Segmented face image verification for age-invariant face recognition

Face recognition has several problems to improve its performance. In particular, aging causes facial appearance variation so that it is the most difficult problem to handle. We propose a face recognition method that is robust against aging. The proposed method employs segmentation verification of frontal face images that consists of the following three steps. (1) Face image segmentation generates three regional subimages from the input face image. (2) A matching score is calculated using gradient features from a pair consisting of the input image and a registered image for each of the three generated subimages and original (whole face) image. We obtain four matching scores. (3) The verifying classifier evaluates the matching score vector and predicts the a posteriori probability that two matching images belong to the same person. The results of an experimental evaluation with the FGNET datasets clarify the effectiveness of the proposed method for age invariant face recognition.