Face Recognition and Facial Attribute Analysis from Unconstrained Visual Data

Abstract

Analyzing human faces from visual data has been one of the most active research areas in the computer vision community. However, it is a very challenging problem in unconstrained environments due to variations in pose, illumination, expression, occlusion and blur between training and testing images. The task becomes even more difficult when only a limited number of images per subject is available for modeling these variations. In this dissertation, different techniques for performing classification of human faces as well as other facial attributes such as expression, age, gender, and head pose in uncontrolled settings are investigated. In the first part of the dissertation, a method for reconstructing the virtual frontal view from a given non-frontal face image using Markov Random Fields (MRFs) and an efficient variant of the Belief Propagation (BP) algorithm is introduced. In the proposed approach, the input face image is divided into a grid of overlapping patches and a globally optimal set of local warps is estimated to synthesize the patches at the frontal view. A set of possible warps for each patch is obtained by aligning it with images from a training database of frontal faces. The alignments are performed efficiently in the Fourier domain using an extension of the Lucas-Kanade (LK) algorithm that can handle illumination variations. The problem of finding the optimal warps is then formulated as a discrete labeling problem using an MRF. The reconstructed frontal face image can then be used with any face recognition technique. The two main advantages of our method are that it does not require manually selected facial landmarks as well as no head pose estimation is needed. In the second part, the task of face recognition in unconstrained settings is formulated as a domain adaptation problem. The domain shift is accounted for by deriving a latent subspace or domain, which jointly characterizes the multifactor variations using appropriate image formation models for each factor. The latent domain is defined as a product of Grassmann manifolds based on the underlying geometry of the tensor space, and recognition is performed across domain shift using statistics consistent with the tensor geometry. More specifically, given a face image from the source or target domain, multiple images of that subject are first synthesized under different illuminations, blur conditions, and 2D perturbations to form a tensor representation of the face. The orthogonal matrices obtained from the decomposition of this tensor, where each matrix corresponds to a factor variation, are used to characterize the subject as a point on a product of Grassmann manifolds. For cases with only one image per subject in the source domain, the identity of target domain faces is estimated using the geodesic distance on product manifolds. When multiple images per subject are available, an extension of kernel discriminant analysis is developed using a novel kernel based on the projection metric on product spaces. Furthermore, a probabilistic approach to the problem of classifying image sets on product manifolds is introduced. Understanding attributes such as expression, age class, and gender from face images has many applications in multimedia processing including content personalization, human-computer interaction, and facial identification. To achieve good performance in these tasks, it is important to be able to extract pertinent visual structures from the input data. In the third part of the dissertation, a fully automatic approach for performing classification of facial attributes based on hierarchical feature learning using sparse coding is presented. The proposed approach is generative in the sense that it does not use label information in the process of feature learning. As a result, the same feature representation can be applied for different tasks such as expression, age, and gender classification. Final classification is performed by linear SVM trained with the corresponding labels for each task. The last part of the dissertation presents an automatic algorithm for determining the head pose from a given face image. The face image is divided into a regular grid and represented by dense SIFT descriptors extracted from the grid points. Random Projection (RP) is then applied to reduce the dimension of the concatenated SIFT descriptor vector. Classification and regression using Support Vector Machine (SVM) are combined in order to obtain an accurate estimate of the head pose. The advantage of the proposed approach is that it does not require facial landmarks such as the eye and mouth corners, the nose tip to be extracted from the input face image as in many other methods.