Probabilistic modeling of local appearance and spatial relationships for object recognition

In this paper, we describe an algorithm for object recognition that explicitly models and estimated 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 o...

Full description

Saved in:
Bibliographic Details
Main Authors: Schneiderman, H., Kanade, T.
Format: Conference Proceeding
Language:English
Subjects:
Aggregates
Color
Face detection
Layout
Object detection
Object recognition
Probability
Random variables
Robots
Statistics
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we describe an algorithm for object recognition that explicitly models and estimated 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 10/sup 6/ 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.
ISSN:1063-6919
DOI:10.1109/CVPR.1998.698586