Analysis Of Facial Features Research Articles

Dissociable roles of internal feelings and face recognition ability in facial expression decoding

The problem of emotion recognition has been tackled by researchers in both affective computing and cognitive neuroscience. While affective computing relies on analyzing visual features from facial expressions, it has been proposed that humans recognize emotions by internally simulating the emotional states conveyed by others' expressions, in addition to perceptual analysis of facial features. Here we investigated whether and how our internal feelings contributed to the ability to decode facial expressions. In two independent large samples of participants, we observed that individuals who generally experienced richer internal feelings exhibited a higher ability to decode facial expressions, and the contribution of internal feelings was independent of face recognition ability. Further, using voxel-based morphometry, we found that the gray matter volume (GMV) of bilateral superior temporal sulcus (STS) and the right inferior parietal lobule was associated with facial expression decoding through the mediating effect of internal feelings, while the GMV of bilateral STS, precuneus, and the right central opercular cortex contributed to facial expression decoding through the mediating effect of face recognition ability. In addition, the clusters in bilateral STS involved in the two components were neighboring yet separate. Our results may provide clues about the mechanism by which internal feelings, in addition to face recognition ability, serve as an important instrument for humans in facial expression decoding.

A robust analysis, detection and recognition of facial features in 2.5D images

A robust technique for recognition of 3D faces which performs well with face images with various poses, expressions and occlusions. In this method, the face images represented in 3D mesh format are smoothed using trilinear interpolation and then converted to 2.5D image or range images. Nose-tip which is the most prominent feature on human face is detected first on the corner points selected by 3D Harris corner and curvedness at those corner points. K-Means clustering is applied to group those corner points in 2 groups. The cluster of points with larger curvedness values represents the possible locations of nose-tip. Nose-tip is finally localized using Mean-Gaussian curvature values of the prospective corner points in that cluster. Using the nose-tip location, other facial landmarks namely corners of the eyes and mouth are located and a facial graph is generated. The dimensionality of 2.5D feature space is that, depth values are stored at each (x, y) grid of the 2.5D image, so a 3D face image uses some function to map the depth value at any pixel position to the intensity with which that pixel will be displayed. Here finally extracted features for each subject is of dimensionality [1ź?ź21], taking into account the Euclidean distances in three dimensional form between each feature points detected automatically. Taking Euclidean distances between all pairs of landmark points as features, face images are classified using Multilayer Perceptron (MLP), as well as Support Vector Machines (SVM). Maximum recognition rates of 75 and 87.5 % have been obtained in case of Bosphorus Databases, 62.5 and 87.5 % in case of GavabDB databases, 75 and 87.5 % in case of Frav3D Databases by Multilayer Perceptron and Support Vector Machines respectively.

Analysis and Reliability Performance Comparison of Different Facial Image Features

This study performs reliability analysis on the different facial features with weighted retrieval accuracy on increasing facial database images. There are many methods analyzed in the existing papers with constant facial databases mentioned in the literature review. There were not much work carried out to study the performance in terms of reliability and also how the method will perform on increasing the size of the database. In this study certain feature extraction methods were analyzed on the regular performance measure and also the performance measures are modified to fit the real time requirements by giving weight ages for the closer matches. In this study four facial feature extraction methods are performed, they are DWT with PCA, LWT with PCA, HMM with SVD and Gabor wavelet with HMM. Reliability of these methods are analyzed and reported. Among all these methods Gabor wavelet with HMM gives more reliability than other three methods performed. Experiments are carried out to evaluate the proposed approach on the Olivetti Research Laboratory (ORL) face database.

Identification of unrecognizable corpses: A novel semi-automated approach for forensic facial reconstruction in Sri Lanka

Introduction : Identification of unrecognizable corpses is of high importance and when all other identification mechanisms fail, the process of forensic facial reconstruction has to be adopted. Objective: This process is still at its infancy in Sri Lanka and is yet to utilize the advanced technologies of other countries. Hence introducing a more efficient, semi-automated 3D Computer graphics based technique for the local forensic officials is the aim of this study. Method : A 3D model of the skull is captured and digitally sculpting facial muscles on the model with the aid of forensic facial markers. Different facial components were added to the completed face model in order to improve the identification process. Separate analyses were also conducted for both facial tissue thickness and facial component variations in Sri Lankans to achieve an improved result. Female cases of the age category 20-30/ medium weight were used in this study. Results: The analysis of the facial tissue thickness confirmed that tissue thickness data of other countries cannot be adopted for facial reconstruction in the local context. Sri Lankans have a different facial soft tissue thickness mainly in the following areas; Gonion, Sub M2, Supra M2 and the area beneath the chin. The facial feature analysis discovered the mean values of the nasal and eye indexes which were then modeled in to the final output. The outputs were thoroughly evaluated using a number of techniques. Conclusion : By adopting the suggested novel application based on the evaluation results and the cost analysis, establishing the first unit for facial reconstruction in Sri Lanka would be highly recommended to uphold the rights of deceased and relatives concerned. Medico-Legal Journal of Sri Lanka 2013; 1(2) : 10-22

The perception of a familiar face is no more than the sum of its parts

Why do faces become easier to recognize with repeated exposure? Previous research has suggested that familiarity may induce a qualitative shift in visual processing from an independent analysis of individual facial features to analysis that includes information about the relationships among features (Farah, Wilson, Drain, & Tanaka Psychological Review, 105, 482-498, 1998; Maurer, Grand, & Mondloch Trends in Cognitive Science, 6, 255-260, 2002). We tested this idea by using a "summation-at-threshold" technique (Gold, Mundy, & Tjan Psychological Science, 23, 427-434, 2012; Nandy & Tjan Journal of Vision, 8, 3.1-20, 2008), in which an observer's ability to recognize each individual facial feature shown independently is used to predict their ability to recognize all of the features shown in combination. We find that, although people are better overall at recognizing familiar as opposed to unfamiliar faces, their ability to integrate information across features is similar for unfamiliar and highly familiar faces and is well predicted by their ability to recognize each of the facial features shown in isolation. These results are consistent with the idea that familiarity has a quantitative effect on the efficiency with which information is extracted from individual features, rather than a qualitative effect on the process by which features are combined.

Developmental trajectories of cortical–subcortical interactions underlying the evaluation of trust in adolescence

Social decision making is guided by the ability to intuitively judge personal attributes, including analysis of facial features to infer the trustworthiness of others. Although the neural basis for trustworthiness evaluation is well characterized in adults, less is known about its development during adolescence. We used event-related functional magnetic resonance imaging to examine age-related changes in neural activation and functional connectivity during the evaluation of trust in faces in a sample of adolescent females. During scanning, participants viewed masked presentations of faces and rated their trustworthiness. Parametric modeling of trust ratings revealed enhanced activation in amygdala and insula to untrustworthy faces, effects which peaked during mid-adolescence. Analysis of amygdala functional connectivity demonstrated enhanced amygdala-insula coupling during the evaluation of untrustworthy faces. This boost in connectivity was attenuated during mid-adolescence, suggesting a functional transition within face-processing circuits. Together, these findings underscore adolescence as a period of reorganization in neural circuits underlying socioemotional behavior.

A novel semi-automated approach for forensic facial reconstruction in Sri Lanka

Introduction: It should be regarded that being buried in accordance with one’s religion and traditions in a grave that bears one's own name a human right. Thus with regard to unrecognizable corpses its identification is of high importance and when all other identification mechanisms fail, the process of forensic facial reconstruction has to be adopted. Objective: Introduction of a more efficient, semi-automated 3D Computer graphics based technique of facial reconstruction was the aim of this study. Method: The process involved capturing a 3D model of the skull and digitally sculpting facial muscles on the model with the aid of forensic facial markers. Different facial components were added to the completed face model in order to improve the identification process. Separate analyses were also conducted for both facial tissue thickness and facial component variations in Sri Lankans to achieve an improved result. Females of the age category 20-30 of average weight were used in this study. Results: The facial tissue thickness analysis conducted by the research team confirmed that tissue thickness data of other countries cannot be adopted for facial reconstruction in the local context and that Sri Lankans have a different facial soft tissue thickness mainly in the following areas; Gonion, Sub M2, Supra M2 and the area beneath the chin. The facial feature analysis discovered the mean values of the nasal and eye indexes which were then modeled in to the final output. The outputs were thoroughly evaluated using a number of techniques. Conclusion: Based on the evaluation results and the cost analysis, adopting the suggested novel application and establishing the first unit for facial reconstruction in Sri Lanka to uphold the rights of deceased and their relatives would be highly recommended. Galle Medical Journal, Vol 18: No. 1, March 2013:Page 16-25 DOI: http://dx.doi.org/10.4038/gmj.v18i1.5517

Decoding face categories in diagnostic subregions of primary visual cortex

Higher visual areas in the occipitotemporal cortex contain discrete regions for face processing, but it remains unclear if V1 is modulated by top-down influences during face discrimination, and if this is widespread throughout V1 or localized to retinotopic regions processing task-relevant facial features. Employing functional magnetic resonance imaging (fMRI), we mapped the cortical representation of two feature locations that modulate higher visual areas during categorical judgements – the eyes and mouth. Subjects were presented with happy and fearful faces, and we measured the fMRI signal of V1 regions processing the eyes and mouth whilst subjects engaged in gender and expression categorization tasks. In a univariate analysis, we used a region-of-interest-based general linear model approach to reveal changes in activation within these regions as a function of task. We then trained a linear pattern classifier to classify facial expression or gender on the basis of V1 data from ‘eye’ and ‘mouth’ regions, and from the remaining non-diagnostic V1 region. Using multivariate techniques, we show that V1 activity discriminates face categories both in local ‘diagnostic’ and widespread ‘non-diagnostic’ cortical subregions. This indicates that V1 might receive the processed outcome of complex facial feature analysis from other cortical (i.e. fusiform face area, occipital face area) or subcortical areas (amygdala).

안면형상을 활용한 사상체질 진단 연구에 관한 체계적 고찰

Objectives : This study proposes developing Sasang Medical Diagnosis Program using Facial form for increase in Sasang Constitution Diagnosis objectivity and putting the Diagnosis Program into practical use. The author presents a review of extant research on Sasang constitution diagnosis utilizing facial feature analysis and suggests an agenda for further research. Methods : For this thesis, a collection of dissertations on the subject of 'Usage of facial form for constitution diagnosis' published until September of 2012 such as RISS4U, OASIS, KISTI, Korean TK were reviewed. The final 33 dissertations were classified into two categories, basic or clinical research and then analyzed. Results : 9 out of 33 dissertations were of basic research and 24 were of clinical research. 1) As result of review of references, a uniform tendency was found in facial form according to Sasang Constitution. 2) In the grade of practical use, facial element is repeatedly used and the facial element of important use has constitutional differences. 3) Standard faces per Sasang Constitution were derived as result of 2-dimensional research. 4) 3-dimensional research focused on improvement of accuracy and reliability of 3D-AFRA, and there has been an attempt to develop a prototype for identification. Conclusions : For practical use of facial feature in Sasang Constitution Diagnosis, 1) Standardization of diagnosis through establishing Sasang Medical Diagnosis clinical protocol must be preceded. After the standardization, practical purpose and direction of facial form in general may be decided. 2) Information on high quality facial form of constitutional and conditional patients must be collected to form extensive database. 3) Subdivided symptomatology, as well as Sasang Constitution must be considered for diagnosis in order for diagnosis technique to acquire clinical practicality.

Analysis of Sasang constitutional types using facial features with compensation for photographic distance

BackgroundFacial features are regarded as representative and reliable characteristics for diagnosing a person's Sasang Constitution (SC). However, the description of these features tends to depend on the interpretation and the opinion of the doctor that follows the SC approach. In this paper, we performed a facial feature analysis of SC types in an objective and quantitative manner. Here, site-to-site variability can be an obstacle to properly analyzing facial features when images are taken from various sites, which may have different experimental environments. A compensation technique to reduce the site-to-site variability was proposed before performing the feature analysis. MethodsThe frontal and profile images of 1464 patients recruited from various oriental medical clinics (19 sites) were used. Candidate feature variables were created, which were inspired by the facial characteristics of the SC types described in the Sasang constitutional medicine literature. To resolve the problems involved in processing data collected from various sites with heterogeneous experimental environments, a compensation technique was proposed. Statistical analysis techniques were employed to observe the differences among the SC types and to demonstrate how effectively the site-to-site variability was reduced. ResultsThe facial features that were significant for diagnosing the SC types were identified by a statistical analysis, and it was verified that the compensation technique reduced the site-to-site variability produced by the differences in photographic distance. ConclusionIt is noted that the significant facial features represent common characteristics of each SC type in the sense that we collected extensive opinions from many Sasang constitutional medicine doctors with various points of view. Additionally, a compensation method for the photographic distance is needed to find the significant facial features. We expect these findings and the related compensation technique to contribute to establishing a scientific basis for the precise diagnosis of SC types in clinical practice.

An efficient illumination invariant face recognition framework via illumination enhancement and DD-DT[formula omitted]WT filtering

In this paper, it is shown that multiscale analysis of facial structure and features of face images leads to superior recognition rates for images under varying illumination. The proposed method, which is computationally cost effective, significantly suppresses illumination effects. The problem is defined as how better to extract the reflectance portion from a given image. This can be used directly as an input to a dimensionality reduction unit followed by a classifier for recognition purposes. We first assume that an image I(x,y) is a black box consisting of a combination of illumination and reflectance. A new approximation is proposed to enhance the illumination removal phase. As illumination resides in the low-frequency part of image, it is reasonable to consider the use of a high-performance multiresolution transformation to first accurately separate the frequency components of an image. The double-density dual-tree complex wavelet transform (DD-DTCWT), possesses three core advantages, i.e., the transformation is (i) shift-invariant, (ii) directionally selective with no checkerboard effect, (iii) enriched by extra wavelets interpreted as double-density. The output of the first phase is sent to a DD-DTCWT unit to be decomposed into frequency subbands. High-frequency subbands are thresholded and an inverse DD-DTCWT is then applied to subbands to construct a low-frequency raw image, which is followed by a fine-tuning process. Finally, after extracting a mask, feature vector is formed and the principal component analysis (PCA) is used for dimensionality reduction which is then proceeded by the extreme learning machine (ELM) as a classifier to evaluate the performance of the proposed algorithm for face recognition under varying illumination. Unlike similar works, the proposed method is free of any prior information about the face shape, it is systematic and easy to implement, and it can be applied separately on each image. Furthermore, the proposed method which is significantly faster than similar techniques presents a robust behavior against the reduction in the number of images required for the training cycle. Several experiments are performed employing the available well-known databases such as the Yale B, Extended-Yale B, CMU-PIE, FERET, AT&T, and the Labeled Faces in the Wild (LFW). Illustrative examples are given and the results compare favorably to the current results in the literature.

Alagille syndrome in a Vietnamese cohort: Mutation analysis and assessment of facial features

Alagille syndrome (ALGS, OMIM #118450) is an autosomal dominant disorder that affects multiple organ systems including the liver, heart, eyes, vertebrae, and face. ALGS is caused by mutations in one of two genes in the Notch Signaling Pathway, Jagged1 (JAG1) or NOTCH2. In this study, analysis of 21 Vietnamese ALGS individuals led to the identification of 19 different mutations (18 JAG1 and 1 NOTCH2), 17 of which are novel, including the third reported NOTCH2 mutation in Alagille Syndrome. The spectrum of JAG1 mutations in the Vietnamese patients is similar to that previously reported, including nine frameshift, three missense, two splice site, one nonsense, two whole gene, and one partial gene deletion. The missense mutations are all likely to be disease causing, as two are loss of cysteines (C22R and C78G) and the third creates a cryptic splice site in exon 9 (G386R). No correlation between genotype and phenotype was observed. Assessment of clinical phenotype revealed that skeletal manifestations occur with a higher frequency than in previously reported Alagille cohorts. Facial features were difficult to assess and a Vietnamese pediatric gastroenterologist was only able to identify the facial phenotype in 61% of the cohort. To assess the agreement among North American dysmorphologists at detecting the presence of ALGS facial features in the Vietnamese patients, 37 clinical dysmorphologists evaluated a photographic panel of 20 Vietnamese children with and without ALGS. The dysmorphologists were unable to identify the individuals with ALGS in the majority of cases, suggesting that evaluation of facial features should not be used in the diagnosis of ALGS in this population. This is the first report of mutations and phenotypic spectrum of ALGS in a Vietnamese population.

Processing social aspects of human gaze: A combined fMRI-DTI study

Human gaze is a critical social cue that can reveal intentions and dispositions of others. The right posterior superior temporal sulcus (pSTS) is thought to be critically involved in processing eye gaze information. We combined diffusion tensor imaging (DTI) and functional magnetic resonance imaging (fMRI) to identify direct neural connections of right pSTS and to determine how these connections are modulated by the social significance of perceived gaze shifts. Participants saw faces with direct or averted gaze during event-related fMRI. Half of these faces remained static, and half displayed a dynamic gaze shift either towards or away from the subject. Social attention (dynamic gaze shifts towards the observer) not only increased activity in right pSTS, but also its functional connectivity with the right anterior insula (aIns) and right fusiform gyrus (FG). However, direct fiber connections from pSTS were demonstrated by DTI for the right aIns, but not the right FG. Moreover, the right FG responded to eye motion irrespective of direction and social significance; whereas the right aIns was selectively sensitive to social significance (i.e. gaze shifts towards the observer), but not generally to eye motion. We conclude that the social aspects of mutual gaze contact are processed by direct fiber pathways between right pSTS and right aIns; whereas increased connectivity with FG could reflect an enhanced perceptual analysis of changing facial features in dynamic gaze conditions and involves indirect fiber pathways with pSTS, perhaps via motion-selective regions in middle temporal (MT) gyrus that exhibited strong white-matter connections with both pSTS and FG and could thus provide inputs to these two areas.

1-6 顔特徴の解析と言葉による記述(第1部門 メディア処理1)

1-6 顔特徴の解析と言葉による記述(第1部門 メディア処理1)

Who can you trust? Behavioral and neural differences between perceptual and memory-based influences

Decisions about whether to trust someone can be influenced by competing sources of information, such as analysis of facial features versus remembering specific information about the person. We hypothesized that such sources can differentially influence trustworthiness judgments depending on the circumstances in which judgments are made. In our experiments, subjects first learned face-word associations. Stimuli were trustworthy and untrustworthy faces, selected on the basis of consensus judgments, and personality attributes that carried either the same valence (consistent with face) or the opposite valence (inconsistent with face). Subsequently, subjects rated the trustworthiness of each face. Both learned and perceptual information influenced ratings, but learned information was less influential under speeded than under non-speeded conditions. EEG data further revealed neural evidence of the processing of these two competing sources. Perceptual influences were apparent earlier than memory influences, substantiating the conclusion that time pressure can selectively disrupt memory retrieval relevant to trustworthiness attributions.

Face to Face: Anthropometry-Based Interactive Face Shape Modeling Using Model Priors

This paper presents a new anthropometrics-based method for generating realistic, controllable face models. Our method establishes an intuitive and efficient interface to facilitate procedures for interactive 3D face modeling and editing. It takes 3D face scans as examples in order to exploit the variations presented in the real faces of individuals. The system automatically learns a model prior from the data-sets of example meshes of facial features using principal component analysis (PCA) and uses it to regulate the naturalness of synthesized faces. For each facial feature, we compute a set of anthropometric measurements to parameterize the example meshes into a measurement space. Using PCA coefficients as a compact shape representation, we formulate the face modeling problem in a scattered data interpolation framework which takes the user-specified anthropometric parameters as input. Solving the interpolation problem in a reduced subspace allows us to generate a natural face shape that satisfies the user-specified constraints. At runtime, the new face shape can be generated at an interactive rate. We demonstrate the utility of our method by presenting several applications, including analysis of facial features of subjects in different race groups, facial feature transfer, and adapting face models to a particular population group.

Feature Selection from a Facial Image for Distinction of Sasang Constitution

Recently, oriental medicine has received attention for providing personalized medicine through consideration of the unique nature and constitution of individual patients. With the eventual goal of globalization, the current trend in oriental medicine research is the standardization by adopting western scientific methods, which could represent a scientific revolution. The purpose of this study is to establish methods for finding statistically significant features in a facial image with respect to distinguishing constitution and to show the meaning of those features. From facial photo images, facial elements are analyzed in terms of the distance, angle and the distance ratios, for which there are 1225, 61 250 and 749 700 features, respectively. Due to the very large number of facial features, it is quite difficult to determine truly meaningful features. We suggest a process for the efficient analysis of facial features including the removal of outliers, control for missing data to guarantee data confidence and calculation of statistical significance by applying ANOVA. We show the statistical properties of selected features according to different constitutions using the nine distances, 10 angles and 10 rates of distance features that are finally established. Additionally, the Sasang constitutional meaning of the selected features is shown here.

Developmental prosopagnosia: A case analysis and treatment study

This paper reports a treatment case study focused on face perception impairments designed for AL, an 8-year-old child with prosopagnosia. AL's prosopagnosia was characterized by deficits at the level of structural encoding—that is, he was unable to achieve normal basic perception of faces. This impairment then impacted on all subsequent aspects of familiar- and unfamiliar-face processing. Detailed assessment of feature processing revealed impairments in perception of facial features with a dissociation between relatively good perception of the mouth feature and poor perception of eye and nose features. Interestingly, results also suggested at least partial internal representation of facial features despite long-standing deficits in perception of these features. A treatment programme focused on training in perception, and analysis of facial features and familiar-face naming was conducted. Treatment resulted in excellent face naming for familiar faces, a decreased reliance on nonfacial cues and a reduction in AL's tendency to misidentify unfamiliar faces as family members.

A statistical model for synthesis of detailed facial geometry

Detailed surface geometry contributes greatly to the visual realism of 3D face models. However, acquiring high-resolution face geometry is often tedious and expensive. Consequently, most face models used in games, virtual reality, or computer vision look unrealistically smooth. In this paper, we introduce a new statistical technique for the analysis and synthesis of small three-dimensional facial features, such as wrinkles and pores. We acquire high-resolution face geometry for people across a wide range of ages, genders, and races. For each scan, we separate the skin surface details from a smooth base mesh using displaced subdivision surfaces. Then, we analyze the resulting displacement maps using the texture analysis/synthesis framework of Heeger and Bergen, adapted to capture statistics that vary spatially across a face. Finally, we use the extracted statistics to synthesize plausible detail on face meshes of arbitrary subjects. We demonstrate the effectiveness of this method in several applications, including analysis of facial texture in subjects with different ages and genders, interpolation between high-resolution face scans, adding detail to low-resolution face scans, and adjusting the apparent age of faces. In all cases, we are able to re-produce fine geometric details consistent with those observed in high resolution scans.

Efficient ocular expression analysis for synthetic reproduction

This paper presents an original framework that analyzes the complete ocular (eye + eyebrow) expression on video sequences to reproduce it later on synthetic three-dimensional (3-D) models in real-time. We propose a two step process to develop robust techniques for facial feature analysis aimed at working without special illumination conditions or physical constraints on the user (markers, fixed frontal pose, etc.). First, simple and efficient image-processing methods based on motion models are designed over a frontal point of view of the face. Natural and realistic intra-feature and inter-feature constraints are applied to improve the analysis results. Then, the usability of these algorithms is extended to enable the analysis regardless of the person's pose in front of the camera. This is achieved by redefining the motion models involved over the speaker's highly realistic synthetic representation (clone), by using a suitable observation model, and by predicting the head pose in 3-D, frame by frame.