Face Recognition With Pre-Moment Processing
Journal of ACS Advances in Computer Science · 2014
Face recognition is an active research area because of the importance of itsapplication areas. Face recognition as almost all digital image processing based systemsbegins with elementary processing on the acquired images. The elementary processing isintended to add more to the abilities of consequent processing steps. The elementaryprocessing phase is in most of the cases processing the image by some filters. In this study,an elementary phase of Sobel derivative filters and the derivatives followed by thresholdingby Otsu’s method effect on features extracted by moments for face recognition is explored.The preprocessing step with this setup aims to highlight face local features. The momentsused in the study are Hu and Legendre. Feed forward neural network used as theclassification facility. The results of the study indicated that edges do not form a majordifferential component in the values of moments. Consequently, moments could be aidedwith feature vectors that focus on edges. Also, the study indicated that Legendre is superiorcompared to Hu and the union of Hu and Legendre increases correct recognitionprobability.