Face Recognition Research Papers - Academia.edu (original) (raw)

The semiotics of the face studies the meaning of the human face in contemporary visual cultures. There are two complementary research foci: widespread practices of face exhibition in social networks like Facebook, Instagram, Snapchat, and Tinder; and minority practices of occultation, including the mask in anti-establishment political activism (Anonymous) and the veil in religious dressing codes. The meaning of the human face is currently changing on a global scale: through the invention and diffusion of new visual technologies (digital photography, visual filters, as well as software for automatic face recognition); through the creation and establishment of novel genres of face representation (the selfie); and through new approaches to face perception, reading, and memorization (e.g., the ‘scrolling’ of faces on Tinder). Cognitions, emotions, and actions that people attach to the interaction with one’s and others’ faces are undergoing dramatic shifts. In the semiotics of the face, an interdisciplinary but focused approach combines visual history, semiotics, phenomenology, visual anthropology, but also face perception studies and collection and analysis of big data, so as to study the social and technological causes of these changes and their effects in terms of alterations in self-perception and communicative interaction. In the tension between, on the one hand, political and economic agencies pressing for increasing disclosure, detection, and marketing of the human face (for reasons of security and control, for commercial or bureaucratic purposes) and, on the other hand, the counter-trends of face occultation (parents ‘hiding’ their children from the Internet, political activists concealing their faces, religious or aesthetic veils, writers and artists like Bansky or Ferrante choosing not to reveal their identity), the visual syntax, the semantics, and the pragmatics of the human face are rapidly evolving. The semiotics of the face carries on a comprehensive survey of this socio-cultural phenomenon.

- by
- •
- Semiotics, Cultural Semiotics, Visual Semiotics, Face Recognition

- by Massimo Leone
- •
- Semiotics, Social Networks, Internet Studies, Social Networking

Emotion recognition is one of the important highlights of human emotional intelligence and has long been studied to be incorporated with machine intelligence argued to make machines even more intelligent. This paper aims to contribute to this field of study by enabling machines to recognize emotion from facial electromyogram (EMG) signals. This includes a compilation of the groups attempt to recognize basic facial expressions namely happy, angry, and sad through the use of EMG signals from facial muscles. The group extracted features from the three EMG signals from the face of two human subjects, a male and a female, and analyzed these features to serve as feature templates. Using a minimum-distance classifier, recognition rates exceeded the target accuracy - 85 percent - reaching 94.44 percent for both the male and female subjects.

- by Grace Briones
- •
- Computer Science, Artificial Intelligence, Emotional intelligence, Biosensors

Expression Glasses provide a wearable \appliance-based" alternative to generalpurpose machine vision face recognition systems. The glasses sense facial muscle movements, and use pattern recognition to identify meaningful expressions such a s confusion or interest. A prototype of the glasses has been built and evaluated. The prototype uses piezoelectric sensors hidden in a visor extension to a pair of glasses, providing for compactness, user control, and anonymity. On users who received no training or feedback, the glasses initially performed at 94% accuracy in detecting an expression, and at 74% accuracy in recognizing whether the expression was confusion or interest. Signi cant i mprovement b e y ond these numbersappears to be possible with extended use, and with a small amount of feedback (letting the user see the output of the system).

A major factor hindering the deployment of a fully functional automatic facial expression detection system is the lack of representative data. A solution to this is to narrow the context of the target application, so enough data is available to build robust models so high performance can be gained. Automatic pain detection from a patient's face represents one such application. To facilitate this work, researchers at McMaster University and University of Northern British Columbia captured video of participant's faces (who were suffering from shoulder pain) while they were performing a series of active and passive range-of-motion tests to their affected and unaffected limbs on two separate occasions. Each frame of this data was AU coded by certified FACS coders, and self-report and observer measures at the sequence level were taken as well. This database is called the UNBC-McMaster Shoulder Pain Expression Archive Database. To promote and facilitate research into pain and augment current datasets, we have publicly made available a portion of this database which includes: 1) 200 video sequences containing spontaneous facial expressions, 2) 48,398 FACS coded frames, 3) associated pain frame-by-frame scores and sequence-level self-report and observer measures, and 4) 66-point AAM landmarks. This paper documents this data distribution in addition to describing baseline results of our AAM/SVM system. This data will be available for distribution in March 2011.

- by Patricia Solomon
- •
- Psychology, Face Recognition, Support Vector Machines, Face

The paper describes a multisensorial personidentification system: visual and acoustic cues are usedjointly for person identification. A simple approach,based on the fusion of the lists of scores produced independentlyby a speaker recognition system and a facerecognition system, is presented. Experiments are reportedwhich show that integration of visual and acousticinformation enhances both performance and reliabilityof the separate systems. Finally two network

In the context of Face Recognition the paper compares between Principal Component Analyses (PCA) and Independent Component Analysis (ICA). In the psychological and algorithmic literature Principal Component Analyses (PCA) and Independent Component Analyses (ICA) are the basis of numerous studies. Classical technique in statistical data analyses is called Principal Component Analyses (PCA) and technique of array processing and data analysis is called Independent Component Analysis (ICA). This paper gives the better concept how each algorithms are worked. This concept helps to advance level experiment. Besides, those method is so strong others system and algorithm. In both case, ICA performs good but not as good as PCA. For Face Recognition Principal Component Analyses basis algorithm represents intelligent suction of a random search within a short time and its can detect to solve the problem.

Computer vision applications for mobile phones are gaining increasing attention due to several practical needs resulting from the popularity of digital cameras in today's mobile phones. In this work, we consider the task of face detection and authentication in mobile phones and experimentally analyze a face authentication scheme using Haar-like features with Ad-aBoost for face and eye detection, and Local Binary Pattern (LBP) approach for face authentication. For comparison, another approach to face detection using skin color for fast processing is also considered and implemented. Despite the limited CPU and memory capabilities of today's mobile phones, our experimental results show good face detection performance and average authentication rates of 82% for small-sized faces (40×40 pixels) and 96% for faces of 80×80 pixels. The system is running at 2 frames per second for images of 320×240 pixels. The obtained results are very promising and assess the feasibility of face authentication in mobile phones. Directions for further enhancing the performance of the system are also discussed.

- by Tran Viet
- •
- Computer Vision, Face Recognition, Face Detection, Mobile phone

Proposes a face recognition method which is characterized by structural simplicity, trainability and high speed. The method consists of two stages of feature extractions: first, higher order local autocorrelation features which are shift-invariant and additive are extracted from an input image; then those features are linearly combined on the basis of multivariate analysis methods so as to provide new effective features for face recognition in learning from examples

- by Takio Kurita
- •
- Face Recognition

Agency is-besides communion-a basic dimension of traits. It can be specifically linked to behavioral outcomes, to status, mastery, self-esteem and to success. The present paper analyzes the situational malleability of agency. Two studies tested whether an individual's agency (but not communion) is situationally influenced by the experience of success versus failure at a task, as well as whether this effect is the same for men and women. Supporting our hypotheses, the induction of success versus failure experiences led to changes in agency that were independent of actual performance, independent of type of task (memorizing vs. face recognition), independent of induction methodology (easy vs. difficult task vs. manipulated performance feedback), and independent of self-esteem, initial level of agency and of the participants' gender. Communion was not influenced by this kind of experience. Implications for both the basic dimension of agency and for theories on gender and gender stereotypes are discussed.

- by Bogdan Wojciszke
- •
- Sociology, Psychology, Cognitive Science, Face Recognition

The aim of this research was to study the influence of exposure duration and the spatial-frequency composition of faces in a «same-different» judgment task. Subjects had to match two faces presented successively. The recognition rate depended on the spatial-frequency composition of the target face, and on exposure duration only for high-frequency stimuli. This effect was observed only for durations which were greater than Bloch's psychophysics threshold and only concerned the «same» face pairs. These results are quite consistent with the hypothesis that exposure duration has a differential effect on low and high frequency integration. They are discussed in relation to the single and dual-process models of the «same-different» judgment task (Farell, 1985). Potential consequences on the format of facial representations in memory are proposed

- by Rémy Versace
- •
- Psychology, Cognitive Science, Perception, Mental Representation

We present two real-time hidden Markov model-based systems for recognizing sentence-level continuous American Sign Language (ASL) using a single camera to track the user's unadorned hands. The first system observes the user from a desk mounted camera and achieves 92% word accuracy. The second system mounts the camera in a cap worn by the user and achieves 98% accuracy (97% with an unrestricted grammar). Both experiments use a 40 word lexicon.

- by Shadman Shahriar
- •
- Information Systems, Computer Vision, Sign Language, Pattern Recognition

This paper describes a method to detect smiles and laughter sounds from the video of natural dialogue. A smile is the most common facial expression observed in a dialogue. Detecting a user's smiles and laughter sounds can be useful for estimating the mental state of the user of a spoken-dialogue-based user interface. In addition, detecting laughter sound can be utilized to prevent the speech recognizer from wrongly recognizing the laughter sound as meaningful words. In this paper, a method to detect smile expression and laughter sound robustly by combining an image-based facial expression recognition method and an audio-based laughter sound recognition method. The image-based method uses a feature vector based on feature point detection from face images. The method could detect smile faces by more than 80% recall and precision rate. A method to combine a GMM-based laughter sound recognizer and the image-based method could improve the accuracy of detection of laughter sounds compared with methods that use image or sound only. As a result, more than 70% recall and precision rate of laughter sound detection was obtained from the natural conversation videos.

- by Akinori Ito
- •
- Face Recognition, User Interface, Speech Recognition, Facial expression

With the increasing demand for online banking lack of security in the system has been felt due to a tremendous increase in fraudulent activities. Facial recognition is one of the numerous ways that banks can increase security and accessibility. This paper proposes to inspect the use of facial recognition for login and for banking purposes. The potency of our system is that it provides strong security, username and password verification, face recognition and pin for a successful transaction. Multilevel Security of this system will reduce problems of cyber-crime and maintain the safety of the internet banking system. The end result is a strengthened authentication system that will escalate the confidence of customers in the banking sector.

Thermal imagery is a substitute of visible imagery for face detection due to its property of illumination invariance with the variation of facial appearances. This paper presents an effective method for human face detection in thermal imaging. The concept of histogram plot has been used in the feature extraction process and later in face detection. Techniques like thresholding, object boundary analysis, morphological operation etc. have been performed on the images to ease the process of detection. In order to enhance the performance of the algorithm and to reduce the computation time, parallelism has been achieved using Message Passing Interface (MPI) model. Overall, the proposed algorithm showed a higher level of accuracy and less complexity time of 0.11 seconds in the parallel environment as compared to 0.20 seconds in a serial environment.

- by Chirag Kyal
- •
- Parallel Computing, Computer Vision, Image Processing, Machine Learning

This paper consists of development of detection strategies for face recognition tasks and to access its feasibility for forensic analysis using the FERET face database Author has used global feature extraction technique using statistical method for image classification. Facial images of three subjects with different expression and angles are used for classification. Principal Component Analysis has been used for three classes. Mahalanobis distance and Euclidian distance are used as similarity measures and a result of both methods is compared.

- by mahananda malkauthekar
- •
- Principal Component Analysis, Face Recognition, Face, Databases

This paper proposes a new approach for face tracking based on the individual tracking of KLT features. The face is initially detected using a face detection scheme, and KLT features are distributed along the face. Each feature is tracked individually, and the displacement of the center of the face is obtained using a Weighted Vector Median Filter (WVMF) of the individual displacements. The scale change is then computed based on the position of each feature w.r.t. the center of the face. The experimental results indicate that the proposed approach is fast and robust in the presence of partial occlusions.

- by Jose Carlos Bins Filho and +1
- •
- Multimedia, Face Recognition, Face Detection, Median Filter

Balancing computational efficiency with recognition accuracy is one of the major challenges in real-world video-based face recognition. A significant design decision for any such system is whether to process and use all possible faces detected over the video frames, or whether to select only a few 'best' faces. This paper presents a video face recognition system based on probabilistic Multi-Region Histograms to characterise performance trade-offs in: (i) selecting a subset of faces compared to using all faces, and (ii) combining information from all faces via clustering. Three face selection metrics are evaluated for choosing a subset: face detection confidence, random subset, and sequential selection. Experiments on the recently introduced MOBIO dataset indicate that the usage of all faces through clustering always outperformed selecting only a subset of faces. The experiments also show that the face selection metric based on face detection confidence generally provides better recognition performance than random or sequential sampling. Moreover, the optimal number of faces varies drastically across selection metric and subsets of MOBIO. Given the trade-offs between computational effort, recognition accuracy and robustness, it is recommended that face feature clustering would be most advantageous in batch processing (particularly for video-based watchlists), whereas face selection methods should be limited to applications with significant computational restrictions.

- by Brian Lovell
- •
- Face Recognition, Video Processing, Probability, Face Detection

In this paper we present a non-intrusive model-based gaze tracking system. The system estimates the 3-D pose of a user's head by tracking as few as six facial feature points. The system locates a human face using a statistical color model without any mark on the face and then finds and tracks the facial features, such as eyes, nostrils and lip corners. A full perspective model is employed to map these feature points onto the 3D pose. Several techniques have been developed to track the features points and recover from failure. We currently achieve a frame rate of 15+ frames per second using an HP 9000 workstation with a framegrabber and a Canon VC-C1 camera. The application of the system has been demonstrated by a gazedriven panorama image viewer. The potential applications of the system include multimodal interfaces, virtual reality and video-teleconferencing.

- by Jie Yang
- •
- Cognitive Science, Human Computer Interaction, Computer Vision, Iterative Methods

Recognizing faces with uncontrolled pose, illumination, and expression is a challenging task due to the fact that features insensitive to one variation may be highly sensitive to the other variations. Existing techniques dealing with just one of these variations are very often unable to cope with the other variations. The problem is even more difficult in applications where only one gallery image per person is available. In this paper, we describe a recognition method, Adaptive Principal Component Analysis (APCA), that can simultaneously deal with large variations in both illumination and facial expression using only a single gallery image per person. We have now extended this method to handle head pose variations in two steps. The first step is to apply an Active Appearance Model (AAM) to the non-frontal face image to construct a synthesized frontal face image. The second is to use APCA for classification robust to lighting and pose. The proposed technique is evaluated on three public face databases -Asian Face, Yale Face, and FERET Database -with images under different lighting conditions, facial expressions, and head poses. Experimental results show that our method performs much better than baseline recognition methods including PCA, FLD and PRM. More specifically, we show that by using AAM for frontal face synthesis from high pose angle faces, the recognition rate of our APCA method increases by up to a factor of 4.

- by Brian Lovell
- •
- Cognitive Science, Principal Component Analysis, Face Recognition

Face recognition is one of the most important image processing research topics which is widely used in personal identification, verification and security applications. In this paper, a face recognition system, based on the principal component analysis (PCA) and the feedforward neural network is developed. The system consists of two phases which are the PCA preprocessing phase, and the neural network classification phase. PCA is applied to calculate the feature projection vector of a given face which is then used for face ...

- by Hasan Demirel
- •
- Computer Science, Artificial Intelligence, Image Processing, System Identification

— There are various face detection methods which usually works on multiple samples per person and has various applications such as e-passport, ID card generation or various law enhancement. In all such practical applications, mostly single sample per person is either enrolled or recorded in the database. Since, only single sample available per person most of the proposed techniques fails in face detection due to lack of availability of sample. To overcome such drawbacks,we propose in this project a novel discriminative multi manifold analysis (DMMA) method by learning discriminative features from image patches. Initially, we partition each enrolled face image into several non-overlapping patches to form an image set for single sample per person. Then, we formulate the single sample per person face recognition as a manifold-manifold matching issues' and learn multiple DMMA feature spaces to maximize the manifold margins of different persons. Finally, we present a recreated-based manifold-manifold distance to identify the unlabeled subjects.

- by IJREAM EDITOR
- •
- Face Recognition
- by Nicholas Butko
- •
- Pediatrics, Machine Learning, Face Recognition, Facial expression

One of the demanding tasks in face recognition is to handle illumination and expression variations. A lot of research is in progress to overcome such problems. This paper addresses the preprocessing method that is composed of grouping SVD perturbation and DWT. The proposed technique also performs well under one picture per person scenarios. The resulting image of this method is fed in to the simple SVD algorithm for face recognition. This paper performs its accuracy test on ORL, Yale, PIE and AR databases and focuses on the illumination problems.

- by muddassar sharif
- •
- Face Recognition

In recent years, the use of Intelligent Closed-Circuit Television (ICCTV) for crime prevention and detection has attracted significant attention. Existing face recognition systems require passport-quality photos to achieve good performance. However, use of CCTV images is much more problematic due to large variations in illumination, facial expressions and pose angle. In this paper we propose a pose variability compensation technique, which synthesizes realistic frontal face images from non-frontal views. It is based on modelling the face via Active Appearance Models and detecting the pose through a correlation model. The proposed technique is coupled with Adaptive Principal Component Analysis (APCA), which was previously shown to perform well in the presence of both lighting and expression variations. Experiments on the FERET dataset show up to 6 fold performance improvements. Finally, in addition to implementation and scalability challenges, we discuss issues related to on-going real life trials in public spaces using existing surveillance hardware.

- by Brian Lovell
- •
- Principal Component Analysis, Face Recognition, Facial expression, Public Space

Existing 3D face recognition algorithms have achieved high enough performances against public datasets like FRGC v2, that it is difficult to achieve further significant increases in recognition performance. However, the 3D TEC dataset is a more challenging dataset which consists of 3D scans of 107 pairs of twins that were acquired in a single session, with each subject having a scan of a neutral expression and a smiling expression. The combination of factors related to the facial similarity of identical twins and the variation in facial expression makes this a challenging dataset. We conduct experiments using state of the art face recognition algorithms and present the results. Our results indicate that 3D face recognition of identical twins in the presence of varying facial expressions is far from a solved problem, but that good performance is possible.

- by Patrick Flynn
- •
- Face Recognition, Facial expression, 3-D scanning

Illumination invariance remains the most researched, yet the most challenging aspect of automatic face recognition. In this paper we investigate the discriminative power of colour-based invariants in the presence of large illumination changes between training and test data, when appearance changes due to cast shadows and non-Lambertian effects are significant. Specifically, there are three main contributions: (i) we employ a more sophisticated photometric model of the camera and show how its parameters can be estimated, (ii) we derive several novel colour-based face invariants, and (iii) on a large database of video sequences we examine and evaluate the largest number of colour-based representations in the literature. Our results suggest that colour invariants do have a substantial discriminative power which may increase the robustness and accuracy of recognition from low resolution images.

- by Ognjen Arandjelovic
- •
- Engineering, Electrical Engineering, Electronic Engineering, Computer Science

For intelligent service robots, it is essential to recognize users in order to provide appropriate services to a correctly authenticated user. However, in robot environments in which users freely move around the robot, it is difficult to force users to cooperate for authentication as in traditional biometric security systems. This paper introduces a user authentication system that is designed to recognize users who are unconscious of a robot or of cameras. In the proposed system, biometrics and semi-biometrics are incorporated to cope with the limited applicability of traditional authentication techniques. Semi-biometrics indicates a set of features useful for discriminating persons, but only in the interested group of persons and in the interested frame of time. As a representative semi-biometric feature, body height and color characteristics of clothes are investigated. In particular, a novel method to measure body height with single camera is proposed. In addition, by incorporating tracking functionality, the system can maintain the user status information continuously, which is useful not only for recognition but also for finding a designated person. 1

- by hosub yoon
- •
- Engineering, Computer Science, Face Recognition, Biometrics

Two experiments were carried out to study the role of gender category in evaluations of face distinctiveness.In Experiment 1, participants had to evaluate the distinctiveness and the femininitymasculinityof real or artificial composite faces. The composite faces were created by blending either faces of thesame gender (sexed composite faces, approximating the sexed prototypes) or faces of both genders(nonsexed composite faces, approximating the face prototype). The results show that the distinctivenessratings decreased as the number of blended faces increased. Distinctiveness and gender ratings did notcovary for real faces or sexed composite faces, but they did vary for nonsexed composite faces. InExperiment 2, participants were asked to state which of two composite faces, one sexed and onenonsexed, was more distinctive. Sexed composite faces were selected less often. The results areinterpreted as indicating that distinctiveness is based on sexed prototypes. Implications for face recognition models are discussed.

- by Mathieu Gallay and +1
- •
- Psychology, Cognitive Science, Psychophysics, Experimental Psychology

This paper presents a real-time auditory and visual tracking of multiple objects for humanoid under real-world environments. Real-time processing is crucial for sensorimotor tasks in tracking, and multiple-object tracking is crucial for real-world applications. Multiple sound source tracking needs perception of a mixture of sounds and cancellation of motor noises caused by body movements. However its real-time processing has not been reported yet. Real-time tracking is attained by fusing information obtained by sound source localization, multiple face recognition, speaker tracking, focus of attention control, and motor control. Auditory streams with sound source direction are extracted by active audition system with motor noise cancellation capability from 48 KHz sampling sounds. Visual streams with face ID and 3D-position are extracted by combining skincolor extraction, correlation-based matching, and multiple-scale image generation from a single camera. These auditory and visual streams are associated by comparing the spatial location, and associated streams are used to control focus of attention. Auditory, visual, and association processing are performed asynchronously on different PC's connected by TCP/IP network. The resulting system implemented on an upper-torso humanoid can track multiple objects with the delay of 200 msec, which is forced by visual tracking and network latency.

- by Blossom Stephan
- •
- Psychology, Cognitive Science, Perception, Face Recognition

People recognize familiar faces in a similar way by using interior facial features (facial regions) such as eyes, nose, mouth, etc. However, the importance of these regions in the realization of face identification and a quantification of the impact of such regions on the recognition process could vary from one region to another. An intuitively appealing observation is that of monotonicity: the more regions are taken into account in the recognition process, the better. From a formal point of view, the relevance of the facial regions and an aggregation of these pieces of experimental evidence can be described in the formal setting of fuzzy measures. Fuzzy measures are of particular interest with this regard given their monotonicity property (which stands in a clear contrast with the more restrictive additivity property inherent to probability-like measures). In this study, we concentrate on the construction of fuzzy measures (more specifically, k-fuzzy measure) and characterize their performance in the problem of face recognition using a collection of experimental data.

- by Paweł Karczmarek
- •
- Face Recognition, Soft Computing, Fuzzy Integral, Fuzzy Measures

Face detection methods are typically considered multiple images for each individual, but in real-world only one training image per person is available. The Robust Sparse Coding by Category (SRC) has been successfully used in face recognition. But the idea and approach continues to be promoted. In this paper, we enhance face detection using sparse matrix classification by using gray wolf optimazation algorithm for parameter setting. This effectively makes the size of dictionaries to keep the detection rate up and the number of variables does not depend on the number of classes (people), also with the proposed method rate of calculations significantly reduced.

- by mohammad karim hardani asl
- •
- Face Recognition, Classification, Face recognition using MATLAB, RSC
- by John Morton
- •
- Psychology, Cognitive Science, Cognitive development, Face Recognition

In this paper a non-linear extension to the synthetic discriminant function (SDF) is proposed. The SDF is a well known 2-D correlation filter for object recognition. The proposed nonlinear version of the SDF is derived from kernel-based learning. The kernel SDF is implemented in a nonlinear high dimensional space by using the kernel trick and it can improve the performance of the linear SDF by incorporating the image's class higher order moments. We show that this kernelized composite correlation filter has an intrinsic connection with the recently proposed correntropy function. We apply this kernel SDF to face recognition and simulations show that the kernel SDF significantly outperforms the traditional SDF as well as is robust in noisy data environments.

- by Kyu-hwa Jeong
- •
- Face Recognition, Nonlinear filters, Object Recognition, Image recognition

These studies ask whether S remembers a picture better the greater the "depth of processing" he allots to it. Depth of processing pictures of faces was varied according to judgments of sex ("superficial") or judgments of likableness or honesty of the person pictured. Performance on a later recognition memory test was high for pictures judged for likableness or honesty, and low for pictures judged for sex. This ordering held as'true for intentional learners as for incidental learners. A final experiment showed that face recognition memory was not materially affected by a context manipulation: an old test picture was remembered at a level determined by its original depth of processing and independently of how it was tested-either alone, along side an old picture it had been studied with, or with a new picture.

- by Martin Karlin
- •
- Experimental Psychology, Research Methodology, Face Recognition, Recognition memory

Security has become a major issue globally and in order to manage the security challenges and reduce the security risks in the world, biometric systems such as face detection and recognition systems have been built. These systems are capable of providing biometric security, crime prevention and video surveillance services because of their inbuilt verification and identification capabilities(Hjelmas & Kee Low, 2001). This has become possible due to technological advancement in the fields of automated face analysis, machine learning and pattern recognition (Wojcik et al, 2016). In the paper, we review some biometric and facial recognition techniques.

- by Bayo Omoyiola
- •
- Information Security, Facial Recognition, Face Recognition, Biometrics

For many decades automatic facial expression recognition has scientifically been considered a real challenging problem in the fields of pattern recognition or robotic vision. The current research aims at proposing Relevance Vector Machines (RVM) as a novel classification technique for the recognition of facial expressions in static images. The aspects related to the use of Support Vector Machines are also presented. The data for testing were selected from the Cohn-Kanade Facial Expression Database. We report 90.84% recognition rates for RVM for six universal expressions based on a range of experiments. Some discussions on the comparison of different classification methods are included.

- by Dragos Datcu
- •
- Robot Vision, Pattern Recognition, Face Recognition, Support Vector Machines

Research in learning algorithms and sensor hardware has led to rapid advances in artificial systems over the past decade. However, their performance continues to fall short of the efficiency and versatility of human behavior. In many ways, a deeper understanding of how human perceptual systems process and act upon physical sensory information can contribute to the development of better artificial systems. In the presented research, we highlight how the latest tools in computer vision, computer graphics, and virtual reality technology can be used to systematically understand the factors that determine how humans perform in realistic scenarios of complex task-solving.

- by Lewis Chuang
- •
- Computer Vision, Face Recognition, Virtual Reality, Human behavior

Children and adults were tested on a forced-choice face recognition task in which the direction of eye gaze was manipulated over the course of the initial presentation and subsequent test phase of the experiment. To establish the effects of gaze direction on the encoding process, participants were presented with to-be-studied faces displaying either direct or deviated gaze (i.e. encoding manipulation). At test, all the faces depicted persons with their eyes closed. To investigate the effects of gaze direction on the efficiency of the retrieval process, a second condition (i.e. retrieval manipulation) was run in which target faces were presented initially with eyes closed and tested with either direct or deviated gaze. The results revealed the encoding advantages enjoyed by faces with direct gaze was present for both children and adults. Faces with direct gaze were also recognized better than faces with deviated gaze at retrieval, although this effect was most pronounced for adults. Finally, the advantage for direct gaze over deviated gaze at encoding was greater than the advantage for direct gaze over deviated gaze at retrieval. We consider the theoretical implications of these findings.

- by Bruce Hood
- •
- Psychology, Cognitive Science, Face Recognition, Linguistics

Several factors influence the reliability of eyewitness identification evidence. Typically, recognition for same-race faces is better than for different-race faces (the own-race bias), and alcohol intoxication decreases overall face recognition accuracy. This research investigated how alcohol intoxication influences the own-race bias. Asian and European participants completed tests of recognition memory for Asian and European faces when either mildly intoxicated (mean breath alcohol concentration of .05) or when sober. Compared to their sober counterparts, intoxicated participants showed a reduced own-race bias. Specifically, alcohol intoxication had a larger negative effect on the recognition of same-race faces compared to different-race faces. The legal and theoretical implications of these results are discussed.

- by Thomas Denson
- •
- Psychology, Cognitive Science, Law, Face Recognition
- by Romina Palermo
- •
- Psychology, Cognitive Science, Psychometrics, Face Recognition

Nonlinear transformation of one image plane relative to another by spatially constrained elastic matching of two pixel grids is proposed a s a t e chnique of measuring image similarity for the purpose of featureless face identi cation. The elastic matching algorithm is devised a s a c ombination of two dynamic programming procedures applied independently to each row and then to each column of the pixel grid. In contrast to the commonly adopted method o f m e asuring face image similarity based on the dynamic link architecture, the proposed method is non-iterative and it avoids image segmentation. Most importantly the method p r ovides the linear computational complexity with respect to the number of pixels without application of parallel computers.

- by A. Kopylov and +1
- •
- Computer Architecture, Computational Complexity, Pattern Recognition, Face Recognition

Evidence has indicated that the right frontal cortex is preferentially involved in self-face recognition. To test this further, we employed a face identification task and examined hand response differences (N=10). Pictures of famous faces were combined with pictures of the participants’ faces (self) and their co-workers’ faces (familiar). These images were presented as a ‘movie’ in which one face transformed

- by Alvaro Pascual-Leone
- •
- Psychology, Cognitive Science, Computer Graphics, Cognition

This paper presents a new scheme of face image feature extraction, namely, the two-dimensional Fisher linear discriminant. Experiments on the ORL and the UMIST face databases show that the new scheme outperforms the PCA and the conventional PCA + FLD schemes, not only in its computational efficiency, but also in its performance for the task of face recognition.

Recognition is a very effective area of research in regard of security with the involvement of biometric analysis, human computer interface and digital image processing. Humans inherently use faces to recognize individuals and similarly gestures are used in non-verbal communication to efficiently and effectively express thoughts. So, in order to migrate the natural means of communication by gesture into computer can setup a good move in making systems more interactive.

- by IJAERS Journal
- •
- Face Recognition, Matlab

Profile face silhouettes have recently been used to generate a behaviorally validated face space. An important method for studying perceptual spaces is the elicitation of aftereffects, shifts in perceptual judgments that occur after prolonged exposure to stimuli that occupy one locus in the perceptual space. Here we show that face silhouettes elicit gender aftereffects (changes in gender judgments following exposure to gendered faces) in a rapid, implicit adaptation paradigm. Further, we observe that these aftereffects persist across image transformations that preserve the perception of a silhouette as a face but not across transformations that disrupt it. Moreover, the aftereffects transfer between two-tone, profile-view silhouettes and gray-scale, front-view face photographs. Together these results suggest that gender processing occurs at a high level of visual representation and can be parametrically investigated within the silhouette face space methodology.

- by Nathan Witthoft and +1
- •
- Face Recognition, Face perception

Improving significantly in the last several years, technologies that can mimic or improve human abilities to recognize and read faces are now maturing for use in medical and security applications. The 2002 Face Recognition Vendor Test (FRVT 2002) demonstrated a significant improvement in face recognition capabilities, and researchers have developed systems to tackle some of face recognition's more interesting challenges. These systems include one that can distinguish between identical twins.

- by Ankit Rajput
- •
- Cognitive Science, Face Recognition