Human Identification Method Research Articles

Gait Analysis of Pedestrians with the Aim of Detecting Disabled People

Gait classification is an effective and non-intrusive method for human identification and it has received significant attention in the recent years due to its applications in visual surveillance and monitoring systems. We analyse gait signatures using spatio-temporal motion characteristics of a person to answer the question ``is there a discriminating feature in the gait signal that can help to categorise a disabled person from healthy''. The procedure has three steps: detection of a pedestrian using YOLO followed by the silhouette extraction using the Gaussian Mixture Model (GMM). Finally, skeletonization from the silhouette image to estimate head and torso locations and their angles with the vertical axis. Furthermore, velocity and acceleration signals were recorded to look for accelerating behaviour of person walking with a limp. Manual segmentations shows that the gait signal has information about unusual walking patterns but existing pedestrian detectors lack accuracy in extracting an accurate gait signal due to localization errors.

Extraction and Classification of Human Body Parameters for Gait Analysis

Human gait analysis is considered a new biometric tool for the ability to obtain metrics from the body at a distance. Biometric identifiers have properties that can technologically measure and analyze the characteristics of the human body and can be used as a form of identification and access control for security applications. Recognition through proper interpretation of gait parameters has become a relevant pattern classification problem. This work aims to develop an image processing system, with the use of the Microsoft Kinect sensor, which is capable to extract movement patterns for gait analysis and to present a comparative study of different pattern recognition methods for human identification. The image processing system, developed in C#, allowed the acquisition of three-dimensional data from several volunteers and made it possible to identify the human skeleton and automatically extract the kinetic and kinematic parameters of the body. For data analysis, different classification methods were compared. Among them, the algorithms that presented better performance were probabilistic neural networks, deep neural networks and k-nearest neighbors, with nearly 99% correct recognition rate. The obtained results demonstrate the efficiency of gait analysis as a biometric method. They also show the viability of gait parameter extraction using the Kinect sensor and the good performance of pattern recognition methods applied to the acquired gait kinetic and kinematic parameters.

Automated Human Identification and Obstacle Avoidance for Visually Impaired

This paper provides a method for human identification and obstacle avoidance for visually impaired. Visually impaired people faces lots of difficulty in accomplishing their day to day activities. Among one such difficulty is to recognize the person, this paper comes up with a technique which will helps blind people to identify person approaching them. Here DWT technique is used for face recognition. In this technique the entire image is decomposed into discrete wavelet bands. From this bands required features of image is obtained. This features when subjected to classifier gives proper output by identifying the person. Another part of paper deals with obstacle avoidance by using a blind stick. Blind stick uses an ultrasonic sensor and PIR sensor that detect obstacle at a distance of 100 cm. This stick can be used as alert signal for blind people.

Radar‐ID: human identification based on radar micro‐Doppler signatures using deep convolutional neural networks

Human identification is crucial in various applications, including terrorist attack preventing, criminal seeking, defence and so on. Traditional human identification methods are usually based on vision, biological features, radio-frequency identification cards and so on. In this study, the authors propose an identification method based on radar micro-Doppler signatures using deep convolutional neural networks (DCNNs) for the first time, which can identify human in non-contact, remote and no lighting status. They employ a K-band Doppler radar to acquire the raw signals due to its stationary clutter rejection and movement detection ability as well as its short wavelength which can generate larger Doppler shift. Then short-time Fourier transform is applied to the raw signals to characterise micro-Doppler signatures. They adopt the DCNNs to deal with the spectrograms for human identification problem. The DCNNs can learn the necessary features and classification conditions from raw micro-Doppler spectrograms without employing any explicit features. While the traditional supervised learning techniques relying on the extracted features require domain knowledge of each problem. It is shown that this method can achieve average accuracy ∼97.1% for 4 people, 90.9% for 6 people, 89.1% for 8 people, 85.6% for 10 people, 77.4% for 12 people, 72.6% for 16 people and 68.9% for 20 people.

RETRACTED: Gait Analysis of Pedestrians with the Aim of Detecting Disabled People

Gait classification is an effective and non-intrusive method for human identification and it has received significant attention in the recent years due to its applications in visual surveillance and monitoring systems. In this project, we analysed gait signatures using spatio-temporal motion characteristics of a person to answer the question ``is there a discriminating feature in gait signal that can help to categorise disable person from healthy''. The procedure has three steps. detection of a pedestrian using YOLO followed by the silhouette extraction using the Gaussian Mixture Model (GMM). Finally, skeletonization from the silhouette image to estimate head and torso locations and their angles with the vertical axis. Furthermore, velocity and acceleration signals were recorded to look for accelerating behaviour of person walking with a limp.

Development and validation of a formula based on maxillary sinus measurements as a tool for sex estimation: a cone beam computed tomography study.

As sex estimation is an important step to delineate the biological profile, the development of tools employing anatomical structures which may maintain their integrity even after extreme events, such as the maxillary sinus, become useful for forensic identification. Thus, the aim in the present study was to develop and validate a formula for sex estimation through measurements in the maxillary sinuses in a Brazilian population, using cone beam computed tomography (CBCT) scans. Linear and volumetric measurements in the maxillary sinus were performed bilaterally in 94 CBCT scans from 45 males (mean age 25.2 ± 0.79) and 49 females (mean age 23.7 ± 0.50). The OnDemand 3D software was employed for linear measurements (height, length and width of, and the largest distance between the right and left maxillary sinuses), while the ITK-SNAP 3.0 segmentation software was used to acquire the volume. The data obtained was applied to a mathematical model for sex estimation. To validate the developed formula, another sample composed of 60 CBCT images of Brazilian individuals was tested. Overall, maxillary sinuses' measurements were significantly higher in males, without statistically significant differences between the right and left sides within each group. The most dimorphic measurement was the height, with an accuracy of 77.7% regarding sex estimation. The formula created lead to a sex estimation of 87.8% for females and 80% for males, with an overall accuracy of 84%. When the formula validity was tested in another sample, it showed an accuracy of 82.4%. The formula developed through measurements in the maxillary sinus using CBCT scans showed an accuracy of 84% for sex estimation and can be applied as a complementary method for human identification in the Brazilian population.

Dental Evidence as a Sole Human Identifier in World Disasters: A Literature Review with Emphasis on the 2004 Tsunami Disaster

Comparative dental analysis is a quick and relatively simple human identification method. In many disaster incidents, dental characteristics have played an important role in establishing the identity of victims when they were visually unidentifiable. A PubMed search was conducted for publications that specifically discussed the role of dental characteristics in Disaster Victim Identification (DVI). Between 1974 and 2012, 14 papers described 17 disasters in which dental characteristics were used to identify the victims. The percentage of victims identified using only dental characteristics ranged from 0% to 89%. This wide range largely depends on the availability and quality of ante mortem dental records provided by dentists. The DVI in Thailand following the Indian Ocean tsunami in December 2004 was unique in involving deceased tourists from more than 30 countries, mostly from Europe. The dental method of identification showed superiority over other identification methods in terms of speed and accuracy of establishing the victims’ identity. This paper discusses the role of forensic odontology in establishing the identity of disaster victims, with specific emphasis on the 2004 Indian Ocean tsunami as an example of good practice, during which the author had first-hand experience.

Human Brain Biometric Identification Method by Extraction of Brain Print

Identification of a human being through visual structural features face challenge of forgery. The hidden biometrics is comparatively recent yet it has appeared as optimistic modality for security. We believe that the distinguishing feature among human is the brain so qualifying and quantifying the uniqueness in structure of the brain should lead to subject identification. Previously, brain signals have been used for biometrics but like behavioral biometrics these can be deceiving. In this paper, we concentrate on extraction of concrete structural features from human brain which are non-deceivable. Our aim is to extract non-linear curves having approximate brain structural information instead of considering brain to be of predefined abstract regular shapes. The results are optimistic as we are able to extract enough number of brain curves from a securely selected slice from complete brain map ensuring the scalability of the approach.

A mini-multiplex SNaPshot assay for the triage of degraded human DNA

Short Tandem Repeat (STR) genotyping is currently the primary DNA-based method for human identification, however it can have limited success when applied to degraded human remains. Massively parallel sequencing (MPS) provides new opportunities to obtain genetic data for hundreds of loci in a single assay with higher success from degraded samples. However, due to the extra requirement for specialised equipment, expertise and resources, routine use of MPS may not be feasible or necessary for many forensic cases. Here we describe the development of a mini-multiplex SNaPshot screening tool (Miniplex) for human samples which allows the qualitative comparison of short mitochondrial and nuclear DNA targets, as well as the interrogation of biogeographic ancestry, lineage, and phenotype single nucleotide polymorphisms (SNPs). This tool is useful to triage samples based on sample quality prior to downstream identification workflows and provides broad biological profile data for intelligence purposes.

個人識別を目的としたパラフィン包埋組織からのDNA抽出法の比較

Formalin-fixed paraffin-embedded (FFPE) tissues are one of the most effective tools for human identification in forensic science. To evaluate the effectiveness for human identification, we compared the following six methods for the extraction of DNA from FFPE tissues; EZ1 DNA Investigator Kit, ReliaPrep FFPE gDNA Miniprep System, DNA Isolator PS-Rapid Reagent, QIAamp DNA FFPE Tissue Kit, NucleoSpin DNA FFPE XS and phenol-chloroform method. DNA extracted using each method from two FFPE tissue blocks were quantified by three different DNA quantification methods (Quant-it dsDNA HS Assay Kit and quantitative PCR based on 207 bp and 98 bp regions in the D17Z1 locus), and short tandem repeat (STR) typing using AmpFlSTR Identifiler Plus PCR Amplification Kit was conducted. All extracts from the FFPE tissues were highly degraded, and large differences were observed among total DNA yields determined by these three quantification methods. DNA obtained using QIAamp DNA FFPE Tissue Kit had the highest total DNA yield among all the quantification methods. In STR typing with 1 ng DNA template estimated by quantitative PCR based on 98 bp region in the D17Z1 locus, the greatest number of detected alleles was observed using QIAamp DNA FFPE Tissue Kit. In contrast, EZ1 DNA Investigator Kit and DNA Isolator PS-Rapid Reagent were inferior to the other methods in terms of the DNA yield and the number of detected alleles via STR typing. In conclusion, QIAamp DNA FFPE Tissue Kit was the most effective method for human identification from FFPE tissues among the other DNA extraction methods, considering the results of this study, its cost-effectiveness, and universal use for forensic science.

3D palmprint identification combining blocked ST and PCA

Three dimensional (3D) palmprint technologies have been widely studied as a method of human identification and recognition, because they offer unique merits over their 2D counterpart. To overcome the limitations of small sample sizes and low one-to-many identification speed, a novel method by combining the blocked surface type (ST) feature and principal component analysis (PCA) has been developed for 3D palmprint identification. This method adopts the histogram of blocked ST as an effective palmprint feature, thus reducing the subsequent computational complexity. The dimensionality of the data is reduced using the histogram method, and the 3D information is further compressed using PCA. A nearest neighbor classifier acts as the discrimination criterion for identifying a person. Experimental results using two databases demonstrate the effectiveness of the proposed method. Compared with other single-feature methods, the proposed approach overcomes the traditional problem of small sample sizes, reduces the computational complexity, and enables accurate, fast, and robust identification. Therefore, the proposed method is especially suitable for large-scale databases.

Beyond the STRs: A comprehensive view of current forensic DNA markers characterized in the PCR-based DNA profiling standard SRM 2391D

Capillary electrophoresis (CE) of the Combined DNA Index System (CODIS) core set of 20 Short Tandem Repeat (STR) markers [1] is the primary genotyping method for forensic human identification in the U.S. With the emergence of new technologies beyond CE testing, other categories of forensic DNA markers are now more readily available. The next iteration of the PCR-Based DNA Profiling Standard Reference Material, SRM 2391d, will contain allele calls and sequence information for forensically relevant markers available in commercial kits. The SRM components will be characterized using CE and next-generation sequencing (NGS). With NGS technology, more data can be mined from these reference samples than previous generations of this SRM. This paper will focus on data from the forensic DNA markers beyond the common autosomal, Y-STR, and X-STR markers to include: insertion/deletions, ancestry single nucleotide polymorphisms (SNPs), identity SNPs, phenotypic SNPs, microhaplotypes and mitochondrial whole genome sequencing. The primary emphasis will be an analysis of the information gained from using NGS vs CE technology with the reference samples going “Beyond the STRs”.

Kennard-Stone combined with least square support vector machine method for noncontact discriminating human blood species

Identifying whole bloods to be either human or nonhuman is an important responsibility for import-export ports and inspection and quarantine departments. Analytical methods and DNA testing methods are usually destructive. Previous studies demonstrated that visible diffuse reflectance spectroscopy method can realize noncontact human and nonhuman blood discrimination. An appropriate method for calibration set selection was very important for a robust quantitative model. In this paper, Random Selection (RS) method and Kennard-Stone (KS) method was applied in selecting samples for calibration set. Moreover, proper stoichiometry method can be greatly beneficial for improving the performance of classification model or quantification model. Partial Least Square Discrimination Analysis (PLSDA) method was commonly used in identification of blood species with spectroscopy methods. Least Square Support Vector Machine (LSSVM) was proved to be perfect for discrimination analysis. In this research, PLSDA method and LSSVM method was used for human blood discrimination. Compared with the results of PLSDA method, this method could enhance the performance of identified models. The overall results convinced that LSSVM method was more feasible for identifying human and animal blood species, and sufficiently demonstrated LSSVM method was a reliable and robust method for human blood identification, and can be more effective and accurate.

Gait-based Human identification using acoustic sensor and deep neural network

This paper proposes a simple, fast and low-cost gait-based human identification system jointly employing an acoustic sensor system and a deep neural network (DNN) based algorithm to process acoustic data for human identification. The acoustic sensor system is employed to detect and acquire individuals’ gait signatures. Compared with the conventional radar based and video/image based human gait identification technologies, our acoustic sensor system is low-cost and feasible in some special cases, such as in private rooms/hotels or in the night time. We perform identification using a DNN which consists of an auto-encoder and a feed-forward neural network. The experimental results demonstrate that the integrated system of acoustic sensor and DNN considerably improves the system’s performance, which achieves an excellent accuracy rate of 97% for human identification. Aside from the high accuracy of the gait-based human identification, the novel system we developed is also capable of identifying human actions (walk, jog, run, jump, etc.) and the human number which has not been addressed in the literature, thereby significantly enhancing the wide adaptability of our identification system in various applications. Additionally, to better enhance the performance of the proposed human identification method, a large feature set, variable-length frame size and variable-dimension feature vectors are exploited in our identification system. The presented work provides prospects in developing high-performance identification system for large-scale security applications via a simple and efficient technique.

Validation study of a new method for sexual prediction based on CBCT analysis of maxillary sinus and mandibular canal

ObjectiveThe aim of this study was to evaluate the accuracy of two craniometric methods for sexual prediction (SP) using cone-beam computed tomography (CBCT) in the Dutch population and to construct a formula for each method and then the two combined. DesignOne-hundred sixty CBCT images were selected from a Dutch database (80 males and 80 females). The images were analyzed by two examiners taking seven measurements in the maxillary sinus (MS) region (first method) and nine in the mandibular canal (MC) region (second method). The most predictive measurements in both methods were used to develop an equation to determine the accuracy of each method. ResultsAll measurements showed statistical difference between genders. Logistic regression results showed two variables with greater SP index with 75% accuracy in the first method and four variables with 71.9% accuracy in the second. The two methods combined showed another four variables with 78.5% accuracy. ConclusionAll measurements showed statistically significant differences between sexes. The SP accuracy values were 75% for first 71.9% for the second method. When the two methods were combined, the accuracy increased to 78.5%. The formulas developed in this study can be applied as a complementary method for human identification in the Dutch population.

Labelled prosthesis linked to aadhaar card id- a reliable method of human identification in forensic odontology

Personal identification in natural and manmade disasters can be made by using methods like DNA analysis, finger prints, carbon 14 enamel dating, rugaescopy, cheiloscopy, skull shape and size, dental structure chart and various denture labeling methods. Implementations of labelled dentures system linked with AADHAAR CARD, a unique identification card of India citizen can be important in identifying people who have lost their memory or in states of unconsciousness or in identifying the bodies of those who have died in natural calamity, disasters, accident etc. Identification is an essential issue in all medico legal investigation because a wrong identity may pose a problem in delivering justice. Positive identification through labelled dentures plays a key role in forensic odontology. A number of labeling systems are available and are broadly classified into either surface marking methods or inclusion methods. This article describes various methods involved in labeling dentures and suggests unique method of labelling dentures linked with Aadhaar ID card in India. Keywords: Denture labeling, Surface methods, Inclusion methods, Aadhaar card ID

Human Identification Method Using Features Extraction of Non-fiducial Point

Human Identification Method Using Features Extraction of Non-fiducial Point

Estimation of gender using cheiloscopy and dermatoglyphics.

Background and Objective:Forensic dentistry plays a vital role in detection and resolution of crime, civil proceedings and personal identification. With ever-increasing demands placed upon law enforcement to provide sufficient physical evidence linking a perpetrator to a crime, it makes sense to utilize any type of physical characteristic to identify a suspect of an offense. The least invasive and cost-effective procedure among all methods of human identification is the study of lip prints and fingerprints. This study is done to determine the predominant pattern of fingerprint and lip print in males and females and to correlate it for gender identification.Materials and Methods:The study sample comprised 100 individuals (50 males and 50 females) aged between 20 and 50 years; dark-colored lipstick was applied uniformly on the lips. The glued portion of cellophane tape was dabbed first in the center and then pressed uniformly over the corner of lips. Cellophane tape was then stuck to a white chart sheet for the purpose of permanent record. Lip print patterns were analyzed following the classification of Suzuki and Tsuchihashi. The imprint of left thumb was taken on a white chart sheet using a blue ink stamp pad and visualized using magnifying lens. Fingerprints were analyzed by following the classification given by Kücken. Correlation of lip print and fingerprint was analyzed using Chi-square test.Results:The overall correlation of lip prints with fingerprints in males revealed branched lip pattern associated with whorl fingerprint and in females as vertical lip print pattern associated with loop fingerprint.Conclusion:We conclude that the study between lip print and fingerprint can aid in gender determination.

Genetyka i daktyloskopia – konkurenci czy sojusznicy

For nearly hundred years, dactyloscopy - as the most effective method of human identification, was treated as the queen of all forensic examination. With the emergence of genetic analysis, particularly when a huge progress in molecular biology and genetics resulted in a more extensive scope of application of biological evidence, the rank of dactyloscopy appears to dissipate. Currently the question is whether it will be completely ruled out of practice or could be utilized alongside genetic examination. For the purpose of verification of theoretical assumptions concerning comprehensive DNA/fingerprint examination opinions and in order to identify potential mistakes which can occur in practice, the analysis of 122 comprehensive opinions from DNA/fingerprint casework examinations was carried out in relation to five police forensic laboratories in Poland in the period between 2010-2013.

Fenomen identyfikacji genetycznej

DNA identification, which counts a few decades only, has revolutionized forensic science. Over a short period of time, genetic identification has become the most effective method of human identification, even when a tiny amount of biological material is available. Its dynamic development has allowed shifting efforts from group to individual identification. DNA analysis is broadly used for identification of criminal offenders, and due to computer-based DNA data bases – also allows detection of offenders internationally. The technique is fundamental in identification of disaster victims and also historically – in identification of bone remains. Furthermore, it is very useful in verification of wrongful convictions. In civil litigation, DNA analysis is irreplaceable in cases involving paternity testing. Genetic identification has quite solid scientific foundations and therefore, it has dethroned fingerprint identification, being earlier recognized as the “golden” standard of human identification. What is more, DNA analysis triggered the wave of criticism towards the majority of forensic methods of identification, which are considered to be characteristic by a high level of subjectivity, and which started the process of scientific development of these methods.