Acquiring linear subspaces for face recognition under variable lighting

Abstract

Previous work has demonstrated that the image variation of many objects (human faces in particular) under variable lighting can be effectively modeled by low dimensional linear spaces, even when there are multiple light sources and shadowing. Basis images spanning this space are usually obtained in one of three ways: A large set of images of the object under different lighting conditions is acquired, and principal component analysis (PCA) is used to estimate a subspace. Alternatively, synthetic images are rendered from a 3D model (perhaps reconstructed from images) under point sources, and again PCA is used to estimate a subspace.Finally, images rendered from a 3D model under diffuse lighting based on spherical harmonics are directly used as basis images.In this paper, we show how to arrange physical lighting so that the acquired images of each object can be directly used as the basis vectors of a low-dimensional linear space, and that this subspace is close to those acquired by the other methods. More specifically, there exist configurations of k point light source directions, with k typically ranging from 5 to 9, such that by taking k images of an object under these single sources, the resulting subspace is an effective representation for recognition under a wide range of lighting conditions. Since the subspace is generated directly from real images, potentially complex and/or brittle intermediate steps such as 3D reconstruction can be completely avoided; nor is it necessary to acquire large numbers of training images or to physically construct complex diffuse (harmonic) light fields. We validate the use of subspaces constructed in this fashion within the context of face recognition.

A Correlational Neural Network for Gender Classification

“…In order to demonstrate the validity of the proposed CorNN for face gender classification, we compare it with a CNN with the same structure on nine human face databases: ORL, Georgia Tech, FERET [15], Extended Yale B (EYB) [16], AR [17], Faces94, LFW [18], MORPH and CelebFaces+ [19]. The examples of face images from these databases are shown in Fig.…”

“…VF HF   w w (16) we can get a CorNN that always produce the same output as the CNN for the same input.…”

Recovering 3D facial shape via coupled 2D/3D space learning

“…We use the same coupled statistical model obtained by training the 100 heads in the USF datasets. The images for testing are selected from the Extended Yale Face database B [2,18] and CMU PIE database [19]. Images in the YaleB database are captured under different illumination conditions with pose variations.…”

Generic and attribute-specific deep representations for maritime vessels

“…Especially, face recognition has been studied extensively, and state-of-the-art methods [31,32], which perform effectively on the benchmark datasets [33][34][35], have been proposed. Since encouraging performance results are obtained with recent methods, another application performed, utilizing MARVEL, is vessel recognition task, where the ultimate goal is to perceive a vessel's identity by its visual appearance.…”