Viewpoint Invariant Face Recognition using Independent Component Analysis and Attractor Networks
نویسندگان
چکیده
We have explored two approaches to recogmzmg faces across changes in pose. First, we developed a representation of face images based on independent component analysis (ICA) and compared it to a principal component analysis (PCA) representation for face recognition. The ICA basis vectors for this data set were more spatially local than the PCA basis vectors and the ICA representation had greater invariance to changes in pose. Second, we present a model for the development of viewpoint invariant responses to faces from visual experience in a biological system. The temporal continuity of natural visual experience was incorporated into an attractor network model by Hebbian learning following a lowpass temporal filter on unit activities. When combined with the temporal filter, a basic Hebbian update rule became a generalization of Griniasty et al. (1993), which associates temporally proximal input patterns into basins of attraction. The system acquired representations of faces that were largely independent of pose. 1 Independent component representations of faces Important advances in face recognition have employed forms of principal component analysis, which considers only second-order moments of the input (Cottrell & Metcalfe, 1991; Turk & Pentland 1991). Independent component analysis (ICA) is a generalization of principal component analysis (PCA), which decorrelates the higher-order moments of the input (Comon, 1994). In a task such as face recognition, much of the important information is contained in the high-order statistics of the images. A representational basis in which the high-order statistics are decorrelated may be more powerful for face recognition than one in which only the second order statistics are decorrelated, as in PCA representations. We compared an ICAbased representation to a PCA-based representation for recognizing faces across changes in pose. 818 M. S. Bartlett and T. J. Sejnowski -30" -IS" 0" IS" 30" Figure 1: Examples from image set (Beymer, 1994). The image set contained 200 images of faces, consisting of 40 subjects at each of five poses (Figure 1). The images were converted to vectors and comprised the rows of a 200 x 3600 data matrix, X. We consider the face images in X to be a linear mixture of an unknown set of statistically independent source images S, where A is an unknown mixing matrix (Figure 2). The sources are recovered by a matrix of learned filters, W, which produce statistically independent outputs, U.
منابع مشابه
oint invariant face recognition using endent component analysis and at tractor networks
We have explored two approaches to recognizing faces across changes in pose. First, we developed a representation of face images based on independent component analysis (ICA) and compared it to a principal component analysis (PCA) representation for face recognition. The ICA basis vectors for this data set were more spatially local than the PCA basis vectors and the ICA representation had great...
متن کاملLearning Viewpoint Invariant Representations of Faces in anAttractor
In natural visual experience, diierent views of an object tend to appear in close temporal proximity as an animal manipulates the object or navigates around it. We investigated the ability of an attractor network to acquire view invariant visual representations by associating rst neighbors in a pattern sequence. The pattern sequence contains successive views of faces of ten individuals as they ...
متن کاملViewpoint-Invariant Face Recognition Based on View-Based Representation
In this paper, we suggest a viewpoint-invariant face recognition model based on view-based representation. The suggested model has four stages: view-based representation, viewpoint classification, frontal face estimation and face recognition. For view-based representation, we obtained the feature space by using independent subspace analysis, the bases of which are grouped like the neurons in th...
متن کاملSelf-Organization of Viewpoint Dependent Face Representation by the Self-Supervised Learning and Viewpoint Independent Face Recognition by the Mixture of Classifiers
This paper proposes a viewpoint invariant face recognition method in which several viewpoint dependent classifiers are combined by a gating network. The gating network is designed as autoencoder with competitive hidden units. The viewpoint dependent representations of faces can be obtained by this autoencoder from many faces with different views. Multinomial logit model is used for the viewpoin...
متن کامل3 D Face Recognition without Facial Surface Reconstruction
geometric invariant signatures, has been proposed. The key idea of the algorithm is a representation of the facial surface, invariant to isometric deformations, such as those resulting from facial expressions. One of the crucial stages in the construction of the geometric invariants is the measurement of geodesic distances on triangulated surfaces, carried out by fast marching on triangulated d...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1996