An Extended Local Binary Pattern for Gender Classification

The face is one of the most important biometric features of humans, conveying race, identity, age, gender and facial expression information, among which gender plays a significant role in social interactions. An automatic gender recognition system has many applications in computer-human interaction, psychology, security, demographic and business issues. In this work, we designed and implemented an efficient gender recognition system with high classification accuracy. In this regard, we proposed a novel local binary descriptor capable of extracting more informative and discriminative local features for the purpose of gender classification. We have evaluated our approach on the standard FERET and CAS-PEAL databases and our experiments show that the proposed approach offers superior results compared to techniques using state-of-the-art descriptors such as LBP, LDP and HoG. Our results demonstrate the effectiveness and robustness of the proposed system with 98.33% classification accuracy.

Level thesis:degree_level

Master's Degree

Year dc:date.issued

2013

Author dc:creator

• Roayaei Ardakany, Abbas

Advisor dc:contributor.advisor

• Nicolescu, Mircea

Committee members dc:contributor.committeemember

• Nicolescu, Monica
• Shen, Shantao

• Gender Recognition
• Genetic Algorithms
• Image Processing
• Local Binary Patterns

Statement dc:rights

• In Copyright(All Rights Reserved)

Handle dc:identifier.uri

http://hdl.handle.net/11714/3241

OAI identifier oai:identifier

oai:scholarwolf.unr.edu:11714/3241