Illumination preprocessing is an effective and efficient approach in handling lighting variations for face recognition. Despite much attention to face illumination preprocessing, there is seldom systemic comparative study on existing approaches that presents fascinating insights and conclusions in how to design better illumination preprocessing methods. To fill this vacancy, we provide a comparative study of 12 representative illumination preprocessing methods (HE, LT, GIC, DGD, LoG, SSR, GHP, SQI, LDCT, LTV, LN and TT) from two novel perspectives: (1) localization for holistic approach and (2) integration of large-scale and small-scale feature bands. Experiments on public face databases (YaleBExt, CMU-PIE, CAS-PEAL and FRGC V2.0) with illumination variations suggest that localization for holistic illumination preprocessing methods (HE, GIC, LTV and TT) further improves the performance. Integration of large-scale and small-scale feature bands for reflectance field estimation based illumination preprocessing approaches (SSR, GHP, SQI, LDCT, LTV and TT) is also found helpful for illumination-insensitive face recognition.

Face recognition from Single Sample per Person (SSPP) is extremely challenging because only one sample is available for each person. While many discriminant analysis methods, such as Fisherfaces and its numerous variants, have achieved great success in face recognition, these methods cannot work in this scenario, because more than one sample per person are needed to calculate the within-class scatter matrix. To address this problem, we propose Adaptive Discriminant Analysis (ADA) in which the within-class scatter matrix of each enrolled subject is inferred using his/her single sample, by leveraging a generic set with multiple samples per person. Our method is motivated from the assumption that subjects who look alike to each other generally share similar within-class variations. In ADA, a limited number of neighbors for each single sample are first determined from the generic set by using kNN regression or Lasso regression. Then, the within-class scatter matrix of this single sample is inferred as the weighted average of the within-class scatter matrices of these neighbors based on the arithmetic mean or Riemannian mean. Finally, the optimal ADA projection directions can be computed analytically by using the inferred within-class scatter matrices and the actual between-class scatter matrix. The proposed method is evaluated on three databases including FERET database, FRGC database and a large real-world passport-like face database. The extensive results demonstrate the effectiveness of our ADA when compared with the existing solutions to the SSPP problem.

This paper proposes a novel method to estimate the head yaw rotation using the symmetry of regions. We argue that the symmetry of 2D regions located in the same horizontal row is more intrinsically relevant to the yaw rotation of head than the symmetry of 1D signals, while at the same time insensitive to the identity of the face. Specifically, the proposed method relies on the effective combination of Gabor filters and covariance descriptors. We first extract the multi-scale and multi-orientation Gabor representations of the input face image, and then use covariance descriptors to compute the symmetry between two regions in terms of Gabor representations under the same scale and orientation. Since the covariance matrix can alleviate the influence caused by rotations and illumination, the proposed method is robust to such variations. In addition, the proposed method is further improved by combining it with a metric learning method named aa KISS MEtric learning (KISSME). Experiments on four challenging databases demonstrated that the proposed method outperformed the state of the art.

Hair segmentation is challenging due to the diverse appearance, irregular region boundary and the influence of complex background. To deal with this problem, we propose a novel data-driven method, named Isomorphic Manifold Inference (IMI). The IMI method assumes the coarse probability map and the binary segmentation map as a couple of isomorphic manifolds and tries to learn hair specific priors from manually labeled training images. For an input image, firstly, the method calculates a coarse probability map. Then it exploits regression techniques to obtain the relationship between the coarse probability map of the test image and those of training images. Finally, this relationship, i.e., a coefficient set, is transferred to the binary segmentation maps and a soft segmentation of the test image will be achieved by a linear combination of those binary maps. Further, we employ this soft segmentation as a shape cue and integrate it with color and texture cues into a unified segmentation framework. A better segmentation is achieved by the Graph Cuts optimization. Extensive experiments are conducted to validate effectiveness of the IMI method, compare contributions of different cues and investigate the generalization of IMI method. The results strongly encourage our method.

Due to the misalignment of image features, the performance of many conventional face recognition methods degrades considerably in across pose scenario. To address this problem, many image matching-based methods are proposed to estimate semantic correspondence between faces in different poses. In this paper, we aim to solve two critical problems in previous image matching-based correspondence learning methods: 1) fail to fully exploit face specific structure information in correspondence estimation and 2) fail to learn personalized correspondence for each probe image. To this end, we first build a model, termed as morphable displacement field (MDF), to encode face specific structure information of semantic correspondence from a set of real samples of correspondences calculated from 3D face models. Then, we propose a maximal likelihood correspondence estimation (MLCE) method to learn personalized correspondence based on maximal likelihood frontal face assumption. After obtaining the semantic correspondence encoded in the learned displacement, we can synthesize virtual frontal images of the profile faces for subsequent recognition. Using linear discriminant analysis method with pixel-intensity features, state-of-the-art performance is achieved on three multipose benchmarks, i.e., CMU-PIE, FERET, and MultiPIE databases. Owe to the rational MDF regularization and the usage of novel maximal likelihood objective, the proposed MLCE method can reliably learn correspondence between faces in different poses even in complex wild environment, i.e., labeled face in the wild database.