the joint statistics of local appearance and position on the object as well as the statistics of local appearance in the visual world at large. We use a discrete representation of local appearance consisting of approximately 1,000,000 patterns. We compute an estimate of P(object|image) in closed form by counting the frequency of occurrence of these patterns over various sets of training images. We have used this method for detecting human faces from frontal and profile views. The algorithm for frontal views has shown a detection rate of 93.0% with 88 false alarms on a set of 125 images containing 483 faces combining the MIT test set of Sung and Poggio with the CMU test sets of Rowley, Baluja, and Kanade. The algorithm for detection of profile views has also demonstrated promising results

BibTeX

@conference{Schneiderman-1998-14711,
author = {Henry Schneiderman and Takeo Kanade},
title = {Probabilistic Modeling of Local Appearance and Spatial Relationships for Object Recognition},
booktitle = {Proceedings of (CVPR) Computer Vision and Pattern Recognition},
year = {1998},
month = {June},
pages = {45 - 51},
keywords = {computer vision, machine vision, object recognition, pattern recognition, pattern classification, face detection, object detection},
}