Title :
Gender Classification Using Interlaced Derivative Patterns
Author :
Shobeirinejad, Ameneh ; Gao, Yongsheng
Author_Institution :
Sch. of Eng., Griffith Univ., Brisbane, QLD, Australia
Abstract :
Automated gender recognition has become an interesting and challenging research problem in recent years with its potential applications in security industry and human-computer interaction systems. In this paper we present a novel feature representation, namely Interlaced Derivative Patterns (IDP), which is a derivative-based technique to extract discriminative facial features for gender classification. The proposed technique operates on a neighborhood around a pixel and concatenates the extracted regional feature distributions to form a feature vector. The experimental results demonstrate the effectiveness of the IDP method for gender classification, showing that the proposed approach achieves 29.6% relative error reduction compared to Local Binary Patterns (LBP), while it performs over four times faster than Local Derivative Patterns (LDP).
Keywords :
face recognition; human computer interaction; image classification; IDP; LBP; LDP; gender classification; gender recognition; human computer interaction; interlaced derivative patterns; local binary patterns; local derivative patterns; relative error reduction; Error analysis; Face; Face recognition; Feature extraction; Histograms; Pixel; Interlaced Derivative Pattern; gender recognition; local derivative pattern; performance evaluation;
Conference_Titel :
Pattern Recognition (ICPR), 2010 20th International Conference on
Conference_Location :
Istanbul
Print_ISBN :
978-1-4244-7542-1
DOI :
10.1109/ICPR.2010.1118