Tensor-Based AAM with Continuous Variation Estimation: Application to Variation-Robust Face Recognition

Abstract

The Active appearance model (AAM) is a well-known model that can represent a nonrigid object effectively. However, because it uses a fixed model of shape and appearance, the fitting result is often unsatisfactory when an input image deviates from the training images. To obtain more robust AAM fitting, we propose a tensor-based AAM that can handle a variety of subjects, poses, expressions, and illuminations in the tensor algebra framework. It consists of an image tensor and a model tensor. The image tensor is used to estimate image variations such as pose, expression, and illumination of the input image. Here, we introduce two different variation estimation approaches: discrete and continuous variation estimation. Then, the model tensor generates a variation-specific AAM from a tensor representation, using the estimation results. This process ensures more accurate fitting results. To validate the usefulness of the tensor-based AAM, we performed variation-robust face recognition using the tensor-based AAM fitting results. To do this, we propose indirect AAM feature transformation. Experimental results show that the tensor-based AAM with continuous variation estimation outperforms that with discrete variation estimation and conventional AAM in terms of the average fitting error and the face recognition rate.