Texture Modelling for Age Invariant Face Recognition

This Research study proposes a novel method for face recognition based on Texture boundaries or edges by using Canny and Sobel Edge detection that make use of global and personalized models. The system is aimed to recognize faces and identify their similarity across ages. A Personalized model covers the individual aging patterns while a Global model captures general aging patterns in the population. We introduced a de-aging factor that de-ages each individual in the image gallery. We used the k nearest neighbor approach for building a personalized model. Regression analysis was applied to build the models. During the test phase, we built a similarity matrix and determined the rank 1 identification by using a Leave One Person Out strategy. We used FG-Net database for validating our technique and achieved 62 percent Rank 1 identification rate. KeywordsEdges; K Nearest Neighbor; Personalised Model; Regression;