Face Shape Research Articles

Gender Classification Based on Fingerprint Analysis

Gender classification plays an active role in several applications such as biometrics, criminology,surveillance, human computer interaction, commercial profiling. Though bbiometric traits such as face, gait, iris and hand shape are used for gender classification in the past, majority of the work is based on face as it contains more prominent features than others. In this paper we have analyzed fingerprints for gender classification with a hope that it has great potential for future research. We have employed a three convolutional layer CNN with rectified linear (ReLu) and tanh activation functions on NIST database which contains a set of 4000 images and achieved 99% accuracy. Performance of the proposed system demonstrated that fingerprints contains vital features to discriminate gender of a person.

Integrated Multi-Model Face Shape and Eye Attributes Identification for Hair Style and Eyelashes Recommendation

Identifying human face shape and eye attributes is the first and most vital process before applying for the right hairstyle and eyelashes extension. The aim of this research work includes the development of a decision support program to constitute an aid system that analyses eye and face features automatically based on the image taken from a user. The system suggests a suitable recommendation of eyelashes type and hairstyle based on the automatic reported users’ eye and face features. To achieve the aim, we develop a multi-model system comprising three separate models; each model targeted a different task, including; face shape classification, eye attribute identification and gender detection model. Face shape classification system has been designed based on the development of a hybrid framework of handcrafting and learned feature. Eye attributes have been identified by exploiting the geometrical eye measurements using the detected eye landmarks. Gender identification system has been realised and designed by implementing a deep learning-based approach. The outputs of three developed models are merged to design a decision support system for haircut and eyelash extension recommendation. The obtained detection results demonstrate that the proposed method effectively identifies the face shape and eye attributes. Developing such computer-aided systems is suitable and beneficial for the user and would be beneficial to the beauty industrial.

Real-time face view correction for front-facing cameras

Face views are particularly important in person-to-person communication. Differenes between the camera location and the face orientation can result in undesirable facial appearances of the participants during video conferencing. This phenomenon is particularly noticeable when using devices where the front-facing camera is placed in unconventional locations such as below the display or within the keyboard. In this paper, we take a video stream from a single RGB camera as input, and generate a video stream that emulates the view from a virtual camera at a designated location. The most challenging issue in this problem is that the corrected view often needs out-of-plane head rotations. To address this challenge, we reconstruct the 3D face shape and re-render it into synthesized frames according to the virtual camera location. To output the corrected video stream with natural appearance in real time, we propose several novel techniques including accurate eyebrow reconstruction, high-quality blending between the corrected face image and background, and template-based 3D reconstruction of glasses. Our system works well for different lighting conditions and skin tones, and can handle users wearing glasses. Extensive experiments and user studies demonstrate that our method provides high-quality results.

Optimal feature selection with hybrid classification for automatic face shape classification using fitness sorted Grey wolf update

Depending on the prevailing researches, the classification of face shapes could be deployed for numerous applications. This paper intends to develop a new method for face shape classification using intelligent approaches. The presented method includes three stages namely, (i) Face Detection (ii) Pre-processing (iii) Feature extraction (iv) Classification. The face detection process is used for identifying the most significant objects in the face, probably eyes, nose, etc. which is done using the Viola-Jones algorithm. Moreover, the pre-processing stage includes the Histogram Equalization (HE) model for enhancing the contrast of the image. The classification of face shapes is performed by a hybrid classifier that links Convolutional Neural Network (CNN) and Neural Network (NN). For performing the CNN-based classification, the images are directly given as input. On the other hand, NN-based classification requires features as input. Hence, the pre-processed image is again subjected to the feature extraction process, where the features are extracted using the Active Appearance Model (AAM) and the Active Shape Model (ASM). For reducing the length of extracted features, the optimal feature selection process is adopted, which is done by improved Grey Wolf Optimization (GWO) algorithm. As the main contribution, the features, number of hidden neurons in the convolutional layer of CNN, and training of NN (weight update) is optimally chosen by improved GWO so-called as Fitness Sorted Grey Wolf Update (FS-GU) model. Finally, the average of two outcomes from both CNN, and NN provides the classified five categories of face shapes like heart, oblong, oval, round, and square. The performance of the proposed classification model is finally validated by comparing over the conventional models by analyzing the relevant performance metrics.

Association between shape changes and bone remodeling patterns in the middle face during ontogeny in South American populations

The morphology of facial bones is modeled by processes of bone formation and resorption induced by interactions between tissues and compensatory responses. However, the role of remodeling patterns on the morphological changes within and among populations has been scarcely explored. Here, we assess the association between facial shape and the underlying bone cell activity throughout the ontogeny in two Amerindian populations that represent the extremes of craniofacial variation in South America. The sample comprises 71 individuals (36 adults and 35 subadults) representing hunter-gatherers from Patagonia and horticulturists from Northwest Argentina. We analyzed the shape and size of the zygomatic and the maxilla, and compared them with the patterns of bone formation and resorption. Bone formation and resorption were described by quantitative histological analysis of bone surfaces. Morphological changes were described by landmarks and semilandmarks digitized on 3D surfaces obtained from CT images. The results from multivariate statistics analysis show that the patterns of bone remodeling are associated with variation in the morphology of the middle face. We found a similar pattern of facial shape variation along the ontogenetic trajectory in the two samples, and a similar trend in the amount of formation and resorption activities across ages. The main differences between samples were found in the distribution of the areas of bone formation and resorption, possibly associated with mechanical bone response to masticatory loading. These findings provide clues about the processes and mechanisms of bone development involved in the facial morphological differentiation in human populations from southern South America.

Functional ecological convergence between the thylacine and small prey-focused canids

BackgroundMorphological convergence is a fundamental aspect of evolution, allowing for inference of the biology and ecology of extinct species by comparison with the form and function of living species as analogues. The thylacine (Thylacinus cynocephalus), the iconic recently extinct marsupial, is considered a classic example of convergent evolution with the distantly related placental wolf or dog, though almost nothing is actually known regarding its ecology. This lack of data leads to questions regarding the degree of convergence with, and the similarity of, the functional ecology of the thylacine and the wolf/dog. Here, we examined the cranium of the thylacine using 3D geometric morphometrics and two quantitative tests of convergence to more precisely determine convergent analogues, within a phylogenetically informed dataset of 56 comparative species across 12 families of marsupial and placental faunivorous mammals. Using this dataset, we investigated patterns of correlation between cranial shape and diet, phylogeny, and relative prey size across these terrestrial faunivores.ResultsWe find a correlation between cranial, facial, and neurocranial shape and the ratio of prey-to-predator body mass, though neurocranial shape may not correlate with prey size within marsupials. The thylacine was found to group with predators that routinely take prey smaller than 45% of their own body mass, not with predators that take subequal-sized or larger prey. Both convergence tests find significant levels of convergence between the thylacine and the African jackals and South American ‘foxes’, with lesser support for the coyote and red fox. We find little support for convergence between the thylacine and the wolf or dog.ConclusionsOur study finds little support for a wolf/dog-like functional ecology in the thylacine, with it instead being most similar to mid-sized canids such as African jackals and South American ‘foxes’ that mainly take prey less than half their size. This work suggests that concepts of convergence should extend beyond superficial similarity, and broader comparisons can lead to false interpretations of functional ecology. The thylacine was a predator of small to mid-sized prey, not a big-game specialist like the placental wolf.

Does Head Orientation Influence 3D Facial Imaging? A Study on Accuracy and Precision of Stereophotogrammetric Acquisition.

This study investigates the reliability and precision of anthropometric measurements collected from 3D images and acquired under different conditions of head rotation. Various sources of error were examined, and the equivalence between craniofacial data generated from alternative head positions was assessed. 3D captures of a mannequin head were obtained with a stereophotogrammetric system (Face Shape 3D MaxiLine). Image acquisition was performed with no rotations and with various pitch, roll, and yaw angulations. On 3D images, 14 linear distances were measured. Various indices were used to quantify error magnitude, among them the acquisition error, the mean and the maximum intra- and inter-operator measurement error, repeatability and reproducibility error, the standard deviation, and the standard error of errors. Two one-sided tests (TOST) were performed to assess the equivalence between measurements recorded in different head angulations. The maximum intra-operator error was very low (0.336 mm), closely followed by the acquisition error (0.496 mm). The maximum inter-operator error was 0.532 mm, and the highest degree of error was found in reproducibility (0.890 mm). Anthropometric measurements from alternative acquisition conditions resulted in significantly equivalent TOST, with the exception of Zygion (l)–Tragion (l) and Cheek (l)–Tragion (l) distances measured with pitch angulation compared to no rotation position. Face Shape 3D Maxiline has sufficient accuracy for orthodontic and surgical use. Precision was not altered by head orientation, making the acquisition simpler and not constrained to a critical precision as in 2D photographs.

Human emotion recognition based on facial expressions via deep learning on high-resolution images

Detecting human emotion based on facial expression is considered a hard task for the computer vision community because of many challenges such as the difference of face shape from a person to another, difficulty of recognition of dynamic facial features, low quality of digital images, etc. In this paper, we propose a face-sensitive convolutional neural network (FS-CNN) for human emotion recognition. The proposed FS-CNN is used to detect faces on large scale images then analyzing face landmarks to predict expressions for emotion recognition. The FS-CNN is composed form two stages, patch cropping, and convolutional neural networks. The first stage is used to detect faces in high-resolution images and crop the face for further processing. The second stage is a convolutional neural network used to predict facial expression based on landmarks analytics, it was applied on pyramid images to process scale invariance. The proposed FS-CNN was trained and evaluated on the UMD Faces dataset. High performance was achieved with a mean average precision of about 95%.

Respiratory adaptation to climate in modern humans and Upper Palaeolithic individuals from Sungir and Mlade\u010d

As our human ancestors migrated into Eurasia, they faced a considerably harsher climate, but the extent to which human cranial morphology has adapted to this climate is still debated. In particular, it remains unclear when such facial adaptations arose in human populations. Here, we explore climate-associated features of face shape in a worldwide modern human sample using 3D geometric morphometrics and a novel application of reduced rank regression. Based on these data, we assess climate adaptations in two crucial Upper Palaeolithic human fossils, Sungir and Mladeč, associated with a boreal-to-temperate climate. We found several aspects of facial shape, especially the relative dimensions of the external nose, internal nose and maxillary sinuses, that are strongly associated with temperature and humidity, even after accounting for autocorrelation due to geographical proximity of populations. For these features, both fossils revealed adaptations to a dry environment, with Sungir being strongly associated with cold temperatures and Mladeč with warm-to-hot temperatures. These results suggest relatively quick adaptative rates of facial morphology in Upper Palaeolithic Europe.

Landmark Detection and 3D Face Reconstruction for Caricature using a Nonlinear Parametric Model

Caricature is an artistic abstraction of the human face by distorting or exaggerating certain facial features, while still retains a likeness with the given face. Due to the large diversity of geometric and texture variations, automatic landmark detection and 3D face reconstruction for caricature is a challenging problem and has rarely been studied before. In this paper, we propose the first automatic method for this task by a novel 3D approach. To this end, we first build a dataset with various styles of 2D caricatures and their corresponding 3D shapes, and then build a parametric model on vertex based deformation space for 3D caricature face. Based on the constructed dataset and the nonlinear parametric model, we propose a neural network based method to regress the 3D face shape and orientation from the input 2D caricature image. Ablation studies and comparison with state-of-the-art methods demonstrate the effectiveness of our algorithm design. Extensive experimental results demonstrate that our method works well for various caricatures. Our constructed dataset, source code and trained model are available at https://github.com/Juyong/CaricatureFace.

Shared heritability of human face and brain shape.

Evidence from model organisms and clinical genetics suggests coordination between the developing brain and face, but the role of this link in common genetic variation remains unknown. We performed a multivariate genome-wide association study (GWAS) of cortical surface morphology in 19,644 European-ancestry individuals, identifying 472 genomic loci influencing brain shape, of which 76 are also linked to facial shape. Shared loci include transcription factors involved in craniofacial development, as well as members of signaling pathways implicated in brain-face crosstalk. Brain shape heritability is equivalently enriched near regulatory regions active in either forebrain organoids or facial progenitors. However, we do not detect significant overlap between shared brain-face GWAS signals and variants affecting behavioral-cognitive traits. These results suggest that early in embryogenesis, the face and brain mutually shape each other through both structural effects and paracrine signaling, but this interplay may not impact later brain development associated with cognitive function.

Facial Expression Recognition with Identity and Emotion Joint Learning

Different subjects may express a specific expression in different ways due to inter-subject variabilities. In this work, besides training deep-learned facial expression feature (emotional feature), we also consider the influence of latent face identity feature such as the shape or appearance of face. We propose an identity and emotion joint learning approach with deep convolutional neural networks (CNNs) to enhance the performance of facial expression recognition (FER) tasks. First, we learn the emotion and identity features separately using two different CNNs with their corresponding training data. Second, we concatenate these two features together as a deep-learned Tandem Facial Expression (TFE) Feature and feed it to the subsequent fully connected layers to form a new model. Finally, we perform joint learning on the newly merged network using only the facial expression training data. Experimental results show that our proposed approach achieves 99.31 and 84.29 percent accuracy on the CK+ and the FER+ database, respectively, which outperforms the residual network baseline as well as many other state-of-the-art methods.

Race Detection using Mutated Salp Swarm Optimization Algorithm based DBN from Face Shape Features

Race Detection using Mutated Salp Swarm Optimization Algorithm based DBN from Face Shape Features

Wnt Signaling Drives Correlated Changes in Facial Morphology and Brain Shape.

Canonical Wnt signaling plays multiple roles critical to normal craniofacial development while its dysregulation is known to be involved in structural birth defects of the face. However, when and how Wnt signaling influences phenotypic variation, including those associated with disease, remains unclear. One potential mechanism is via Wnt signaling’s role in the patterning of an early facial signaling center, the frontonasal ectodermal zone (FEZ), and its subsequent regulation of early facial morphogenesis. For example, Wnt signaling may directly alter the shape and/or magnitude of expression of the sonic hedgehog (SHH) domain in the FEZ. To test this idea, we used a replication-competent avian sarcoma retrovirus (RCAS) encoding Wnt3a to modulate its expression in the facial mesenchyme. We then quantified and compared ontogenetic changes in treated to untreated embryos in the three-dimensional (3D) shape of both the SHH expression domain of the FEZ, and the morphology of the facial primordia and brain using iodine-contrast microcomputed tomography imaging and 3D geometric morphometrics (3DGM). We found that increased Wnt3a expression in early stages of head development produces correlated variation in shape between both structural and signaling levels of analysis. In addition, altered Wnt3a activation disrupted the integration between the forebrain and other neural tube derivatives. These results show that activation of Wnt signaling influences facial shape through its impact on the forebrain and SHH expression in the FEZ, and highlights the close relationship between morphogenesis of the forebrain and midface.

A New Hybrid Technique for Face Identification Based on Facial Parts Moments Descriptors

Robust facial feature extraction is an effective and important process for face recognition and identification system. The facial features should be invariant to scaling, translation, illumination and rotation, several feature extraction techniques may be used to increase the recognition accuracy. This paper inspects three-moment invariants techniques and then determines how is influenced by the variation which may happen to the various shapes of the face (globally and locally) Globally means the whole face shapes and locally means face part's shape (right eye, left eye, mouth, and nose). The proposed technique is tested using CARL database images. The proposal method of the new method that collects the robust features of each method is trained by a feed-forward neural network. The result has been improved and achieved an accuracy of 99.29%.

Preference of eyebrow apex positions on different facial shapes in Malaysian population: An inter‐ethnic study

Eyebrows are an important esthetic feature of the face. In cosmetic surgery, knowledge about the patient's preference of eyebrow apex position is important to achieve agreeable esthetic results. To study the preference of eyebrow apex positions on the different facial shapes in the Malaysian population. A frontal view photograph of a female model was morphed into oval, square, round, and long facial shapes. Four types of brow apex were created on each facial shape, A. above the midpupil (A-MP), B. above the lateral limbus (A-LL), C. halfway between the lateral limbus and lateral canthus (A-HF) and D. above the lateral canthus (A-LC). Out of the four brow apexes, the respondent selected one esthetically appealing brow apex for each facial shape. A total of 441 Malaysians completed the survey questionnaire. Differences in preference between the ethnic groups were analyzed by the chi-square test. The majority of Malaysian Chinese (MC) and Malaysian Indians (MI) subjects found A-LL as attractive on the oval (MC-73%, MI-52%), square (MC-42%, MI-42%), round (MC-45%, MI-40%) and long (MC-39%, MI-44%) shape, but the Malaysian Malays preferred more the A-HF on long (42%) and round (42%) face. While the Malaysian Indians least preferred the A-MP on the oval (4%), square (5%), round (6%), and long (5%). A significant difference in preference of apex position was observed between MC versus MI and MC versus MM in both oval and square faces. On the round face, the difference was noted between all the ethnic groups. However, on the long face, a significant difference was noted only between MI and MM. Significant interethnic differences exist in the preference of eyebrow apex position on the facial shapes.

How and why patterns of sexual dimorphism in human faces vary across the world

Sexual selection, including mate choice and intrasexual competition, is responsible for the evolution of some of the most elaborated and sexually dimorphic traits in animals. Although there is sexual dimorphism in the shape of human faces, it is not clear whether this is similarly due to mate choice, or whether mate choice affects only part of the facial shape difference between men and women. Here we explore these questions by investigating patterns of both facial shape and facial preference across a diverse set of human populations. We find evidence that human populations vary substantially and unexpectedly in both the magnitude and direction of facial sexually dimorphic traits. In particular, European and South American populations display larger levels of facial sexual dimorphism than African populations. Neither cross-cultural differences in facial shape variation, sex differences in body height, nor differing preferences for facial femininity and masculinity across countries, explain the observed patterns of facial dimorphism. Altogether, the association between sexual shape dimorphism and attractiveness is moderate for women and weak (or absent) for men. Analysis that distinguishes between allometric and non-allometric components reveals that non-allometric facial dimorphism is preferred in women’s faces but not in faces of men. This might be due to different regimes of ongoing sexual selection acting on men, such as stronger intersexual selection for body height and more intense intrasexual physical competition, compared with women.

Towards effective learning for face super-resolution with shape and pose perturbations

Recent development of convolutional neural networks (CNNs) has activated a lot of studies and boosted the performance greatly on image super-resolution. This paper addresses the issue of face super-resolution, which attracts a lot of interests in the photographic industry. We propose to make use of the face-specific priors to enhance the performance of face super-resolution with the convolutional neural networks. Classical facial prior models represent the 2D facial shape in a compact low-dimensional space expressed by principal components. Here, we impose perturbations on the low-dimensional space and generate face samples with novel appearance. First, we conduct 2D facial image perturbations through 2D facial landmarks. Then, we carry on the study with perturbations on 3D facial landmarks. Facial pose and shape are perturbated to generate novel appearances of a single 2D facial image. These novel facial samples are then fed into the training process of the convolutional neural networks for face super-resolution. The experimental results demonstrate that the proposed method is adaptable to various networks and achieves superior performance for the face super-resolution task.

A Novel Method in Predicting Hypertension Using Facial Images

Hypertension has been a crucial public health challenge among adults. This study aimed to develop a novel method for non-contact prediction of hypertension using facial characteristics such as facial features and facial color. The data of 1099 subjects (376 men and 723 women) analyzed in this study were obtained from the Korean Constitutional Multicenter Study of Korean medicine Data Center (KDC) at the Korea Institute of Oriental Medicine (KIOM). Facial images were collected and facial variables were extracted using image processing techniques. Analysis of covariance (ANCOVA) and Least Absolute Shrinkage and Selection Operator (LASSO) were performed to compare and identify the facial characteristic variables between the hypertension group and normal group. We found that the most distinct facial feature differences between hypertension patients and normal individuals were facial shape and nose shape for men in addition to eye shape and nose shape for women. In terms of facial colors, cheek color in men, as well as forehead and nose color in women, were the most distinct facial colors between the hypertension groups and normal individuals. Looking at the AUC value, the prediction power for women is better than men. In conclusion, we managed to explore and identify the facial characteristics variables related to hypertension. This study may provide new evidence in the validity of predicting hypertension using facial characteristics.

Multistage Model for Robust Face Alignment Using Deep Neural Networks

The ability to generalize unconstrained conditions such as severe occlusions and large pose variations remains a challenging goal to achieve in face alignment. In this paper, a multistage model based on deep neural networks is proposed which takes advantage of spatial transformer networks, hourglass networks and exemplar-based shape constraints. First, a spatial transformer-generative adversarial network which consists of convolutional layers and residual units is utilized to solve the initialization issues caused by face detectors, such as rotation and scale variations, to obtain improved face bounding boxes for face alignment. Then, stacked hourglass network is employed to obtain preliminary locations of landmarks as well as their corresponding scores. In addition, an exemplar-based shape dictionary is designed to determine landmarks with low scores based on those with high scores. By incorporating face shape constraints, misaligned landmarks caused by occlusions or cluttered backgrounds can be considerably improved. Extensive experiments based on challenging benchmark datasets are performed to demonstrate the superior performance of the proposed method over other state-of-the-art methods.