Example-based learning for view-based human face detection

DMCA

Example-based learning for view-based human face detection (1998)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Kah-kay Sung , Tomaso Poggio

Venue:	IEEE Transactions on Pattern Analysis and Machine Intelligence
Citations:	688 - 23 self

BibTeX

@ARTICLE{Sung98example-basedlearning,
    author = {Kah-kay Sung and Tomaso Poggio},
    title = {Example-based learning for view-based human face detection},
    journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
    year = {1998},
    volume = {20},
    pages = {39--51}
}

OpenURL

Abstract

Abstract—We present an example-based learning approach for locating vertical frontal views of human faces in complex scenes. The technique models the distribution of human face patterns by means of a few view-based “face ” and “nonface ” model clusters. At each image location, a difference feature vector is computed between the local image pattern and the distribution-based model. A trained classifier determines, based on the difference feature vector measurements, whether or not a human face exists at the current image location. We show empirically that the distance metric we adopt for computing difference feature vectors, and the “nonface ” clusters we include in our distribution-based model, are both critical for the success of our system. Index Terms—Face detection, object detection, example-based learning, example selection, pattern recognition, view-based

Keyphrases

example-based learning view-based human face detection difference feature vector distribution-based model view-based face pattern recognition example selection vertical frontal view human face exists local image pattern example-based learning approach nonface model cluster current image location object detection image location index term face detection complex scene technique model difference feature vector measurement human face pattern

DMCA