FEATURE-EXTRACTION FROM FACES USING DEFORMABLE TEMPLATES

被引：781

作者：

YUILLE, AL ^{[1
]}

HALLINAN, PW ^{[1
]}

COHEN, DS ^{[1
]}

机构：

[1] HARVARD UNIV,DIV APPL SCI,CAMBRIDGE,MA 02138

来源：

INTERNATIONAL JOURNAL OF COMPUTER VISION | 1992年 / 8卷 / 02期

关键词：

D O I：

10.1007/BF00127169

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We propose a method for detecting and describing features of faces using deformable templates. The feature of interest, an eye for example, is described by a parameterized template. An energy function is defined which links edges, peaks, and valleys in the image intensity to corresponding properties of the template. The template then interacts dynamically with the image by altering its parameter values to minimize the energy function, thereby deforming itself to find the best fit. The final parameter values can be used as descriptors for the feature. We illustrate this method by showing deformable templates detecting eyes and mouths in real images. We demonstrate their ability for tracking features.

引用

页码：99 / 111

页数：13

共 21 条

[1]

AYAACHE N, 1989, COMP ASS RAD P INT S, P765

[2]

Ballard DH, 1982, COMPUTER VISION

[3]

BENNETT A, 1991, FINDING IMAGE FEATUR

[4]

BRUNELLI R, 1991, 91006 I JRIC SCI TEC