DMCA
Face recognition: features versus templates (1993)
| Venue: | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE |
| Citations: | 745 - 23 self |
BibTeX
@ARTICLE{Brunelli93facerecognition:,
author = {Roberto Brunelli and Tomaso Poggio},
title = {Face recognition: features versus templates},
journal = {IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE},
year = {1993},
volume = {15},
number = {10},
pages = {1042--1052}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Over the last 20 years, several different techniques have been proposed for computer recognition of human faces. The purpose of this paper is to compare two simple but general strategies on a common database (frontal images of faces of 47 people: 26 males and 21 females, four images per person). We have developed and implemented two new algorithms; the first one is based on the computation of a set of geometrical features, such as nose width and length, mouth position, and chin shape, and the second one is based on almost-grey-level template matching. The results obtained on the testing sets (about 90 % correct recognition using geometrical features and perfect recognition using template matching) favor our implementation of the template-matching approach.
Keyphrases
face recognition template matching geometrical feature mouth position common database correct recognition frontal image chin shape several different technique first one new algorithm second one perfect recognition computer recognition almost-grey-level template matching template-matching approach nose width index terms-classification karhunen-loeve expansion general strategy
