Using face recognition for authentication by anthro pometric model

Dissertant

Abd al-Husayn, Farah Tawfiq

University

University of Technology

Faculty

-

Department

Computer Sciences Department

University Country

Iraq

Degree

Master

Degree Date

2008

English Abstract

In many researches biometric recognition algorithms has been implemented with different physical features like finger print, palm print, iris, ear,......and face and in all cases the results are used for authentication. In this research human face biometric type is used to build an authorized computer system based on anthropometric face model to facilitate measuring the distances between face features, the system composed of many stages to detect human face and recognizing it from the image by using binary mask to extract the face region only from the original image without any noise.

The extracted face image is masked with elliptical mask then face contrast is increased by using Sobel edge detection to distinguish skin and nonskin pixels (features) which are convened to black pixels to facilitate feature extraction process.

These features isolated into separated .sub images and the lengths and distances among them which represents authenticated persons information. In authentication stage all the above stages are repeated to compare the results with stored authenticated person's inflation in the database to determine whether the person in the image is authenticated or not, he or she is authenticated if a percentage of similarity equal to or greater than 78% is achieved.

Main Subjects

Engineering & Technology Sciences (Multidisciplinary)

Topics

• Data processing

• APA
• MLA
• AMA

Language

English

Data Type

Arab Theses

Record ID

BIM-305083