Facial feature extraction is an important step in automated visual interpretation and human face recognition. Deformable template is a method used in extracting the eye boundaries. However, a weakness of the deformable template is the lenghty processing time. In this paper, the head boundary is first located in a head-and-shoulders image. The approximate positions of the eyes are estimated by means of average anthropometric measures. Corners, the salient features of the eyes, are detected and used to set the initial parameters of the eye templates. This scheme can accurately position the templates in relation to the eye images and greatly reduce the processing time for the templates. In order to illustrate this performance, a simplified eye template model is used in the experiment.
|Number of pages||5|
|Journal||National Conference Publication - Institution of Engineers, Australia|
|Issue number||94 /9|
|Publication status||Published - 1 Dec 1994|
|Event||Proceedings of the International Symposium on Information Theory & Its Applications 1994. Part 1 (of 2) - Sydney, Australia|
Duration: 20 Nov 1994 → 24 Nov 1994
ASJC Scopus subject areas