Indian Journal of Science and Technology
DOI: 10.17485/ijst/2011/v4i10.1
Year: 2011, Volume: 4, Issue: 10, Pages: 1198-1201
Original Article
B. Somayeh Mousavi1 and Alireza Hirad2*
1 Department of Computer, Zahedan Branch, Islamic Azad University, Zahedan, Iran
2 Department of Economic, Khash Branch, Islamic Azad University, Khash, Iran
[email protected] ; [email protected]
The automatic classification of gender has important applications in many commercial domains. Existing systems mainly use features such as words, word classes, and POS (part of speech) n-grams, for classification learning. In this paper, we propose a novel automatic classifier which applies accurately designed fuzzy inference system. This system is 2-inputs, 1-output Sugeno type one, applies facial characteristics as inputs and reveals the probability of being male face or not. Choosing proper threshold value, the decision about gender is made. 87.5% rate of obtained classification proves the efficiency of the proposed method.
Keywords: Gender classification, Fuzzy inference system, Neuro fuzzy, Face database
Subscribe now for latest articles and news.