Özet:

Age estimation from facial images and facial age progression is crucial in security systems design. In this study local binary pattern (LBP) histograms are used to classify the age from facial images. The LBP operator is an effective texture descriptor and used in the fields of texture classification, segmentation, face detection, face recognition and gender estimation. The local binary patterns (LBP) are fundamental properties of local image texture and the occurrence histogram of these patterns is an effective texture feature for face description. In the study the faces are divided into small regions from which the LBP histograms are extracted and concatenated into a feature vector to be used as an efficient face descriptor. For every new face presented to the system, spatial LBP histograms are produced and used to classify the image into one of the age classes. In the classification phase we use minimum distance, nearest neighbor and k-nearest neighbor classifiers. The distances between the samples are calculated with Euclidean, normalized Euclidean, chi-square and weighted chi-square distances. The experimental results have shown that system performance is 89% for age estimation.

Anahtar Kelimeler: