Human Identification System Research Articles

Genetic analysis of old skeletal remains from Korean War victims using PowerPlex® Fusion 6C and MiniSTR system for human identification

To analyze and identify the population of the Korean War victims by studying degraded old bones based genetic analysis, we examined 108 unrelated individual femurs except two low quality bones from total investigated 110 samples. In order to obtain significantly improved genetic profiles, amplification was performed using recently developed commercial PowerPlex® Fusion 6C system and miniSTR system. We have modified PCR condition to gain enhanced DNA profiling at a success rate. When each value of two different systems came out respectively as 92.35% and 91.05% only, it created 4.40% increased value which rated at 95.45% by using these two systems simultaneously. Especially, 100% showed at D1S1656, D2S441 and D12S391, which overlapped with miniSTR system. Total of 24 autosomal STRs had gene diversity values from 0.7751 to 0.9934; SE33, Penta E, and D2S1338 which were the best in that order. The most frequent value was 0.5170 at TPOX(8) in the frequencies ranging from 6 to 37 allele. Polymorphism information content, power of discrimination and exclusion, typical paternity index and heterozygote were the highest value at SE33, but TPOX appeared the lowest in all statistics. However the value of matching probability and homozygote showed the opposite result. Since above data anticipate that these outcomes confirm the similar patterns compared to previous reported Korean population papers, it verifies the population based genetic analysis using advanced these two systems is very helpful to increase an efficiency as well as a higher accuracy on identification of victims and also to check of identical samples.

SmartITS: Smartphone-based identification and tracking using seamless indoor-outdoor localization

Localization in both indoor and outdoor environments is a long-studied problem. Using Smartphone for localization has also gained popularity recently. However, none of the existing solutions consider seamless localization and tracking of individuals in both indoor and outdoor stretches with significant accuracy. In this paper, we propose a human identification, monitoring, and location tracking system, called SmartITS, which continuously tracks MAC ids of user equipment (Smartphones, BLE tags, and Bluetooth devices) and can provide a Google map-based visualization of their trajectories. Our tracker is a portable mobile entity comprising of a Smartphone and an external Wi-Fi adapter which does not require any extra hardware infrastructure to deploy as well as does not need any modification in hardware design at all. Extensive testing with a prototype testbed system in densely populated areas shows that the SmartITS system can seamlessly track user trajectories in indoor and outdoor stretches with a high aggregate location accuracy which is up to 44.49% more accurate than the simple GPS based location tracking system. Our proof-of-concept prototype shows the usability of SmartITS architecture. We also perform several experiments for evaluating the Smartphone’s performance as a scanner and as a sensor tag.

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.

Low-Cost Intelligent Carpet System for Footstep Detection

Recently, significant activities have been focused on the research of human identification and tracking systems in different environments. In this context, this paper describes a novel design and construction methodology for a low-cost intelligent carpet system for footstep detection. The carpet consists of activated carbon nonwoven material sandwiched between a pair of cross-aligned conductive wires to form in situ piezoresistive sensors. The assembly is externally covered with textiles to form a regular carpet. An electronic interface device and data treatment system is developed to monitor human footstep action-based piezoresistive changes observed within the carpet. The system is further practically validated for human footstep detection, localization, and counting. To demonstrate the potential application in human foot-step-based tracking, seven Gait features were extracted from piezoresistance change profile formed by human walking on the carpet and subsequently, a walking signature has been introduced. It is anticipated that such an intelligent carpet that retains its flexibility and textile aesthetics can be a good alternative for the conventional textile carpet with auxiliary functionality and added value.

A New Automatic Gait Cycle Partitioning Method and Its Application to Human Identification

Gait cycle partitioning is very important prior to human gait analysis such as gait modeling, gait recognition, gait feature analysis, etc. In this paper, we propose a new automatic gait cycle partitioning method based on two kinds of simple gait representation. Then, the propose method is applied to find keyframe corresponding the rest position for gait-based human identification system. To demonstrate the validity of the proposed method, the CASIA gait dataset A and the SOTON gait database are used to evaluate the recognition performance of the gait recognition system identifying subjects using the decision level fusion based on majority voting.

Accurate Human Recognition by Score-Level and Feature-Level Fusion Using Palm–Phalanges Print

Here, a highly precise human identification system is developed using a newly proposed biometric trait—palm–phalanges print (PPP). For PPP, NSIT database has been used which includes palm–phalanges. This database consists of anterior hand images of fifty individuals with ten samples each. To crop the region of interest from hand samples to get palm–phalanges, database is preprocessed. First, it has been shown that each finger phalange can be used as a biometric modality and give moderate/sufficient performance for low-accuracy system. For feature extraction, histograms of oriented gradients, GMF feature, mean and AAD methods have been used. To further enhance the performance, score-level and feature-level fusion strategies are applied and compared. Score-level fusion is performed using different fusion rules. Next for feature-level fusion, five methods are used: (1) simple concatenate, (2) PCA feature fusion, (3) linear discriminant analysis feature fusion, (4) fusion codes and (5) supervised local-preserving canonical correlation analysis method. Receiver operating characteristics (ROC), equal error rate, area under the curve of ROC and decidability index (d) are used to show the performance of the system qualitatively and quantitatively.

Radio Biometrics: Human Recognition Through a Wall

In this paper, we show the existence of human radio biometrics and present a human identification system that can discriminate individuals even through the walls in a non-line-of-sight condition. Using commodity Wi-Fi devices, the proposed system captures the channel state information (CSI) and extracts human radio biometric information from Wi-Fi signals using the time-reversal (TR) technique. By leveraging the fact that broadband wireless CSI has a significant number of multipaths, which can be altered by human body interferences, the proposed system can recognize individuals in the TR domain without line-of-sight radio. We built a prototype of the TR human identification system using standard Wi-Fi chipsets with $3 \times 3$ multi-in multi-out (MIMO) transmission. The performance of the proposed system is evaluated and validated through multiple experiments. In general, the TR human identification system achieves an accuracy of 98.78% for identifying about a dozen of individuals using a single transmitter and receiver pair. Thanks to the ubiquitousness of Wi-Fi, the proposed system shows the promise for future low-cost low-complexity reliable human identification applications based on radio biometrics.

Validation study of a 15-plex rapid STR amplification system for human identification

Conventional PCR amplification requires approximately 3h to complete and thus does not meet the requirements of rapid DNA analysis. The purpose of this study was to validate a rapid 15-plex PCR system that can amplify 14 autosomal short tandem repeat (STR) loci (i.e., D6S1043, D21S11, D7S820, CFS1PO, D2S1338, D3S1358, D13S317, D8S1179, D16S539, Penta E, D5S818, vWA, D18S51, and FGA) and Amelogenin. This system was validated by sensitivity, species specificity, inhibitor tests, sizing accuracy, stutter calculation, concordance tests, DNA mixture, and case sample tests according to the Scientific Working Group for DNA Analysis Methods (SWGDAM) guidelines and Chinese criteria. We found that the rapid 15-plex PCR system could shorten the amplification time to 37min and proved that it provides an alternative method for conventional PCR in human identification detection.

Development of a polymorphic short tandem repeat locus multiplex system for efficient human identification.

This study aimed to develop a short tandem repeat (STR) multiplex system, made up of 22 highly informative STR loci, for application in forensic genetics. The system comprised 21 polymorphic autosomal loci (D3S1358, TH01, D21S11, D18S51, Penta E, D5S818, D13S317, D7S820, D16S539, CSF1PO, Penta D, vWA, D8S1179, TPOX, FGA, D2S441, D17S1301, D19S433, D18S853, D20S482, and D14S1434) and the amelogenin gene locus. Strategies were developed to overcome the challenges involved in creating a multiplex system. Based on the literature and available databases, the STR loci were selected with the aim to obtain discriminatory markers, and followed specific criteria for this purpose. Primers were projected using the Primer3 software, and AutoDimer was used to evaluate possible interactions between them. The 22 selected STR loci were validated individually and jointly, both to assess their sensitivity and to test the efficiency of the multiplex system. Statistical analyses were based on the genetic data of 450 unrelated individuals living in the State of Goiás, thus allowing the establishment of the parameters necessary to use this system. A total of 239 alleles were detected for the 22 loci in the set, allowing for a probability of identity of 4.23 x 10-25 to be obtained. The combined power of discrimination was 0.999999999999999999999999 and the combined power of exclusion was 0.99999. Upon complete validation of the entire system, this multiplex assay was considered to be a powerful tool for application in human identification by DNA analysis.

Dental X-Ray Based Human Identification System for Forensic

Forensic dentistry is an important branch of the forensic science. It is based on the dental characteristic. This method uses the dental features as a biometric tool to identify persons, who their bodies have been affected badly. In the other meaning, the dental biometrics are considered at the absence of tools, such as, DNA, fingerprint, iris etc. for different reasons. This paper presented a biometric system for forensic human identification based on dental X-ray. The aim of this system is to build a database, which contain ante-mortem dental radiograph features (AM), used later for matching with the post-mortem dental radiograph features (PM). These features are Standard Deviation (STD), Euler number and Area extracted from X-ray image of type bite-wing. The investigated X-Ray image goes through three stages algorithm which are: image segmentation, classification and features extraction. The obtained features represents the records of the system database for each tooth individually in distinct person. The proposed system utilizes the Graphical User Interface (GUI) provided from the Visual Studio with the usage of MATLAB software for feature extraction and the SQL Server 2012 environment for database building. The Achieved results show the outperformance of the proposed system in terms of matching and searching accuracy as well as the finding time. In addition the editing and insertion processes are performed in high accuracy and efficiency.

Human Gait identification System

Few biometrics can be used to recognize a person from distance without need for direct sharing or cooperation of that person, gait (walking behavior) is one of them. Walking behavior (gait) recognition includes specifying person identity by analyzing his walking style (walking manner). In this paper, a human gait identification system depending on extracted features, which are vertical hip, horizontal hip angle and slop of thigh. The first step of the proposed system is detecting the binary silhouette of a walking individual from the uploaded videos. Then, the gait cycle is allocated using aspect ratio method. Finally, the required features from each frame in gait cycle are extracted. Different image processing operation have been performed to extract the required features. The outcome of the proposal system reflects flexibility in term of inserting, searching, updating, deleting and matching. The proposed system is tested in terms of offered functions, human recognition and noise effects. The obtained results show the efficient performance of the system and high ability of covering the error caused by surrounding conditions. The system is evaluated using the matching rate with the threshold of 70%. The adding noise can degrade the matching rate, particularly for high variance values. This is because of the increasing of noise values that might be the reason of moving the object irregularly while capturing or unexpected changing in the effected surrounding conditions.

Walking Behavior Based Human Recognition System

In the recent period with the growing need for surveillance system, people looking for suitable method to identify person. Depending on the features of biometric that can specify human identity by using identification and verification functions. The verification process is done by compare the biometric features such as, fingerprint, iris, face recognition, etc., with a record stored previously. While the identification process is performed by find the best match between the biometric features and all records kept in a database. Walking behavior recognition is the only biometric that can specify an individual identity at distance that relying on walking behavior features such as step length, angle of hip and knee, etc. In this paper we propose a biometric based human identification system depending on walking behavior characteristic which is vertical hip angle, horizontal hip angle and slop of thigh that extract from captured picture of person. A database of numerous people has been used. A database has been constructed using SQL server software environment in which person identification performed with high efficiency. The outcome of the proposal system reflects flexibility in term of inserting, searching, updating, deleting and matching.

X-HuBIS: A Fuzzy Rule based Human Behaviour Identification System based on Body Gestures

Objectives: In this paper, an attempt is made to identify the behaviour of human based on his/her body gesture. Body gesture recognition is very important and prime feature to detect the behaviour of the human being so behaviour and frame of mind of any person can be judged from one’s body gesture. Methods/Statistical Analysis: Our proposed system captures an image of a person and recognizes different gestures related to head, hands and legs positions. The different types of rules are defined in fuzzy system that will produce the behaviour and mood after analysing the captured image with knowledge base. Findings: The result is produced in the form of classes which tells the behavior and other characteristics of the person. There are 3 main classes that describe the behavior of the person that is: Positive mood, Negative mood and Neutral mood. These three gestures are matched in the database. Name of gestures are passed to fuzzy system and fuzzy system will produce the result. Application/Improvements: This system can be used to identify the behavior of a person. So it can be used to identify any criminals and terrorists.This proposed system can be used to analyse psychological behaviour of human being which may help in different medical treatments.

Evaluation of the RapidHIT™ 200 and RapidHIT GlobalFiler® Express kit for fully automated STR genotyping

The RapidHIT™ 200 Human Identification System and RapidHIT GlobalFiler® Express kit were evaluated and validated for use with single-source reference samples. It was of primary interest to evaluate the system for its efficacy as an expert system and to estimate a first pass success rate, as well as to identify the technical variables impacting that result. While results indicated that this instrument/kit combination can be used to accurately type single-source buccal samples, substantial variability in sensitivity and intra-color balance were observed, as were multiple artifacts, requiring extensive manual editing of the profiles. Artifacts included dye “blobs” and spectral overlap (pull-up) peaks that often originated from relatively low intensity allele peaks. Reduced intra-color balance, in combination with low sensitivity, occasionally resulted in instances of allelic dropout. Overall, 50% of the buccal samples analyzed in this study would have been successfully typed to give full GlobalFiler® profiles without the need for manual review and editing.

PiSHi: click the images and I tell if you are a human

This paper introduces pictorial intelligent system for human identification (PiSHi), an image-based captcha which uses three human cognitive abilities to distinguish humans from machines. The first is the human ability to easily recognise the image’s upright orientation. The second is the human brain’s ability in recognising a picture’s content when it is only partially visible. And the third is the human ability in unconscious decision making when encountering pictorial challenges. This work models such complicated human patterns in problem solving for the first time. In order to extract these behavioural patterns and save them in a pattern database, we have implemented our own captcha and performed a series of experiments. PiSHi’s interface presents the user with a set of distorted pictures and asks her to click on the upright orientation of all the pictures in any preferred order. Next, it captures the user’s interaction patterns, compares them with the ones saved in the pattern database, and grants her a corresponding credit. Based on this credit, the user either passes or fails the test, and participates in updating the picture database. Our experiments indicate that human users can solve our proposed captcha effectively—with an accuracy of 99.44 %. Besides, our proposed system is secure against several types of attacks including random guessing and reverse image search engines. The results offer the possibility of utilising the identified human behavioural models in practical captchas.

Ear Features based Human Identification System

Biometric features such as fingerprint, Iris were considered in the past for human identification. Ear biometrics can be considered as a new class of human identification system. The performance of ear biometric system mainly depends on proper segmentation of ear from the image and the feature extracted from the segmented ear image. It is observed from the literature, that most of the ear identification methods are not automatic. It needs user intervention in segmenting the ear from the image in order to process further. In this paper, an approach for fully automated ear segmentation and “Adaptive blocks” based feature extraction technique was proposed. Along with the extracted features, the Histogram of Oriented Gradients (HOG) features will be extracted from the ear image. The human will be identified by designing a suitable Artificial Neural Network (ANN) with the extracted ear features as the inputs and the image index as the targets. The performance of the network will be studied with different test ear images.

A centrifugal microfluidic device with integrated gold leaf electrodes for the electrophoretic separation of DNA.

Current conventional methods utilized for forensic DNA analysis are time consuming and labor-intensive requiring large and expensive equipment and instrumentation. While more portable Rapid DNA systems have been developed, introducing them to a working laboratory still necessitates a high cost of initiation followed by the recurrent cost of the devices. This has highlighted the need for an inexpensive, rapid and portable DNA analysis tool for human identification in a forensic setting. In order for an integrated DNA analysis system such as this to be realized, device operations must always be concluded by a rapid separation of short-tandem repeat (STR) DNA fragments. Contributing to this, we report the development of a unique, multi-level, centrifugal microdevice that can perform both reagent loading and DNA separation. The fabrication protocol was inspired by the print, cut and laminate (PCL) technique described previously by our group, and in accordance, offers a rapid and inexpensive option compared with existing approaches. The device comprises multiple polyester-toner fluidic layers, a cyclic olefin copolymer separation domain and integrated gold leaf electrodes. All materials are commercially-available and complement the PCL process in a way that permits fabrication of increasingly sought after single-use devices. All reagents, including a viscous sieving matrix, are loaded centrifugally, eliminating external pneumatic pumping, and the sample is separated in <5 minutes using an effective separation length of only 4 cm (reagent loading to completed separation, is <37 minutes). The protocol for gold leaf electrode manufacture yielded up to 30 electrodes for less than $3 (cost of a 79 mm × 79 mm gold leaf sheet) and when using a device combining these electrodes and centrifugal reagent/polymer loading, the electrophoretic separation of STR fragments with two base resolution was demonstrated. This exemplary performance makes the device an ideal candidate for further integration and development of an inexpensive, portable and rapid forensic human identification system.

Forensic parameters of the Powerplex® 21 system (Promega Corp.) in mestizo populations from the West of Mexico

IntroductionMicrosatellites or short tandem repeats (STR) are the markers of choice in human identification. For this purpose, they must be analyzed in populations. This task has been scarcely performed for new generation human identification systems, which is critical in Mexican mestizo populations, because a significant genetic structure has been demonstrated due to admixture differences. ObjectiveTo validate the system in mestizo populations from the west region of Mexico. MethodsA total of 374 unrelated Mexican-mestizos from the west region were analyzed with the Powerplex® 21 system. Genetic data were analyzed using different softwares and including additional related populations for comparison purposes. Results and conclusionsWe estimated allele frequencies, and genotype distribution of all markers was in agreement with Hardy-Weinberg expectations; the linkage disequilibrium test discarded association between all pair of loci. The following forensic parameters were estimated: power of discrimination (PD), power of exclusion (PE), heterozygosity (Het), polymorphism information content (PIC), and typical paternity index (PI); its combined power of discrimination and exclusion was –100% and 99.999999473%, respectively. This constitutes an important increment with respect to typical 15 STR systems for the same population/region. This report validates the Powerplex® 21 system in western Mexican-mestizos for confident interpretation of DNA profiles in forensic cases and paternity testing. Sistema Powerplex® 21; México; Identificación humana; Poblaciones.

Non-invasive Multi-modal Human Identification System Combining ECG, GSR, and Airflow Biosignals

A huge amount of data can be collected through a wide variety of sensor technologies. Data mining techniques are often useful for the analysis of gathered data. This paper studies the use of three wearable sensors that monitor the electrocardiogram, airflow, and galvanic skin response of a subject with the purpose of designing an efficient multi-modal human identification system. The proposed system, based on the rotation forest ensemble algorithm, offers a high accuracy (99.6 % true acceptance rate and just 0.1 % false positive rate). For its evaluation, the proposed system was testing against the characteristics commonly demanded in a biometric system, including universality, uniqueness, permanence, and acceptance. Finally, a proof-of-concept implementation of the system is demonstrated on a smartphone and its performance is evaluated in terms of processing speed and power consumption. The identification of a sample is extremely efficient, taking around 200 ms and consuming just a few millijoules. It is thus feasible to use the proposed system on a regular smartphone for user identification.

On designing an unconstrained tri-band pupil detection system for human identification

The majority of facial recognition systems depend on the accurate location of both the left and right eye centers in an effort to geometrically normalize the face images available in a database under study. In this paper, we propose a novel pupil detection algorithmic approach that automatically and efficiently locates the eye centers of face images captured using visible and infrared sensors when operating under challenging conditions. Our proposed approach includes the usage of long-range and night-time face images captured in the infrared (IR) band under active illumination. It also efficiently deals with partial face obstruction (subjects wearing eye glasses) as well as face pose and illumination variation. Our scenario-adaptable methodological approach involves a number of algorithmic steps, including (i) situation classification (to automatically determine the acquisition scenario each input face image is coming from), (ii) generation and usage of 2D normalized correlation coefficients, (iii) prediction of eye localization, (iv) computation of summation range filters for accurate pupil detection, and an (v) eye glasses classifier on facial images using support vector machines (to determine when subjects are wearing glasses or not). Our proposed approach is compared against state-of-the-art academic and commercial eye detection algorithms, including the (a) Viola and Jones Adaboost method, (b) one of the latest academic eye detection algorithms proposed by Valenti and Gevers (IEEE TPAMI), and (c) the eye detection approach that is available as part of the G8 commercial face recognition software (package provided by L1 systems). Experimental results demonstrate that our proposed approach outperforms all other approaches when applied on various challenging face datasets, including IR face images captured behind tinted glass or at long ranges up to about 350 feet away, day or night. We also show the benefits of our approach to face normalization and, as a result, face recognition improvement performance in terms of rank-1 identification rates. This is an important achievement that has practical value for forensic tool operators who may have to manually localize the eye centers of all face images available in a dataset, before further face image preprocessing and face-based matching algorithms can be applied.