PROJECT TITLE :

Gender classification based on fuzzy clustering and principal component analysis

ABSTRACT:

Gender classification is one in all the foremost difficult problems in computer vision. Facial gender detection of neonates and youngsters is additionally referred to as a highly demanding issue for human observers. This study proposes a unique gender classification method using frontal facial images of folks. The proposed approach employs principal part analysis (PCA) and fuzzy clustering technique, respectively, for feature extraction and classification steps. In different words, PCA is applied to extract the foremost applicable features from pictures furthermore reducing the dimensionality of information. The extracted options are then used to assign the new pictures to appropriate classes - male or feminine - based on fuzzy clustering. The computational time and accuracy of the proposed methodology are examined along and also the prominence of the proposed approach compared to most of the other well-known competing strategies is proved, especially for younger faces. Experimental results indicate the considerable classification accuracies which are acquired for FG-Internet, Stanford and FERET databases. Meanwhile, since the proposed algorithm is relatively straightforward, its computational time is affordable and typically but the other state-of-the-art gender classification strategies.