Face recognition at-a-distance using texture, Sparse-Stereo, and Dense-Stereo

This paper proposes a framework for face recognition at a distance based on texture, Sparse-Stereo, and Dense-stereo reconstruction. We develop a 3D acquisition system that consists of two CCD stereo cameras mounted on pan-tilt units with adjustable baseline. In this paper we introduce our stereo-based indoor/outdoor environment and different ranges human faces database. Also, we propose a front-to-end system of 3D face reconstruction and recognition. We first detect the facial region and extract its landmark points, which are used to initialize the face alignment algorithm. The fitted mesh vertices, generated from the face alignment process, provide point correspondences between the left and right images of a stereo pair; stereo-based reconstruction is then used to infer the 3D information of the mesh vertices. Also the dense 3D is reconstructed for the cropped stereo pair based on graph cut approach. We perform experiments regarding the use of different features extracted from these vertices for face recognition. The cumulative rank curves (CMC), which are generated using the proposed framework, confirm the feasibility of the proposed work for long distance recognition of human faces.

1. INTRODUCTION

Face recognition is one of the biometric methods identifying individuals by the features of face. Automatic face recognition has evolved from small scale research systems to a wide range of commercial products. Therefore, computer vision methodology for automatic face recognition has become an attractive research area in the past three decades (for more details see [1],[2]). In the beginning, most efforts were directed towards 2D facial recognition. However, there are challenging issues, when using 2D images for face recognition. Automatic face recognition is a challenging task that has been an attractive research area in the past three decades (for more details see [25] and references therein). At the outset, most efforts were directed towards 2D facial recognition which utilizes the projection of the 3D human face onto the 2D image plane acquired by digital cameras. The face recognition problem is then formulated as follows: given a still image, identify or verify one or more persons in the scene using a stored database of face images. The main theme of the solutions provided by different researchers involves detecting one or more faces from the given image, followed by facial feature extraction which can be used for recognition. Challenges involving 2D face recognition are well-documented in the literature. Intra-subject variations such as illumination, expression, pose, makeup, and aging can severely affect a face recognition system. To address pose and illumination, researchers recently are focusing on 3D face recognition [26]. 3D face geometry can either be acquired using 3D sensing devices such as laser scanners [27]–[29]or reconstructed from one or more images [13],[30] [31]. Although 3D sensing devices have been proven to be effective in 3D face recognition [32], their high cost, limited availability and controlled environment settings have created the need for methods that extract 3D information from acquired 2D face images. Recently, there has been interest in face recognition at-a-distance. Yao, et al. [33] created a face video database, acquired from long distances, high magnifications, and both indoor and outdoor under uncontrolled surveillance conditions. Medioni, et al. [34] presented an approach to identify noncooperative individuals at a distance by inferring 3D shape from a sequence of images.