Facial Image Identification Research Articles

Development of abnormal facial temperature detection technology using thermal imaging to prevent the spread of infectious diseases

Substantial research has been conducted on image-based augmentation, segmentation, detection, and classification of COVID-19. Thermal image classification methods have been used to identify people with high fever. However, these methods cannot always identify infected patients because aberrant images cannot be detected using face temperatures. For example, if the individual in the thermal image cleansed his/her face a few minutes earlier or was perspiring, the method cannot reliably determine their facial temperature. Moreover, the active movements of the human body can produce temperature variations in the face. Thus, achieving high accuracy remains challenging in thermal facial image identification. Therefore, in this study, a novel research has been conducted to solve the problems. Based on preliminary experimental results, a deep-learning-based classification system was proposed for detecting faces with abnormal facial temperatures in thermal pictures. Two different experiments including abnormal face images detection and classification were conducted. To conduct these experiments, a self-collected thermal face-image dataset including abnormal (faces after exercise, sweaty and wet faces) and normal images was used. In the detection method, a binary image classification was conducted to classify the abnormal and normal images. Moreover, in the classification method, an input image is classified into four classes, such as normal faces (class 1) and three abnormal faces, namely, after physical activity (class 2), sweaty face (class 3), and wet face (class 4). Testing on the dataset collected in this study revealed that the proposed detection and classification methods achieved F1-score of 95.71 and 96.17, respectively. These performances are superior to those of the state-of-the-art methods.

Application of biometric systems in face identification technologies

The paper presents an analytical review of the application of biometric recognition systems in relation to facial image identification technologies. The classification of biometric systems is presented. The trends of technological progress in the field of biometrics and facial recognition capabilities are considered. It is determined that in 2020 there is a trend of transition from the use of biometric recognition technologies in traditional state security systems to the sphere of commercial and user applications. The process of «linking» encryption keys and passwords with the biometric parameters of the data subject is described. It is proposed that a biometric feature and a biometrics parameter mean a certain value that has a physical meaning that characterizes the subject itself. The possibility of using circular neighborhood and bilinear interpolation of pixel intensity values in biometrics is also presented. This will make it possible to build a local binary template. In order to solve the problem of identification of persons, it is advisable to investigate the essence of biometric systems in the technologies of identification of persons, their types, identifying the shortcomings of each of them, on the basis of which to present the directions of elimination and search for the most reliable technologies. The essence of the use of biometric systems in the technologies of identification of persons is, for example, that the user can provide the bank or other counterparty with evidence that it is he who wants to use the services on his accounts. At the same time, the demand has increased for contactless biometric solutions. These technologies are implemented in order to conduct additional biometric verification of users. This allows to minimize possible fraud or violation of the internal rules of the service, for example, the transfer of accounts of some registered users to others.

Identification and Recognition of facial images

Face detection is the power to identify a face and recognition is the ability to recognize whose face it is by means of facial characteristics. Face is multivariate and requires a lot of mathematical summation. Almost all imperative applications use a face recognition system. There are many methods that have been already proposed which provides low recognition rate. Hence, the main task of research is to develop a face recognition system with higher recognition capability and better accuracy. This paper proposes Face recognition system by combining two techniques Viola Jones and Principal Component Analysis. An approach of Eigen faces is employed in Principle Component Analysis(PCA). The face recognition system is implemented in MATLAB.

The model is a reprint of an object in the image

The problem of facial image recognition (identification) is presented. The difference between facial image recognition and identification is shown. To solve the identification problem, a model of object reprint in the image was developed. This model solves the problem by representing the object in 3-dimensional form, which makes it possible to evaluate and form the necessary characteristics of the object in full, whereas in 2-dimensional form, it is impossible to do this. The model of an object reprint in an image can be used to create a reprint of any spatial objects. To train a reprint model of an object in an image, a multi-layer neural network is used, which is trained sequentially. A local detector for the facial image identification model has been developed to account for acceptable changes in angle, various noise, and different light levels. The binary value that is the result of model processing, represented as activation, determines the relation of a particular image to the corresponding class. The local detector is not only the main element of the model of the object reprint in the image, but it is also a separate mathematical construction. It accepts input data as two-dimensional images. The developed model of object reprint on the image completely solves the problem of identifying a person from the facial image as a whole in conditions of interference and regardless of changes in the angle.

Design and Implementation of a Computerized User Authentication System for E-Learning

The system based on formalized teaching with the help of electronic resources is called as E-learning. Using E-Learning in the university education systems has been growing rapidly based on the application of Information Technology (IT) designed for the substitute of traditional based learning approach. In terms of the E-learning based examinations, security constraints such as, identification of the user, misuse the passwords, unauthorized user instead of the authenticated one are available. Because of these disadvantages, the need of an authentication system is very important. The main challenge facing the security of E-learning environment is how to identify the unauthorized users from accessing and managing any platform. Therefore solving the problem of authenticating the valid user is very important. So, an intelligent examination system along with user authentication based on facial expression recognition is proposed in this paper. The proposed system can be classified in to three phases. The first phase is the design of facial database from the captured images. The second phase is the design of Artificial Intelligence (AI) based system for facial feature extraction and its classification using intelligent Agents. The final phase is the authentication of respective users by automatic identification of facial images. The results obtained shows that the proposed methodology has managed to validate the authenticated users and to provide an effective security in the E-learning platform.

Full-Reference Facial Image Quality Assessment and Identification by Two Proposed Measures

In this paper, the goal was to identify a person’s face in the acquired image by the proposed measures. We discuss the appearance of two types of noise together in an image. The acquired facial image quality was also assessed by two proposed measures, the histogram similarity measure and the histogram error mean measure. The histogram structural similarity measure is a previously described modified version of the information-theoretic structural similarity measure. It was merged with the structural similarity measure and the error mean measure, derived from the mean squared error, to get the proposed measures. The first proposed histogram similarity measure consists of merging histogram structural similarity with structural similarity measure, and the second proposed histogram error mean measure consists of merging histogram structural similarity with error mean measure. Finally, many algorithms for identification have recently been proposed to measure the similarity between two images. The results showed that the two proposed measures were better than existing methods. Different noises types (such as white Gaussian, speckle, and salt-and-pepper) are used with the proposed methods. Two facial image datasets were used in this paper. The AT&T database included color images of 92 x 112 pixels (px), and the Faculty of Industrial Engineering database included color images of 480 x 640 px. To evaluate performance and quantify the error, the structural similarity measure, histogram structural similarity, and error mean measure were considered. Noise ratios that depended on a peak signal-to-noise ratio were used in this experiment.

Joint Demographic Features Extraction for Gender, Age and Race Classification based on CNN

Automatic verification and identification of face from facial image to obtain good accuracy with huge dataset of training and testing to using face attributes from images is still challengeable. Hence proposing efficient and accurate facial image identification and classification based of facial attributes is important task. The prediction from human face image is much complex. The proposed research work for automatic gender, age and race classification is based on facial features and Convolutional Neural Network (CNN). The proposed study uses the physical appearance of human face to predict age, gender and race. The proposed methodology consists of three sub systems, Gender, Ageing and Race. Therefore different feature are extracted for every sub system. These features are extracted by using Primary, Secondary features, Face Angle, Wrinkle Analysis, LBP and WLD. The accuracy of classification is based on these features. CNN used to classify by using these features. The proposed study has been evaluated and tested on large database MORPH II and UTKF. The performance of proposed system is compared with state of art techniques.

Performance of distance-based matching algorithms in 3D facial identification

Facial image identification is an area of forensic sciences, where an expert provides an opinion on whether or not two or more images depict the same individual. The primary concern for facial image identification is that it must be based on sound scientific principles. The recent extensive development in 3D recording technology, which is presumed to enhance performances of identification tasks, has made essential to question conditions, under which 3D images can yield accurate and reliable results. The present paper explores the effect of mesh resolution, adequacy of selected measures of dissimilarity and number of variables employed to encode identity-specific facial features on a dataset of 528 3D face models sampled from the Fidentis 3D Face Database (N∼2100). In order to match 3D images two quantitative approaches were tested, the first based on closest point-to-point distances computed from registered surface models and the second grounded on Procrustes distances derived from discrete 3D facial points collected manually on textured 3D facial models. The results expressed in terms of rank-1 identification rates, ROC curves and likelihood ratios show that under optimized conditions the tested algorithms have the capacity to provide very accurate and reliable results. The performance of the tested algorithms is, however, highly dependent on mesh resolution and the number of variables employed in the task. The results also show that in addition to numerical measures of dissimilarity, various 3D visualization tools can be of assistance in the decision-making.

Photo anthropometric variations in Japanese facial features: Establishment of large-sample standard reference data for personal identification using a three-dimensional capture system

This study clarifies the anthropometric variations of the Japanese face by presenting large-sample population data of photo anthropometric measurements. The measurements can be used as standard reference data for the personal identification of facial images in forensic practices.To this end, three-dimensional (3D) facial images of 1126 Japanese individuals (865 male and 261 female Japanese individuals, aged 19–60 years) were acquired as samples using an already validated 3D capture system, and normative anthropometric analysis was carried out. In this anthropometric analysis, first, anthropological landmarks (22 items, i.e., entocanthion (en), alare (al), cheilion (ch), zygion (zy), gonion (go), sellion (se), gnathion (gn), labrale superius (ls), stomion (sto), labrale inferius (li)) were positioned on each 3D facial image (the direction of which had been adjusted to the Frankfort horizontal plane as the standard position for appropriate anthropometry), and anthropometric absolute measurements (19 items, i.e., bientocanthion breadth (en-en), nose breadth (al-al), mouth breadth (ch-ch), bizygomatic breadth (zy-zy), bigonial breadth (go-go), morphologic face height (se-gn), upper-lip height (ls-sto), lower-lip height (sto-li)) were exported using computer software for the measurement of a 3D digital object. Second, anthropometric indices (21 items, i.e., (se-gn)/(zy-zy), (en-en)/(al-al), (ls-li)/(ch-ch), (ls-sto)/(sto-li)) were calculated from these exported measurements.As a result, basic statistics, such as the mean values, standard deviations, and quartiles, and details of the distributions of these anthropometric results were shown. All of the results except “upper/lower lip ratio (ls-sto)/(sto-li)” were normally distributed. They were acquired as carefully as possible employing a 3D capture system and 3D digital imaging technologies. The sample of images was much larger than any Japanese sample used before for the purpose of personal identification. The measurements will be useful as standard reference data for forensic practices and as material data for future studies in this field.

基于S3C2440的人脸识别平台的设计

To realize the need of low-cost intelligent access control/monitoring system,this paper designs the platform of the face recognition based on S3C2440 processor and researches the acquisition/display driver algorithms and face recognition algorithm based on the platform.Using Samsung's S3C2440 processor and OmniVision's OV9650 camera to build the hardware platform,the feature points of human face images is extracted by Harris algorithm,and the data in the database is matched to draw relevant information.In order to accelerate real-time facial image capture-matching the speed of the platform,the cache is opened to accelerate the program.The platform is designed using intelligent access control/monitoring systems to achieve the rapid identification of facial images,a simple structure and low cost.It meets the need of monitoring applications.

Assessment of some problematic factors in facial image identification using a 2D/3D superimposition technique

The number of criminal cases requiring facial image identification of a suspect has been increasing because a surveillance camera is installed everywhere in the city and furthermore, the intercom with the recording function is installed in the home. In this study, we aimed to analyze the usefulness of a 2D/3D facial image superimposition system for image identification when facial aging, facial expression, and twins are under consideration. As a result, the mean values of the average distances calculated from the 16 anatomical landmarks between the 3D facial images of the 50s groups and the 2D facial images of the 20s, 30s, and 40s groups were 2.6, 2.3, and 2.2mm, respectively (facial aging). The mean values of the average distances calculated from 12 anatomical landmarks between the 3D normal facial images and four emotional expressions were 4.9 (laughter), 2.9 (anger), 2.9 (sadness), and 3.6mm (surprised), respectively (facial expressions). The average distance obtained from 11 anatomical landmarks between the same person in twins was 1.1mm, while the average distance between different person in twins was 2.0mm (twins). Facial image identification using the 2D/3D facial image superimposition system demonstrated adequate statistical power and identified an individual with high accuracy, suggesting its usefulness. However, computer technology concerning video image processing and superimpose progress, there is a need to keep familiar with the morphology and anatomy as its base.

Independent Component Analysis–Based Feature Extraction Technique for Defect Classification Applied for Pulsed Eddy Current NDE

With the development of nondestructive detection, the emerging testing techniques provide new challenges to signal analysis and interpretation approach applied to the inspection evaluation. Some researchers have developed the methods that focus on feature analysis of detected signals. This article presents a new feature analysis by the Independent Component Analysis (ICA) approach to evaluate the defects tested by the pulsed eddy current (PEC) technique. ICA is a high-order statistics technique used to separate multi-unknown sources, which has been successfully applied to facial image identification and separation of the components of 1D signal. In this article, the ICA approach is utilized to project the response signals of various defects into the independent components (ICs) feature subspace by signal representation model. Dependent on the selected ICs, each defect is represented by different projected coefficients, which are proposed to discriminate and classify the defects that belong to three categories. The improved ICA model is proposed to improve the classification of two similar categories of single defects: metal loss and subsurface defects. The evaluation using the series of experimental data has validated the classification of single defects and the defects with lift-off effect by our ICA approach. The comparison with Principal component analysis (PCA)–based approach further verified the better performance of the ICA-based model.

Morphological Classification of the Ear Components and the Correlation between Morphological Characteristics in Each Component

Facial image identification has become important in forensic science because surveillance cameras are popularly used as silent witnesses at potential crime scenes. In general, three methods are used for facial image identification: morphological comparison of facial features, facial image anthropometry and face-to-face superimposition. The most commonly employed method in actual casework is morphological comparison based on the morphological classification of facial components such as facial types, eyebrows, eyes, nose, lips and ears. However, classification for ear morphology has not been developed, except for the ear lobe. The human ear has various anatomical parts, including the helix, antihelix, tragus, antitragus, scaphoid fossa, and ear lobe. The present study was designed to develop a new classification system for the ear. Ear images obtained from 164 Japanese adult males (n=94, age range: 24-60) and females (n=70, age range: 20-54) were used for establishing the morphological classification. In general, the features of the ear are very easily influenced by camera angle, which usually make it difficult to compare facial images taken with surveillance cameras to mug shots in actual casework. In our previous study, however, it was suggested that some components of the ear are little affected by camera angles if the scaphoid fossa could be found on the image even though the external acoustic meatus could not be found. Therefore, the morphological characteristics of some components such as the antihelix, tragus, antitragus, scaphoid fossa, and ear lobe were observed in the ear images from all persons, and morphological classification items for those components were established. All data classified according to these items were analyzed to obtain their frequency distribution in each component and to clarify the correlation between morphological characteristics. The results revealed that some morphological characteristics in each component were significantly correlated. The present classification system for ear morphology would be useful for facial image identification.

Individual identification of disguised faces by morphometrical matching

The reliability of a morphometrical matching method for identifying disguised faces was examined experimentally using a computer-assisted facial image identification system. The 2D right oblique facial images of three target persons disguised with sunglasses, cap and gauze mask were each compared with each of the 3D facial images of 100 subjects, yielding 900 face-to-face superimpositions. The average perpendicular distance between the facial outlines and the average point-to-point distance of the corresponding landmarks in the 2D image of the disguised face and the 3D facial image, were calculated. As a matching criterion, the sum of the values of the average perpendicular difference of the facial outlines and the average point-to-point difference between the corresponding landmarks was used (abbreviation: average difference).The range of the average difference was 2.3–2.8mm for the same person (a match) and 4.0–14.6mm for different (non-matching) people, respectively. The ranges for matching and non-matching faces did not overlap. Even the 3D facial images of the non-matching person showing the closest value of average difference to the average difference for the matching person could be excluded easily. It was concluded that the morphometrical matching method can reliably identify disguised faces and the results produced by this method could be easily understandable by a court of law.

Recent Advances in Facial Image Identification

This paper reviewed recent advances in facial image identification from the forensic aspects. Although literatures reviewed included mathematics and computer engineering fields, anthropological techniques were mainly described. Facial image identification is generally attempted using three methods: morphological comparison of facial features, facial image anthropometry and face-to-face superimposition. The most commonly employed method in actual caseworks is morphological comparison based on surface anatomy, followed by anthropometrical analysis and then face-to-face superimposition. The current technique using a 2D/3D facial image superimposition was introduced and its advantage and disadvantage were described. The evaluation of reliability in facial image identification including expert opinions was discussed, along with some problems of facial images submitted as evidential samples.

Evaluation of Morphometric Matching for the Identification of Caucasian Faces from Blurred Images.

The reliability of the morphometric matching method for identifying the blurred images of Caucasian faces was examined experimentally using a computer-assisted facial image identification system. For evaluating the match of the 3D and 2D facial images in the same person (a match), the 3D facial image obtained from 10 subjects was compared to the 2D oblique facial image of the same subject ten times, yielding 100 superimpositions. In the case of different persons (non-matching), the 3D facial images of 10 subjects were each compared to the 2D facial images of other 9 subjects, yielding 90 superimpositions. As a matching criterion, the sum of the values of the average perpendicular difference of the facial outlines and the average point-to-point difference between the corresponding landmarks was used (abbr.: average difference). The range of the average difference was 3.6-6.3 mm for the matching person and 5.8-15.3 mm for non-matching persons, respectively. The average difference and percentage error at the FP/FN crossover point were 6.0 mm and 3.2 percent. In this experiment, it was concluded that the morphometric matching method would be applicable to the identification of blurred images of Caucasian faces.

Identification of facial images in peripheral vision

Contrast sensitivity for face identification was measured as a function of image size to find out whether foveal and peripheral performance would become equivalent by magnification. Size scaling was not sufficient for this task, but when the data was scaled both in size and contrast dimensions, there was no significant eccentricity-dependent variation in the data, i.e. for equivalent performance both the size and contrast needed to increase in the periphery. By utilising spatial noise added to the images we found that in periphery information was utilised less efficiently and peripheral inferiority arose completely from lower efficiency, not from increased internal noise.

Computer-assisted facial image identification system using a 3-D physiognomic range finder

This system consists of a 3-D physiognomic range finder and a computer-assisted facial image superimposition unit. The 3-D range finder is composed of a detector for measuring facial surface and its control computer. The detector has two sinusoidal grating projection devices and two CCD cameras. The computer-assisted facial image superimposition unit consists of a host computer including a proprietary software, a flat surface color display and a color image scanner for inputting 2-D facial images of a criminal. The 3-D facial shape and texture of a suspect is obtained by using the range finder. To make the comparison between the 3-D facial image and the 2-D facial image, the 3-D facial image is first reproduced on a display of the host computer from a MO disk and then the 2-D facial image is taken with the color image scanner and reproduced on the display. The 3-D facial image is exactly adjusted to match the orientation and size of the 2-D facial image under the fine framework mode, and then the fine framework mode of 3-D facial image is converted to the fine texture image. The shape and positional relationships of facial components between the 3-D and 2-D facial images are examined by the fade-out or wipe image mode. The distance between the selected two points and angle among the selected three points on the 3-D and 2-D facial images are automatically measured for the assessment of anthropometrical data between both images. For evaluating the fit between the anthropometrical points on the 3-D and 2-D facial images, the reciprocal point-to-point difference between both images is compared.

Assessment of Computer-assisted Comparison between 3D and 2D Facial Images.

The face-to-face superimposition was experimentally performed to assess the reliability of the facial image comparison with the computer-assisted facial image identification system. For evaluating the match of the 3D and 2D facial images of the same person, the 3D facial image obtained from 25 examinees was compared to the 2D oblique facial image of the same examinees ten times, yielding 250 superimpositions. In the case of the different person, the 3D facial images of 25 examinees were each compared to the 2D facial images of other 24 examinees, yielding 600 superimpositions. The average distance obtained from the reciprocal point-to-point differences on sixteen anthropometrical points of the 3D and 2D images was used as a matching criterion. The results showed that the measuring system for the reciprocal point-to-point differences on the superimposition image was reproducible. The ranges of the average distance were 1.4-3.3 for the same person and 2.6-7.0 for a different person, respectively. The average distance and percentage error at the FP/FN crossover point were 3.1 and 4.2%. In this experiment, it was suggested that the facial image comparison using the reciprocal points matching was reliable when the threshold of the average distance was 2.5.

The cranial base: By J. H. Scott. Am. J. Phys. Anthropol.16: 319–348, September 1958

The number of criminal cases requiring facial image identification of a suspect has been increasing because a surveillance camera is installed everywhere in the city and furthermore, the intercom with the recording function is installed in the home. In this study, we aimed to analyze the usefulness of a 2D/3D facial image superimposition system for image identification when facial aging, facial expression, and twins are under consideration. As a result, the mean values of the average distances calculated from the 16 anatomical landmarks between the 3D facial images of the 50s groups and the 2D facial images of the 20s, 30s, and 40s groups were 2.6, 2.3, and 2.2 mm, respectively (facial aging). The mean values of the average distances calculated from 12 anatomical landmarks between the 3D normal facial images and four emotional expressions were 4.9 (laughter), 2.9 (anger), 2.9 (sadness), and 3.6 mm (surprised), respectively (facial expressions). The average distance obtained from 11 anatomical landmarks between the same person in twins was 1.1 mm, while the average distance between different person in twins was 2.0 mm (twins). Facial image identification using the 2D/3D facial image superimposition system demonstrated adequate statistical power and identified an individual with high accuracy, suggesting its usefulness. However, computer technology concerning video image processing and superimpose progress, there is a need to keep familiar with the morphology and anatomy as its base.