Font Size: a A A

An Identification System Based On Facial Biometrics And Eye Localization

Posted on:2011-08-29Degree:MasterType:Thesis
Country:ChinaCandidate:T WangFull Text:PDF
GTID:2178360305464732Subject:Computer application technology
Abstract/Summary:PDF Full Text Request
A proposal for a person authentication system, which localizes facial landmarks and extracts biometrical features for face authentication, is presented in this thesis. An efficient algorithm for eye localization and biometrical feature extraction and person identification is developed by using Gabor filters. Based on a reasonably good face tracking algorithm, this thesis focuses on two relative aspects for implementing this person authentication system. In the eye localization part, we build artificial average eye models for eye location. In the person identification part, we construct databases of biometrical features around the eye area of clients and, for authentication, Schwartz inequality and the sum square error (SSE) are used. After locating the eye centers of face image of a client, we then extract biometrical features around the eye areas and store the feature information, which best represents this specific client, into our database along with feature information from other clients. When information from an unidentified person comes into the system, we compare that information with the data stored in our client database and give identity of this person or, deny his or her access.
Keywords/Search Tags:Artificial eye model, Gabor filters, Biometrical feature, Eye localization, Client authentication
PDF Full Text Request
Related items