Ngoc-Son Vu

Enhanced Patterns of Oriented Edge Magnitudes for Face Recognition and Image Matching

A good feature descriptor is desired to be discriminative, robust, and computationally inexpensive in both terms of time and storage requirement. In the domain of face recognition, these properties allow the system to quickly deliver high recognition results to the end user. Motivated by the recent feature descriptor called Patterns of Oriented Edge Magnitudes (POEM), which balances the three concerns, this paper aims at enhancing its performance with respect to all these criteria. To this end, we first optimize the parameters of POEM and then apply the whitened principal-component-analysis dimensionality reduction technique to get a more compact, robust, and discriminative descriptor. For face recognition, the efficiency of our algorithm is proved by strong results obtained on both constrained (Face Recognition Technology, FERET) and unconstrained (Labeled Faces in the Wild, LFW) data sets in addition with the low complexity. Impressively, our algorithm is about 30 times faster than those based on Gabor filters. Furthermore, by proposing an additional technique that makes our descriptor robust to rotation, we validate its efficiency for the task of image matching.

Face recognition with patterns of oriented edge magnitudes

This paper addresses the question of computationally inexpensive yet discriminative and robust feature sets for real-world face recognition. The proposed descriptor named Patterns of Oriented Edge Magnitudes (POEM) has desirable properties: POEM (1) is an oriented, spatial multi-resolution descriptor capturing rich information about the original image; (2) is a multi-scale self-similarity based structure that results in robustness to exterior variations; and (3) is of low complexity and is therefore practical for real-time applications. Briefly speaking, for every pixel, the POEM feature is built by applying a self-similarity based structure on oriented magnitudes, calculated by accumulating a local histogram of gradient orientations over all pixels of image cells, centered on the considered pixel. The robustness and discriminative power of the POEM descriptor is evaluated for face recognition on both constrained (FERET) and unconstrained (LFW) datasets. Experimental results show that our algorithm achieves better performance than the state-of-the-art representations. More impressively, the computational cost of extracting the POEM descriptor is so low that it runs around 20 times faster than just the first step of the methods based upon Gabor filters. Moreover, its data storage requirements are 13 and 27 times smaller than those of the LGBP (Local Gabor Binary Patterns) and HGPP (Histogram of Gabor Phase Patterns) descriptors respectively.

Illumination-robust face recognition using retina modeling

Illumination variations that might occur on face images degrade the performance of face recognition systems. In this paper, we propose a novel method of illumination normalization based on retina modeling by combining two adaptive nonlinear functions and a Difference of Gaussians filter. The proposed algorithm is evaluated on the Yale B database and the Feret illumination database using two face recognition methods: PCA based and Local Binary Pattern based (LBP). Experimental results show that the proposed method achieves very high recognition rates even for the most challenging illumination conditions. Our algorithm has also a low computational complexity.

Face recognition using the POEM descriptor

Real-world face recognition systems require careful balancing of three concerns: computational cost, robustness, and discriminative power. In this paper we describe a new descriptor, POEM (patterns of oriented edge magnitudes), by applying a self-similarity based structure on oriented magnitudes and prove that it addresses all three criteria. Experimental results on the FERET database show that POEM outperforms other descriptors when used with nearest neighbour classifiers. With the LFW database by combining POEM with GMMs and with multi-kernel SVMs, we achieve comparable results to the state of the art. Impressively, POEM is around 20 times faster than Gabor-based methods.

Mining patterns of orientations and magnitudes for face recognition

Good face recognition system is one which quickly delivers high accurate results to the end user. For this purpose, face representation must be robust, discriminative and also of low computational cost in both terms of time and space. Inspired by recently proposed feature set so-called POEM (Patterns of Oriented Edge Magnitudes) which considers the relationships between edge distributions of different image patches and is argued balancing well the three concerns, this work proposes to further exploit patterns of both orientations and magnitudes for building more efficient algorithm. We first present novel features called Patterns of Dominant Orientations (PDO) which consider the relationships between “dominant” orientations of local image regions at different scales. We also propose to apply the whitened PCA technique upon both the POEM and PDO based representations to get more compact and discriminative face descriptors. We then show that the two methods have complementary strength and that by combining the two descriptors, one obtains stronger results than either of them considered separately. By experiments carried out on several common benchmarks, including both frontal and non-frontal FERET as well as the AR datasets, we prove that our approach is more efficient than contemporary ones.

Statistical binary patterns for rotational invariant texture classification

A new texture representation framework called statistical binary patterns (SBPs) is presented. It consists in applying rotation invariant local binary pattern operators ( LBP riu 2 ) to a series of moment images, defined by local statistics uniformly computed using a given spatial support. It can be seen as a generalisation of the commonly used complementation approach (CLBP), since it extends the local description not only to local contrast information, but also to higher order local variations. In short, SBPs aim at expanding LBP self-similarity operator from the local grey level to the regional distribution level. Thanks to a richer local description, the SBPs have better discrimination power than other LBP variants. Furthermore, thanks to the regularisation effect of the statistical moments, the SBP descriptors show better noise robustness than classical CLBPs. The interest of the approach is validated through a large experimental study performed on five texture databases: KTH-TIPS, KTH-TIPS 2b, CUReT, UIUC and DTD. The results show that, for the four first datasets, the SBPs are comparable or outperform the recent state-of-the-art methods, even using small support for the LBP operator, and using limited size spatial support for the computation of the local statistics. HighlightsWe extend the binary patterns from the pixel level to the local distribution level.We exploit moment images calculated from spatial support of the statistics.Statistical moments clearly improve the expressiveness and robustness of descriptor.

Patch-Based Similarity HMMs for Face Recognition with a Single Reference Image

In this paper we present a new architecture for face recognition with a single reference image, which completely separates the training process from the recognition process. In the training stage, by using a database containing various individuals, the spatial relations between face components are represented by two Hidden Markov Models (HMMs), one modeling within-subject similarities, and the other modeling inter-subject differences. This allows us during the recognition stage to take a pair of face images, neither of which has been seen before, and to determine whether or not they come from the same individual. Whilst other face-recognition HMMs use Maximum Likelihood criterion, we test our approach using both Maximum Likelihood and Maximum a Posteriori (MAP) criterion, and find that MAP provides better results. Importantly, the training database can be entirely separated from the gallery and test images: this means that adding new individuals to the system can be done without re-training. We present results based upon models trained on the FERET training dataset, and demonstrate that these give satisfactory recognition rates on both the FERET database itself and more impressively the unseen AR database. When compared to other HMM based face recognition techniques, our algorithm is of much lower complexity due to the small size of our observation sequence.

Efficient statistical face recognition across pose using Local Binary Patterns and Gabor wavelets

The performance of face recognition systems can be dramatically degraded when the pose of the probe face is different from the gallery face. In this paper, we present a pose robust face recognition model, centered on modeling how face patches change in appearance as the viewpoint varies. We present a novel model based on two robust local appearance descriptors, Gabor wavelets and Local Binary Patterns (LBP). These two descriptors have been widely exploited for face recognition and different strategies for combining them have been investigated. However, to the best of our knowledge, all existing combination methods are designed for frontal face recognition. We introduce a local statistical framework for face recognition across pose variations, given only one frontal reference image. The method is evaluated on the Feret pose dataset and experimental results show that we achieve very high recognition rates over the wide range of pose variations presented in this challenging dataset.

How far we can improve micro features based face recognition systems

This paper presents improvements for face recognition methods that use LBP descriptor as a main technique in encoding micro features of face images. Our improvements are focused on the feature extraction and dimension reduction steps. In feature extraction, we use a variant of Local Binary Pattern (LBP) so-called Elliptical Local Binary Pattern (ELBP), which is more efficient than LBP for extracting micro facial features of the human face. ELBP of one pixel is built by thresholding its gray value with its P neighboring pixels on a horizontal ellipse. ELBP operator is applied in Pattern of Oriented Edge Magnitudes (POEM) to build Elliptical POEM (EPOEM) descriptor. The dimension reduction step is conducted by using Singular Value Decomposition (SVD) based Whitened Principal Component Analysis (WPCA). For performance evaluation of our improvements, we compare them with LBP based, POEM based approaches and other popular face recognition systems. The experimental results on state-of-the-art FERET and AR face databases prove the advantages and effectiveness of our improvements.

An online three-stage method for facial point localization

Finding facial features respectively under expression and illumination variations is always a difficult problem. One popular solution for improving the performance of facial point localization is to use the spatial relation between facial feature positions. While existing algorithms mostly rely on the priori knowledge of facial structure and on a training phase, this paper presents an online approach without requirements of pre-defined constraints on feature distributions. Instead of training specific detectors for each facial feature, a generic method is first used to extract a set of interest points from test images. With a robust feature descriptor named Patterns Oriented Edge Magnitude (POEM) histogram, a smaller set of these points are picked as candidates. Then we apply a game-theoretic technique to select facial points from the candidates, while the global geometric properties of face are well preserved. The experimental results demonstrate that our method achieves satisfactory performance for face images under expression and lighting variations.