Skip to main navigation Skip to search Skip to main content

Eye extraction using spatial fuzzy clustering method

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

Abstract

Facial features extraction and tracking are crucial steps for many multimedia communication applications such as automated visual interpretation, human face recognition, and development of high quality model-based coding (e.g. MPEG-4) systems. Among different facial features, eyes and lip play an important role in either recognition process or teleconferencing applications. However, automatic human facial features detection is a difficult task due to different scale, rotation and translation of the features.
This paper describes a computational approach for locating the eye position from a given eye window. The proposed algorithm will extract the eye in two stages. The iris will first be extracted using a region-based energy minimization approach from the membership map generated by the spatial fuzzy clustering technique. In second two, control points will be detected to locate the sclera and two parabolas will be used to model the upper and lower eyelids. Satisfactory results have been achieved with the proposed method.
© 2002 IEEE
Original languageEnglish
Title of host publication2002 IEEE Region 10 Conference on Computer, Communications, Control and Power Engineering
Subtitle of host publicationIEEE TENCOM'02
EditorsBaozong YUAN , Xiaofang TANG
PublisherIEEE
Pages515-518
Volume1
ISBN (Print)0-7803-7490-8
DOIs
Publication statusPublished - Oct 2002
Event2002 IEEE Region 10 Conference on Computers, Communications, Control and Power Engineering (TENCOM '02) - Beijing, China
Duration: 28 Oct 200231 Oct 2002

Conference

Conference2002 IEEE Region 10 Conference on Computers, Communications, Control and Power Engineering (TENCOM '02)
PlaceChina
CityBeijing
Period28/10/0231/10/02

Fingerprint

Dive into the research topics of 'Eye extraction using spatial fuzzy clustering method'. Together they form a unique fingerprint.

Cite this