Original Face Research Articles

Fusing Two Kinds of Virtual Samples for Small Sample Face Recognition

Face recognition has become a very active field of biometrics. Different pictures of the same face might include various changes of expressions, poses, and illumination. However, a face recognition system usually suffers from the problem that nonsufficient training samples cannot convey these possible changes effectively. The main reason is that a system has only limited storage space and limited time to capture training samples. Many previous literatures ignored the problem of nonsufficient training samples. In this paper, we overcome the insufficiency of training sample size problem by fusing two kinds of virtual samples and the original samples to perform small sample face recognition. The two used kinds of virtual samples are mirror faces and symmetrical faces. Firstly, we transform the original face image to obtain mirror faces and symmetrical faces. Secondly, we fuse these two kinds of virtual samples to achieve the matching scores between the test sample and each class. Finally, we integrate the matching scores to get the final classification results. We compare the proposed method with the single virtual sample augment methods and the original representation-based classification. The experiments on various face databases show that the proposed scheme achieves the best accuracy among the representation-based classification methods.

Automatic Analysis of Smoothing Techniques by Simulation Model Based Real-Time System for Processing 3D Human Faces

The pivotal research work that has been carried out and described in this literature acknowledges the importance of various smoothing techniques for processing 3D human faces from 2.5D range face images. The smoothing techniques have been developed and implemented using MATLAB-Simulink for real time processing in embedded system. In addition, the significance of smoothed 2.5D range image over original face range image has been discovered as well as its time complexity has also been reported with array of experiments. The variations in time complexities are also accomplished using different optimization levels and execution modes. A set of filtering techniques such as, Max filter, Min filter, Median filter, Mean filter, Mid-point filter and Gaussian filter, have been designed and illustrated using Simulink model. The model takes depth face image (i.e. the range face image) as input in real time and presents the improvement over original face images. In the design flow, the performance of every block has also been characterized by range face images from Frav3D, GavabDB, and Bosphorus databases. In the experimental section of this research article, an array of performance analysis for these smoothing techniques with variation of frameworks is explained.

A CORRELATIVE TWO-STEP APPROACH TO HALLUCINATING FACES

Face hallucination is to synthesize high-resolution face image from the input low-resolution one. Although many two-step learning-based face hallucination approaches have been developed, they suffer from the expensive computational cost due to the separate calculation of the global and local models. To overcome this problem, we propose a correlative two-step learning-based face hallucination approach which bridges the gap between the global model and the local model. In the global phase, we build a global face hallucination framework by combining the steerable pyramid decomposition and the reconstruction. In the residue compensation phase, based on the combination weights and constituent samples obtained in the global phase, a residue face image is synthesized by the neighbor reconstruction algorithm to compensate the hallucinated global face image with subtle facial features. The ultimate hallucinated result is synthesized by adding the residue face image to the global face image. Compared with existing methods, in the global phase, our global face image is more similar to the original high-resolution face image. Furthermore, in the residue compensation phase, we use the combination weights and constituent samples obtained in the global phase to compute the residue face image, by which the computational efficiency can be greatly improved without compromising the quality of facial details. The experimental results and comparisons demonstrate that our approach can not only generate convincible high-resolution face images efficiently, but also has high computational efficiency. Furthermore, our proposed approach can be used to restore the damaged face images in image inpainting. The efficacy of our approach is validated by recovering the damaged face images with visually good results.

Within- and Between-Category Face Identity Discrimination: Association with Physical Facial Features

Facial identity discrimination is crucial for success in the social world. Yet, how this task is accomplished remains incompletely understood. Face perception involves identifying members of same or different of social categories (such as gender and race). We know that differences in facial morphology are critical for discriminating individual faces. What is unclear, however, is whether the same mechanisms are used to discriminate identities when they are members of the same versus different social categories. To address this question, this study examined and compared perceptual performance on within- and between-category facial identity discrimination tasks and evaluated the relationship between the perceptual performances and physical features of face images used for discrimination. Face images from each of five pairs of individuals (two Asian females, two Caucasian females, two African males, one African male and one Caucasian male, or one Caucasian female and one Caucasian male) were morphed to create images along a continuum of facial dissimilarity. Using the original and created images, with psychophysical methods we measured perceptual thresholds for facial identity discrimination in a group of human observers (n=24). For each pair of original face images, the differences in six physical facial features (end-lip raise, mid-top-lip raise, mid-top-lip, mid-low-lip, eye-opening, mid-eyebrow raise and luminance) were also measured. Perceptual thresholds were the lowest (best performance) for the across-race condition, the second lowest for the across-gender condition and the highest for the three same-race and same-gender conditions. Two physical facial features, mid-top-lip raise and luminance, each accounted for a significant portion of perceptual performance (35% and 40%, respectively). These results indicate that between-category facial identity discrimination is more precise than within-category discrimination. Precise discrimination of facial identity is associated with selective physical facial features.

The Adaptation Analysis of the Fully Mechanized Coal Mining Face of Huopu Mine’s Third Soft Coal Seam

To get the maximum coal in front of the working face of the 17# coal seam, we installed a longer beam which is 1.2m in length in the leading end of the original working face supports ZF3000/17/28, and know that working face supports’ setting load and working resistance are lower .We changed the original supports with shield supports ZY3800/15/33 that are adaptable in the geological condition and got the favorable affection.

The Evolution of a Meme Cluster: A Personal Account of a Countercultural Odyssey through <em>The Age of Aquarius</em>

The Evolution of a Meme Cluster: A Personal Account of a Countercultural Odyssey through <em>The Age of Aquarius</em>

Automatic Expression Recognition Based on Mouth Shape Analysis

This paper presents a simple approach for facial expression recognition. In the preprocessing stage, rough lips region is obtained from original face image using HSI space. Then, based on the binary image, exact lips region is located within a rectangle. To achieve this goal, PSO algorithm is applied to search for the best rectangle region. Finally, expression is estimated based on the parts ratio of lips. The simulation results show that this geometric approach is accurate and effective, even for the slightly smile.

3D Face Reconstruction With Local Feature Refinement

In this paper, we propose 3D face reconstruction from two or three images. The reconstruction process begins with a face localization and facial feature extraction. Global transformation process is done for facial features which have been obtained. Local feature refinement is used to refine the result of global transformation. Last, texture mapping process is done to provide texture of 3D model. The method used for face reconstruction can generate accurate and fast result for various poses and facial expressions, and by using local feature refinement can improve the quality of reconstruction output more similar to the original face image.

Face drawing experience is associated with better face recognition performance and reduced left-side bias in face perception

Recent research in computer vision showed that while both analytic (local) and holistic (global) approaches perform well in face recognition, the fusion of the two yields the best performance. Professional face artists/caricaturists mastering both the drawing of individual facial features and whole faces may engage in such fused processing of faces, and thus may excel in face recognition. Zhou et al. (2012) found that art students with face drawing experience showed weaker holistic face processing than non-drawers; nevertheless, the two groups did not differ in sequential face-matching performance. Here we recruited professional face artists, in contrast to art students, in a simultaneous face-matching task with unfamiliar faces that differed in illumination, pose, disguise and expression. In contrast to sequential face-matching, our task reduces the involvement of visual short-term memory, as face artists' advantage is more likely to be in their perceptual ability than in memory. We recruited 15 face artists and 15 non-drawers. Before the experiment, participants drew a face within 15 minutes. An experienced face artist rated participants' expertise according to the drawings. We found that face artists outperformed non-drawers in the simultaneous face-matching task (t(28) = 2.56, p <.05). Face drawing expertise was positively correlated with face recognition performance (r = 0.38, p <.05). In addition, while non-drawers judged a face made from two left half-faces more similar to the original face than one from two right half-faces, i.e., the left side bias (right hemisphere dominance) in face perception, face artists had a reduced bias than non-drawers (t(28) = -2.39, p <.05), suggesting reduced global face processing. Face drawing expertise was negatively correlated with the bias (r = -0.47, p <.05). Together, the results suggest that face drawing expertise may shift attention from global to local, which may help face recognition in challenging tasks. Meeting abstract presented at VSS 2014

Improved CO2 Capture from Flue Gas by Basic Sites, Charge Gradients, and Missing Linker Defects on Nickel Face Cubic Centered MOFs

The adsorptive properties of the isoreticular series [Ni8(OH)4(H2O)2(BDP_X)6] (H2BDP_X = 1,4‐bis(pyrazol‐4‐yl)benzene‐4‐X with X = H (1), OH (2), NH2 (3)) can be enhanced by postsynthetic treatment with an excess of KOH in ethanol. In the case of X = H, NH2, this treatment leads to partial removal of the organic linkers, deprotonation of coordinated water molecules and introduction of extraframework cations, giving rise to materials of K[Ni8(OH)5(EtO)‐(H2O)2(BDP_X)5.5] (1@KOH, 3@KOH) formulation, in which the original framework topology is maintained. By contrast, the same treatment with KOH in the [Ni8(OH)4(H2O)2(BDP_OH)6] (2) system, enclosing the more acidic phenol residues, leads to a new material containing a larger fraction of missing linker defects and extra‐framework cations as well as phenolate residues, giving rise to the material K3[Ni8(OH)3(EtO)(H2O)6(BDP_O)5] (2@KOH), which also conserves the original face cubic centered (fcu) topology. It is noteworthy that the introduction of missing linker defects leads to a higher accessible pore volume with a concomitant increased adsorption capacity. Moreover, the creation of coordinatively unsaturated metal centers, charge gradients, and phenolate nucleophilic sites in 2@KOH gives rise to a boosting of CO2 capture features with increased adsorption heat and adsorption capacity, as proven by the measurement of pulse gas chromatography and breakthrough curve measurements of simulated flue gas.

Naturalness in Zen and Shin Buddhism: Before and Beyond Self- and Other-Power

This article seeks to clarify the fundamental similarities and differences between the two most prominent forms of Buddhism in Japan: Zen and Shin (or True Pure Land School) Buddhism. While proponents of Zen typically criticize Shin for seeking the Buddha outside the self, rather than as one's ‘true self’ or ‘original face’, proponents of Shin typically criticize Zen for relying of ‘self-power’, which they understand as inevitably a form of ‘ego-power’, rather than entrusting oneself to the ‘Other-power’ of Amida Buddha. Yet Zen and Shin in fact share some deep commonalities: not only do they both characterize the ultimate ‘Dharma-body’ of the Buddha as ‘emptiness’ or ‘formlessness’, they also both speak of the enlightened state issuing from a realization of this Dharma-body in terms of ‘naturalness’. While attending to the significant differences between the Zen and Shin approaches to this enlightened state of naturalness, this article also pursues the most radical indications of both schools which suggest that this naturalness itself ultimately lies before and beyond both self- and Other-power.

Human Perception of Visual Realism for Photo and Computer-Generated Face Images

Computer-generated (CG) face images are common in video games, advertisements, and other media. CG faces vary in their degree of realism, a factor that impacts viewer reactions. Therefore, efficient control of visual realism of face images is important. Efficient control is enabled by a deep understanding of visual realism perception: the extent to which viewers judge an image as a real photograph rather than a CG image. Across two experiments, we explored the processes involved in visual realism perception of face images. In Experiment 1, participants made visual realism judgments on original face images, inverted face images, and images of faces that had the top and bottom halves misaligned. In Experiment 2, participants made visual realism judgments on original face images, scrambled faces, and images that showed different parts of faces. Our findings indicate that both holistic and piecemeal processing are involved in visual realism perception of faces, with holistic processing becoming more dominant when resolution is lower. Our results also suggest that shading information is more important than color for holistic processing, and that inversion makes visual realism judgments harder for realistic images but not for unrealistic images. Furthermore, we found that eyes are the most influential face part for visual realism, and face context is critical for evaluating realism of face parts. To the best of our knowledge, this work is a first realism-centric study attempting to bridge the human perception of visual realism on face images with general face perception tasks.

A New Method of Face Modeling with Construction of Local Texture Model

The active shape model (ASM) is a statistical parametric model, which is mainly used in image feature extraction. On the basis of the analysis of the original ASM texture model, a new texture modeling method was proposed in this paper. The improved method fully utilized the gray level information of adjacent points in the neighborhood of sampling points, improved the original face modeling method which only used the one-dimensional gray information with model matching accuracy problems. The experiments on Weizmann face database Indicate that, the improved method can obviously improve the feature point positioning accuracy, and accelerate the speed of face model fitting.

Noise-free representation based classification and face recognition experiments

The representation based classification has achieved promising performance in high-dimensional pattern classification problems. As we know, in real-world applications the samples are usually corrupted by noise. However, representation based classification can take only noise in the test sample into account and is not able to deal with noise in the training sample, which causes side-effect on the classification result. In order to make the representation based classification more suitable for real-world applications such as face recognition, we propose a new representation based classification method in this paper. This method can effectively and simultaneously reduce noise in the test and training samples. Moreover, the proposed method can reduce noise in both the original and virtual training samples and then exploits them to determine the label of the test sample. The virtual training sample is generated from the original face image and shows possible variation of the face in scale, facial pose and expression. The experimental results show that the proposed method performs very well in face recognition.

Research of Face Recognition Methods Based on Binding Feature Extraction

To address the problem that the dimension of the feature vector extracted by Local Binary Pattern (LBP) for face recognition is too high and Principal Component Analysis (PCA) extract features are not the best classification features, an efficient feature extraction method using LBP, PCA and Maximum scatter difference (MSD) has been introduced in this paper. The original face image is firstly divided into sub-images, then the LBP operator is applied to extract the histogram feature. and the feature dimensions are further reduced by using PCA. Finally,MSD is performed on the reduced PCA-based feature.The experimental results on ORL and Yale database demonstrate that the proposed method can classify more effectively and can get higher recognition rate than the traditional recognition methods.

Influence of skin ageing features on Chinese women's perception of facial age and attractiveness

ObjectivesAgeing leads to characteristic changes in the appearance of facial skin. Among these changes, we can distinguish the skin topographic cues (skin sagging and wrinkles), the dark spots and the dark circles around the eyes. Although skin changes are similar in Caucasian and Chinese faces, the age of occurrence and the severity of age-related features differ between the two populations. Little is known about how the ageing of skin influences the perception of female faces in Chinese women. The aim of this study is to evaluate the contribution of the different age-related skin features to the perception of age and attractiveness in Chinese women.MethodsFacial images of Caucasian women and Chinese women in their 60s were manipulated separately to reduce the following skin features: (i) skin sagging and wrinkles, (ii) dark spots and (iii) dark circles. Finally, all signs were reduced simultaneously (iv). Female Chinese participants were asked to estimate the age difference between the modified and original images and evaluate the attractiveness of modified and original faces.ResultsChinese women perceived the Chinese faces as younger after the manipulation of dark spots than after the reduction in wrinkles/sagging, whereas they perceived the Caucasian faces as the youngest after the manipulation of wrinkles/sagging. Interestingly, Chinese women evaluated faces with reduced dark spots as being the most attractive whatever the origin of the face. The manipulation of dark circles contributed to making Caucasian and Chinese faces being perceived younger and more attractive than the original faces, although the effect was less pronounced than for the two other types of manipulation.ConclusionThis is the first study to have examined the influence of various age-related skin features on the facial age and attractiveness perception of Chinese women. The results highlight different contributions of dark spots, sagging/wrinkles and dark circles to their perception of Chinese and Caucasian faces.RésuméObjectifsLe vieillissement entraine des changements caractéristiques de l'apparence de la peau du visage. Parmi ces changements on distingue les éléments topographiques (relâchement de la peau et rides), les taches brunes et les cernes sur le contour de l'œil. Bien que ces modifications cutanées avec l'âge soient similaires pour les visages caucasiens et chinois; leur âge d'apparition et leur degré de sévérité varient entre ces deux populations. Il y a très peu d'informations disponibles liées à l'influence du vieillissement cutané sur la perception des visages féminins par les femmes chinoises. L'objectif de cette étude est d'évaluer la contribution des différents signes de vieillissement à la perception de l'âge et d'attirance chez ces femmes.MethodesDes photos de visages de femmes caucasiennes et chinoises d'environ 60 ans ont été manipulées de façon à réduire séparément les signes suivants: (i) le relâchement de la peau et les rides, (ii) les taches brunes, et (iii) les cernes. Enfin, tous les signes ont été atténués ensemble (iv). Des participantes chinoises ont estimé, à partir de ces photos, l'écart d'âge entre la version originale et chaque version modifiée; elles ont également évalué l'attirance des visages originaux et modifiés.ResultatsLes femmes chinoises ont jugé les visages chinois plus jeunes après correction des taches qu'après correction des rides/relâchement, alors que les visages caucasiens ont été perçus les plus jeunes après correction des rides/relâchement. Les femmes chinoises ont jugé que les visages avec correction des taches étaient les plus attirants quelle que soit l'origine du visage. La manipulation des cernes a entraîné un rajeunissement des 2 types de visages et les a rendus plus attirants, même si l'effet observé était moindre que pour les autres corrections.ConclusionIl s'agit de première étude qui examine l'influence de plusieurs signes de vieillissement cutanés sur la perception de l'âge et de l'attirance des visages par les femmes chinoises. Les résultats mettent en évidence que les taches, les rides/relâchement et les cernes contribuent différemment à leur perception des visages chinois et caucasiens.

Face region authentication and recovery system based on SPIHT and watermarking

The face regions of digital pictures are some of the principal target of tampering to generate a potential scandal, causing social and economic damages to involved persons. In this paper, we propose a face region authentication and recovery system, in which the face regions are automatically protected at the moment when the picture is taken by a digital camera. When the original face of the picture is replaced by another face by malicious person, the system can detect the tampered face and recover the original one. The proposed system consists of two stages: the face region protection stage and the face region tamper detection and recovery stage. In both stages, the face detection module based on the Viola-Jones algorithm, face region encoding/decoding modules based on the Set Partitioning in Hierarchical Trees (SPIHT) algorithm and watermarking module based on Quantization Index Modulation (QIM) are used. These three algorithms, Viola-Jones detector, SPIHT and QIM, are determined as most adequate algorithms for proposed system after several evaluations. The experimental results show a high quality of the watermarked as well as the recovered images, obtaining average Peak Signals to Noise Ratios (PSNR) of more than 40 and 38 dB, respectively.

Contribution of detailed parts around talker's mouth for audio-visual speech perception

In this study, the relationship between speech intelligibility and effects of the parts around talker's mouth was investigated based on the results of audio-visual speech intelligibility tests. As the stimuli, nonsense tri-syllables speech sounds were combined with three kinds of moving image of the talker's face: original face, circumference of the lips (mouth part extracted from the original face), and masked lips (face without the mouth). The extracted area around the mouth was varied as a parameter in the circumference-of-the-lips conditions. Generated stimuli were presented with speech spectrum noise to the participants. The results showed that intelligibility scores of several phonemes (/h/, /m/, /w/, /b/, /p/) were increased by adding the visual information. Moreover, there was no significant difference between the score of the original-face condition and that of the circumference-of-the-lips condition. Interestingly, significant difference was observed between the score of the audio-only condition and that of the masked-lips-condition. These results imply that not only a mouth but also areas around the mouth without mouth itself provide rich information for speech understanding. Effects of the mouth edges on speech intelligibility are being examined as a next step.

Integrating the original face images and “symmetrical faces” to perform face recognition

Using the original and ‘symmetrical face’ training samples to perform representation based face recognition was first proposed in [1]. It simultaneously used the original and ‘symmetrical face’ training samples to perform a two-step classification and achieved an outstanding classification result. However, in [1] the “symmetrical face” is devised only for one method. In this paper, we do some improvements on the basis of [1] and combine this “symmetrical faces” transformation with several representation based methods. We exploit all original training samples, left “symmetrical face” training samples and right “symmetrical face” training samples for classification and use the score fusion for ultimate face recognition. The symmetry of the face is first used to generate new samples, which is different from original face image but can really reflect some possible appearance of the face. It effectively overcomes the problem of non-sufficient training samples. The experimental results show that the proposed scheme can be used to improve a number of traditional representation based methods including those that are not presented in the paper.

Kernel inverse Fisher discriminant analysis for face recognition

In this paper, we present a new nonlinear feature extraction method for face recognition. The proposed method incorporates the kernel trick with inverse Fisher discriminant analysis and develops a two-phase kernel inverse Fisher discriminant analysis criterion – KPCA plus IFDA. In the proposed method, we first apply the nonlinear kernel trick to map the original face samples into an implicit feature space and then perform inverse Fisher discriminant analysis in the feature space to produce nonlinear discriminating features. In implementation, kernel IFDA seeks nonlinear discriminating features by minimizing the inverse Fisher discriminant quotient and overcome the singularity problem by projective transformation of scatter matrices. Experimental results on ORL, FERET and AR face databases demonstrate the effectiveness of the proposed method.