Repeatability and agreement of white-to-white measurements between slit-scanning tomography, infrared biometry, dual rotating Scheimpflug camera/Placido disc tomography, and swept source anterior segment optical coherence tomography.

PURPOSE: To assess the agreement and repeatability of horizontal visible iris diameter (HVID) or white-to-white (WTW) measurements between four imaging modalities; combination slit scanning elevation/Placido tomography, infrared biometry, dual rotating scheimpflug camera/Placido tomography, and swept source anterior segment optical coherence tomography (AS-OCT). METHODS: A prospective study of 35 right eyes of healthy volunteers were evaluated using the Orbscan IIz, IOL Master 700, Galilei G2, and DRI Triton OCT devices. The inter-device agreement and repeatability of HVID/WTW measurements for each device were analysed. RESULTS: Mean HVID/WTW values obtained by the Orbscan IIz, IOL Master 700, Galilei G2 and DRI Triton OCT were 11.77 ± 0.40 mm, 12.40 ± 0.43 mm, 12.25 ± 0.42 mm, and 12.42 ± 0.47 mm, respectively. All pairwise comparisons revealed statistically significant differences in mean HVID/WTW measurements (p = <0.01) except for the IOL Master 700-DRI OCT Triton pair (p = 0.56). Mean differences showed that the DRI Triton OCT produced the highest HVID/WTW values, followed by the IOL Master 700, Galilei G2 and Orbscan IIz, respectively. The limits of agreement were large on all device pairs. There was high repeatability for all devices (ICC ≥ 0.980). The highest repeatability was seen in the Galilei G2 (ICC = 0.995) and lowest in the Orbscan IIz (ICC = 0.980). CONCLUSIONS: The four devices exhibit high repeatability, but should not be used interchangeably for HVID/WTW measurements in clinical practice.

Repeatability and agreement of biometric measurements using spectral domain anterior segment optical coherence tomography and Scheimpflug tomography in keratoconus.

PURPOSE: To compare the repeatability and agreement in biometric measurements using Spectral Domain Anterior Segment OCT (AS-OCT, REVO-NX, Optopol) and Scheimpflug tomography (Pentacam-AXL, Oculus) in keratoconus. METHODS: Prospective case series at a university hospital tertiary center. Axial length (AL), anterior chamber depth (ACD), central corneal thickness (CCT), and thinnest corneal thickness (TCT) were measured using both devices in patients with keratoconus. Three groups were analyzed: eyes with no prior crosslinking or contact lens wear (Group A), eyes with prior crosslinking (Group B), and eyes with prior contact lens wear (Group C). Repeatability and agreement of measurements were analyzed. RESULTS: The study comprised of 214 eyes of 157 subjects. In Group A (n = 95 eyes), Group B (n = 86 eyes), and Group C (n = 33 eyes), intraclass correlation coefficient (ICC) was higher than 0.90 for all examined parameters, except for ACD readings in Group A with the REVO-NX (ICC = 0.83). Differences in ACD, TCT, and CCT were significantly different between the two devices for Groups A, B and C (p<0.05). AL measurements differed significantly in Groups A and B (p<0.05) but not in Group C (p = 0.18). Repeatability did not vary significantly between Groups A, B, or C in any parameter with both devices (p>0.05). There was poor agreement between the two devices across all parameters (p<0.05). CONCLUSIONS: Both devices demonstrated good repeatability but poor agreement across AL, ACD, CCT and TCT measurements. There was no significant difference in repeatability in virgin eyes compared to eyes with prior crosslinking or contact lens wear, however, the interchangeable use of the two devices is not recommended.

An end-to-end exemplar association for unsupervised person Re-identification.

Tracklet association methods learn the cross camera retrieval ability though associating underlying cross camera positive samples, which have proven to be successful in unsupervised person re-identification task. However, most of them use poor-efficiency association strategies which costs long training hours but gains the low performance. To solve this, we propose an effective end-to-end exemplar associations (EEA) framework in this work. EEA mainly adapts three strategies to improve efficiency: (1) end-to-end exemplar-based training, (2) exemplar association and (3) dynamic selection threshold. The first one is to accelerate the training process, while the others aim to improve the tracklet association precision. Compared with existing tracklet associating methods, EEA obviously reduces the training cost and achieves the higher performance. Extensive experiments and ablation studies on seven RE-ID datasets demonstrate the superiority of the proposed EEA over most state-of-the-art unsupervised and domain adaptation RE-ID methods.

Person Re-Identification with Feature Pyramid Optimization and Gradual Background Suppression.

Compared with face recognition, the performance of person re-identification (re-ID) is still far from practical application. Among various interferences, there are two factors seriously limiting the performance improvement, i.e., the feature discriminability determined by "external network effectiveness", and the image quality determined by "internal background clutters". Target at the "external network effectiveness" problem, feature pyramids are effective to learn discriminative features because they can learn both detailed features from high-resolution shallow layers and semantical features from low-resolution deep layers, however, it can only achieve slight improvement on re-ID tasks because of the error back propagation problem. To handle the problem and utilize the effectiveness of feature pyramids, we propose a strategy called Feature Pyramid Optimization (FPO). Instead of concatenating features directly, the selected layers are optimized independently in a top-bottom order. Target at the "internal background clutters" problem, background suppression is generally considered for removing the environmental interference and improving the image quality. Several mask-based methods are used attempting to totally remove background clutters but achieve limited promotion because of the mask sharpening effect. We propose a novel strategy, i.e., Gradual Background Suppression (GBS) to reduce the background clutters and keep the smoothness of images simultaneously. Extensive experiments have been conducted and the results demonstrate the effectiveness of both FPO and GBS.

An innovative panel containing a set of insertion/deletion loci for individual identification and its forensic efficiency evaluations in Chinese Hui ethnic minority.

BACKGROUND: Individual identification is one of the most important tasks in the field of forensic genetics. Insertion/Deletion (InDel) polymorphism marker has been a promising marker for individual identification. However, a part of InDel loci in commonly used commercial kit show low polymorphisms in Chinese populations. METHODS: We evaluated a panel of 35 InDel loci constructed previously for individual identifications in Hui group. Subsequently, population data of three Chinese populations from 1,000 Genomes Project database were used to evaluate individual identification performance of these 35 InDels. Forensic parameters, such as heterozygosity, power of exclusion, match probability and power of discrimination, were calculated to evaluate the forensic efficiency of these loci in Hui group. The heatmap of insertion allelic frequencies, Nei's genetic distances, pairwise fixation index values, principal component analyses and admixture analyses were used to analyze the genetic differentiations and structure between Hui group and other populations. RESULTS: In studied Hui group, besides rs3054057, polymorphism information content values of the remaining loci were greater than 0.3. Values of expected heterozygosity of these loci were close to 0.5. The combined power of discrimination and power of exclusion values were 0.99999999999999659609 and 0.998682, respectively. Analyses of population genetics revealed that Chinese Hui group had closer genetic relationships with East Asian populations than other intercontinental populations. CONCLUSION: The forensic statistical analyses revealed these loci showed relatively high genetic polymorphisms in Chinese Hui group, and could be served as a useful tool for individual identifications in Hui group. Population genetic evaluations indicated that Chinese Hui group had close genetic relationships with East Asian populations.

A Facial Recognition Mobile App for Patient Safety and Biometric Identification: Design, Development, and Validation.

BACKGROUND: Patient verification by unique identification is an important procedure in health care settings. Risks to patient safety occur throughout health care settings by failure to correctly identify patients, resulting in the incorrect patient, incorrect site procedure, incorrect medication, and other errors. To avoid medical malpractice, radio-frequency identification (RFID), fingerprint scanners, iris scanners, and other technologies have been implemented in care settings. The drawbacks of these technologies include the possibility to lose the RFID bracelet, infection transmission, and impracticality when the patient is unconscious. OBJECTIVE: The purpose of this study was to develop a mobile health app for patient identification to overcome the limitations of current patient identification alternatives. The development of this app is expected to provide an easy-to-use alternative method for patient identification. METHODS: We have developed a facial recognition mobile app for improved patient verification. As an evaluation purpose, a total of 62 pediatric patients, including both outpatient and inpatient, were registered for the facial recognition test and tracked throughout the facilities for patient verification purpose. RESULTS: The app was developed to contain 5 main parts: registration, medical records, examinations, prescriptions, and appointments. Among 62 patients, 30 were outpatients visiting plastic surgery department and 32 were inpatients reserved for surgery. Whether patients were under anesthesia or unconscious, facial recognition verified all patients with 99% accuracy even after a surgery. CONCLUSIONS: It is possible to correctly identify both outpatients and inpatients and also reduce the unnecessary cost of patient verification by using the mobile facial recognition app with great accuracy. Our mobile app can provide valuable aid to patient verification, including when the patient is unconscious, as an alternative identification method.

A Novel Technique for Multi Biometric Cryptosystem Using Fuzzy Vault.

Biometric authentication is the process of recognizing a person by means of his\her psychological or behavioral traits. One of the most important issues faced by the biometric system developer is to protect the template obtained from the biometric of a person. Unimodal biometric system has some drawbacks such as noisy data, interclass variations and spoof attack. Multimodal biometric system has been developed to address the boundaries of unimodal biometric system and increase the security of template. In this paper, template security analysis of multimodal biometric system based of fingerprint and palmprint is proposed and implemented. Fuzzy vault scheme is employed to protect both the fingerprint and palmprint template. At enrollment, image processing techniques such as image enhancement, segmentation and bottom-hat filtering are applied on both the biometric to improve the quality and subsequently the most important features are extracted. Extracted features are concatenated. Combined features along with secret key are utilized to generate the database in the vault. During authentication, query images are sent as an input with the stored template to recover the key. Experimental results are shown that the proposed multi biometrics system performs well than the other methods considered for comparison.

A secure heterogeneous mobile authentication and key agreement scheme for e-healthcare cloud systems.

Heterogeneous mobile authentication is a crucial technique to securely retrieve the resource of e-healthcare cloud servers which are commonly implemented in a public key Infrastructure (PKI). Conventionally, a mobile data user can utilize a self-chosen password along with a portable device to request the access privilege of clouds. However, to validate the membership of users, a cloud server usually has to make use of a password table, which not only increases the burden of management, but also raises the possibility of information leakage. In this paper, we propose a secure heterogeneous mobile authentication and key agreement scheme for e-healthcare cloud systems. In our system structure, an e-healthcare cloud server of traditional PKIs does not have to store a password table. A legitimate data user only possesses a security token hardware and keeps an offline updatable password without using any private key. Our scheme is classified into the category of dynamic ID authentication techniques, since a data user is able to preserve his/her anonymity during authentication processes. We formally prove that the proposed mechanism fulfills the essential authenticated key exchange (AKE) security and owns lower computational costs. To further ensure the practical application security, an automatic security validation tool called AVISPA is also adopted to analyze possible attacks and pitfalls of our designed protocol.

3D software scanning, processing and archiving palatal rugae: "identity base" technology.

The palatal rugae, which are anatomically described as folds or wrinkles of the palate, are located on the anterior third of the palate on each side of the palatal raphe and behind the incisive papilla. The use of palatal rugae for personal identification was suggested several years ago, and attracted interest from different researchers which created different classifications, still used in scientific literature. The "identity base" (IB) system has as its object a complex information system and a personal identification protocol by means of three-dimensional palatal scans in digital format. The usefulness of this system is based on the management needs of big data. For example, in the field of forensic odontology, IB can be useful in the identification of a living or cadaver subject; and can estimate the age of a human subject. Moreover, IB stores its associated biometric data. The IB system demonstrated to overcome the issues shown by other similar systems of digital image storage. Furthermore, its high accuracy in the identification process makes IB a reliable tool for institutions in the management of immigrants, as well as in the archiving of people under restrictive measures. Finally, IB is also a system for sharing and processing clinical images, useful in dental prosthetics to reduce the number of steps from the first visit to dental prosthesis. The next generation of big-data archiving will speak the same language as IB: the route has been already set out.

A secure biometrics-based authentication key exchange protocol for multi-server TMIS using ECC.

BACKGROUND AND OBJECTIVES: Telecare Medicine Information System (TMIS) enables physicians to efficiently and conveniently make certain diagnoses and medical treatment for patients over the insecure public Internet. To ensure patients securely access to medicinal services, many authentication schemes have been proposed. Although numerous cryptographic authentication schemes for TMIS have been proposed with the aim to ensure data security, user privacy and authentication, various forms of attacks make these schemes impractical. METHODS: To design a truly secure and practical authentication scheme for TMIS, a new biometrics-based authentication key exchange protocol for multi-server TMIS without sharing the system private key with distributed servers is presented in this work. RESULTS: Our proposed protocol has perfect security features including mutual authentication, user anonymity, perfect forward secrecy and resisting various well-known attacks, and these security feathers are confirmed by the BAN logic and heuristic cryptanalysis, respectively. CONCLUSIONS: A secure biometrics-based authentication key exchange protocol for multi-server TMIS is presented in this work, which has perfect security properties including perfect forward secrecy, supporting user anonymity, etc., and can withstand various attacks such as impersonation attack, off-line password guessing attack, etc.. Considering security is the most important factor for an authentication scheme, so our scheme is more suitable for multi-server TMIS.

Nonlinear analysis and synthesis of video images using deep dynamic bottleneck neural networks for face recognition.

Nonlinear components extracted from deep structures of bottleneck neural networks exhibit a great ability to express input space in a low-dimensional manifold. Sharing and combining the components boost the capability of the neural networks to synthesize and interpolate new and imaginary data. This synthesis is possibly a simple model of imaginations in human brain where the components are expressed in a nonlinear low dimensional manifold. The current paper introduces a novel Dynamic Deep Bottleneck Neural Network to analyze and extract three main features of videos regarding the expression of emotions on the face. These main features are identity, emotion and expression intensity that are laid in three different sub-manifolds of one nonlinear general manifold. The proposed model enjoying the advantages of recurrent networks was used to analyze the sequence and dynamics of information in videos. It is noteworthy to mention that this model also has also the potential to synthesize new videos showing variations of one specific emotion on the face of unknown subjects. Experiments on discrimination and recognition ability of extracted components showed that the proposed model has an average of 97.77% accuracy in recognition of six prominent emotions (Fear, Surprise, Sadness, Anger, Disgust, and Happiness), and 78.17% accuracy in the recognition of intensity. The produced videos revealed variations from neutral to the apex of an emotion on the face of the unfamiliar test subject which is on average 0.8 similar to reference videos in the scale of the SSIM method.

Deep facial analysis: A new phase I epilepsy evaluation using computer vision.

Semiology observation and characterization play a major role in the presurgical evaluation of epilepsy. However, the interpretation of patient movements has subjective and intrinsic challenges. In this paper, we develop approaches to attempt to automatically extract and classify semiological patterns from facial expressions. We address limitations of existing computer-based analytical approaches of epilepsy monitoring, where facial movements have largely been ignored. This is an area that has seen limited advances in the literature. Inspired by recent advances in deep learning, we propose two deep learning models, landmark-based and region-based, to quantitatively identify changes in facial semiology in patients with mesial temporal lobe epilepsy (MTLE) from spontaneous expressions during phase I monitoring. A dataset has been collected from the Mater Advanced Epilepsy Unit (Brisbane, Australia) and is used to evaluate our proposed approach. Our experiments show that a landmark-based approach achieves promising results in analyzing facial semiology, where movements can be effectively marked and tracked when there is a frontal face on visualization. However, the region-based counterpart with spatiotemporal features achieves more accurate results when confronted with extreme head positions. A multifold cross-validation of the region-based approach exhibited an average test accuracy of 95.19% and an average AUC of 0.98 of the ROC curve. Conversely, a leave-one-subject-out cross-validation scheme for the same approach reveals a reduction in accuracy for the model as it is affected by data limitations and achieves an average test accuracy of 50.85%. Overall, the proposed deep learning models have shown promise in quantifying ictal facial movements in patients with MTLE. In turn, this may serve to enhance the automated presurgical epilepsy evaluation by allowing for standardization, mitigating bias, and assessing key features. The computer-aided diagnosis may help to support clinical decision-making and prevent erroneous localization and surgery.

Facial Emotion Recognition: A Survey and Real-World User Experiences in Mixed Reality.

Extensive possibilities of applications have made emotion recognition ineluctable and challenging in the field of computer science. The use of non-verbal cues such as gestures, body movement, and facial expressions convey the feeling and the feedback to the user. This discipline of Human-Computer Interaction places reliance on the algorithmic robustness and the sensitivity of the sensor to ameliorate the recognition. Sensors play a significant role in accurate detection by providing a very high-quality input, hence increasing the efficiency and the reliability of the system. Automatic recognition of human emotions would help in teaching social intelligence in the machines. This paper presents a brief study of the various approaches and the techniques of emotion recognition. The survey covers a succinct review of the databases that are considered as data sets for algorithms detecting the emotions by facial expressions. Later, mixed reality device Microsoft HoloLens (MHL) is introduced for observing emotion recognition in Augmented Reality (AR). A brief introduction of its sensors, their application in emotion recognition and some preliminary results of emotion recognition using MHL are presented. The paper then concludes by comparing results of emotion recognition by the MHL and a regular webcam.

A Hypergraph and Arithmetic Residue-based Probabilistic Neural Network for classification in Intrusion Detection Systems.

Over the past few decades, the design of an intelligent Intrusion Detection System (IDS) remains an open challenge to the research community. Continuous efforts by the researchers have resulted in the development of several learning models based on Artificial Neural Network (ANN) to improve the performance of the IDSs. However, there exists a tradeoff with respect to the stability of ANN architecture and the detection rate for less frequent attacks. This paper presents a novel approach based on Helly property of Hypergraph and Arithmetic Residue-based Probabilistic Neural Network (HG AR-PNN) to address the classification problem in IDS. The Helly property of Hypergraph was exploited for the identification of the optimal feature subset and the arithmetic residue of the optimal feature subset was used to train the PNN. The performance of HG AR-PNN was evaluated using KDD CUP 1999 intrusion dataset. Experimental results prove the dominance of HG AR-PNN classifier over the existing classifiers with respect to the stability and improved detection rate for less frequent attacks.

Automated facial recognition and candidate list rank change of computer generated facial approximations generated with multiple eye orb positions.

Expanding on research previously reported by the authors, this study further examines the recognizability of ReFace facial approximations generated with the following eye orb positions: (i) centrally within the bony eye socket, (ii) 1.0mm superior and 2.0mm lateral relative to center, and (iii) 1.0mm superior and 2.5mm lateral relative to center. Overall, 81% of the test subjects' approximation ranks improved with the use of either of the two supero-lateral eye orbs. Highly significant performance differences (p<0.01) were observed between the approximations with centrally positioned eye orbs (i) and approximations with the eye orbs placed in the supero-laterally positions (ii and iii). Noteworthy was the observation that in all cases when the best rank for an approximation was obtained with the eye orbs in position (iii), the second best rank was achieved with the eye orbs in position (ii). A similar pattern was also observed when the best rank was obtained with the eye orbs in position (ii), with 60% of the second best ranks observed in position (iii). It is argued, therefore, that an approximation constructed with the eye orbs placed in either of the two supero-lateral positions may be more effective and operationally informative than centrally positioned orbs.

[The specific age-related palmometric features of an adult subject].

In connection with the variability and as a consequence of the poor diagnostic value of the external (planimetric) parameters of the palm traces, the new system of absolute and relative dimensional attributes based on the stable palmoglyphic reference points is considered. The purpose of the present study was the search for the new biological markers of biological age. The material for the study consisted of the palm prints obtained from 180 men and 120 women of the Caucasoid stock at the age from 16 to 80 years. The use of the descriptive statistics methods yielded the basic statistical characteristics of the traits being investigated and revealed the limits of their variability in the groups of men and women belonging to the age groups from 16 to 29 and from 30 to 80 years. The method of threshold values made it possible to identify 13 attributes the excess of which allows, with the probability of no less than 0.95, to perform diagnostics of the age group of an unknown subject.

Towards Open-World Person Re-Identification by One-Shot Group-Based Verification.

Solving the problem of matching people across non-overlapping multi-camera views, known as person re-identification (re-id), has received increasing interests in computer vision. In a real-world application scenario, a watch-list (gallery set) of a handful of known target people are provided with very few (in many cases only a single) image(s) (shots) per target. Existing re-id methods are largely unsuitable to address this open-world re-id challenge because they are designed for (1) a closed-world scenario where the gallery and probe sets are assumed to contain exactly the same people, (2) person-wise identification whereby the model attempts to verify exhaustively against each individual in the gallery set, and (3) learning a matching model using multi-shots. In this paper, a novel transfer local relative distance comparison (t-LRDC) model is formulated to address the open-world person re-identification problem by one-shot group-based verification. The model is designed to mine and transfer useful information from a labelled open-world non-target dataset. Extensive experiments demonstrate that the proposed approach outperforms both non-transfer learning and existing transfer learning based re-id methods.

Optimized face recognition algorithm using radial basis function neural networks and its practical applications.

In this study, we propose a hybrid method of face recognition by using face region information extracted from the detected face region. In the preprocessing part, we develop a hybrid approach based on the Active Shape Model (ASM) and the Principal Component Analysis (PCA) algorithm. At this step, we use a CCD (Charge Coupled Device) camera to acquire a facial image by using AdaBoost and then Histogram Equalization (HE) is employed to improve the quality of the image. ASM extracts the face contour and image shape to produce a personal profile. Then we use a PCA method to reduce dimensionality of face images. In the recognition part, we consider the improved Radial Basis Function Neural Networks (RBF NNs) to identify a unique pattern associated with each person. The proposed RBF NN architecture consists of three functional modules realizing the condition phase, the conclusion phase, and the inference phase completed with the help of fuzzy rules coming in the standard 'if-then' format. In the formation of the condition part of the fuzzy rules, the input space is partitioned with the use of Fuzzy C-Means (FCM) clustering. In the conclusion part of the fuzzy rules, the connections (weights) of the RBF NNs are represented by four kinds of polynomials such as constant, linear, quadratic, and reduced quadratic. The values of the coefficients are determined by running a gradient descent method. The output of the RBF NNs model is obtained by running a fuzzy inference method. The essential design parameters of the network (including learning rate, momentum coefficient and fuzzification coefficient used by the FCM) are optimized by means of Differential Evolution (DE). The proposed P-RBF NNs (Polynomial based RBF NNs) are applied to facial recognition and its performance is quantified from the viewpoint of the output performance and recognition rate.