Title :
Facial feature extraction using improved deformable templates
Author :
Zhang Baizhen ; Ruan Qiuqi
Author_Institution :
Inst. of Inf. Sci., Beijing Jiaotong Univ.
Abstract :
This paper proposes a method to extract facial features using improved deformable templates. Our method include two steps, first locating features using rectangle templates designed by myself; then, extracting features using deformable templates. In the first step, we get rectangle block including facial feature from facial images, the rectangle block is our template to locate feature. In the second step extracting feature, we describe the feature of interest by a parameterized template, we design energy function which links with edges, weighted grads, weighted variance and etc, when the energy function gets its minimum, the parameter values can be a good description for facial feature. The experiment results show that this arithmetic can extract facial feature better and more quickly
Keywords :
face recognition; feature extraction; energy function design; facial feature extraction; template deformation; Arithmetic; Data mining; Deformable models; Eyebrows; Facial features; Feature extraction; Frequency estimation; Image segmentation; Iris; Mouth;
Conference_Titel :
Signal Processing, 2006 8th International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-9736-3
Electronic_ISBN :
0-7803-9736-3
DOI :
10.1109/ICOSP.2006.345929