Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 576
Filtrar
1.
Medicine (Baltimore) ; 100(1): e23960, 2021 Jan 08.
Artigo em Inglês | MEDLINE | ID: mdl-33429756

RESUMO

BACKGROUND: Rotator cuff injury is the most common cause of shoulder dysfunction. Despite the continuous advancement of surgical techniques, the incidence of re-tearing after rotator cuff repair is still high. The main reason is that it is difficult to reconstruct the normal tendon bone interface and the process is slow, and the application of tissue engineering technology can promote tendon and bone healing. This study will evaluate the effect of the bionic double membrane stent on the rotator cuff healing after arthroscopic rotator cuff repair. METHODS: This is a prospective randomized controlled trial to study the effect of biomimetic double-layer biofilm stent on rotator cuff healing. Approved by the clinical research ethics committee of our hospital. The patients were randomly divided into 1 of 2 treatment options: (A) a biomimetic double-layer biofilm stent group and (B) a non-bionic dual-layer biofilm stent group. Observation indicators include: visual analog scale score, University of California Los Angeles score, American Shoulder & Elbow Surgeons score and Constant-Murley score. Data were analyzed using the statistical software package SPSS version 16.0 (Chicago, IL). DISCUSSION: This study will evaluate and evaluate the effect of the bionic double-layer membrane stent on the rotator cuff healing after arthroscopic rotator cuff repair. The results of this experiment will provide new treatment ideas for promoting rotator cuff tendon bone healing. OSF REGISTRATION NUMBER: DOI 10.17605/OSF.IO/FWKD6.


Assuntos
Biofilmes , Identificação Biométrica/instrumentação , Protocolos Clínicos , Lesões do Manguito Rotador/cirurgia , Idoso , Identificação Biométrica/métodos , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Estudos Prospectivos , Ensaios Clínicos Controlados Aleatórios como Assunto , Resultado do Tratamento
2.
BMC Bioinformatics ; 21(Suppl 21): 514, 2020 Dec 28.
Artigo em Inglês | MEDLINE | ID: mdl-33371876

RESUMO

BACKGROUND: Fingerprint biometrics play an essential role in authentication. It remains a challenge to match fingerprints with the minutiae or ridges missing. Many fingerprints failed to match their targets due to the incompleteness. RESULT: In this work, we modeled the fingerprints with Bezier curves and proposed a novel algorithm to detect and restore fragmented ridges in incomplete fingerprints. In the proposed model, the Bezier curves' control points represent the fingerprint fragments, reducing the data size by 89% compared to image representations. The representation is lossless as the restoration from the control points fully recovering the image. Our algorithm can effectively restore incomplete fingerprints. In the SFinGe synthetic dataset, the fingerprint image matching score increased by an average of 39.54%, the ERR (equal error rate) is 4.59%, and the FMR1000 (false match rate) is 2.83%, these are lower than 6.56% (ERR) and 5.93% (FMR1000) before restoration. In FVC2004 DB1 real fingerprint dataset, the average matching score increased by 13.22%. The ERR reduced from 8.46% before restoration to 7.23%, and the FMR1000 reduced from 20.58 to 18.01%. Moreover, We assessed the proposed algorithm against FDP-M-net and U-finger in SFinGe synthetic dataset, where FDP-M-net and U-finger are both convolutional neural network models. The results show that the average match score improvement ratio of FDP-M-net is 1.39%, U-finger is 14.62%, both of which are lower than 39.54%, yielded by our algorithm. CONCLUSIONS: Experimental results show that the proposed algorithm can successfully repair and reconstruct ridges in single or multiple damaged regions of incomplete fingerprint images, and hence improve the accuracy of fingerprint matching.


Assuntos
Identificação Biométrica/métodos , Dermatoglifia , Algoritmos , Humanos
3.
PLoS One ; 15(9): e0238872, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-32915850

RESUMO

Association between electroencephalography (EEG) and individually personal information is being explored by the scientific community. Though person identification using EEG is an attraction among researchers, the complexity of sensing limits using such technologies in real-world applications. In this research, the challenge has been addressed by reducing the complexity of the brain signal acquisition and analysis processes. This was achieved by reducing the number of electrodes, simplifying the critical task without compromising accuracy. Event-related potentials (ERP), a.k.a. time-locked stimulation, was used to collect data from each subject's head. Following a relaxation period, each subject was visually presented a random four-digit number and then asked to think of it for 10 seconds. Fifteen trials were conducted with each subject with relaxation and visual stimulation phases preceding each mental recall segment. We introduce a novel derived feature, dubbed Inter-Hemispheric Amplitude Ratio (IHAR), which expresses the ratio of amplitudes of laterally corresponding electrode pairs. The feature was extracted after expanding the training set using signal augmentation techniques and tested with several machine learning (ML) algorithms, including Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), and k-Nearest Neighbor (kNN). Most of the ML algorithms showed 100% accuracy with 14 electrodes, and according to our results, perfect accuracy can also be achieved using fewer electrodes. However, AF3, AF4, F7, and F8 electrode combination with kNN classifier which yielded 99.0±0.8% testing accuracy is the best for person identification to maintain both user-friendliness and performance. Surprisingly, the relaxation phase manifested the highest accuracy of the three phases.


Assuntos
Algoritmos , Identificação Biométrica/métodos , Encéfalo/fisiologia , Eletroencefalografia/métodos , Potenciais Evocados , Processamento de Imagem Assistida por Computador/métodos , Aprendizado de Máquina , Adulto , Análise Discriminante , Eletrodos , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Estimulação Luminosa , Máquina de Vetores de Suporte , Adulto Jovem
5.
Neural Netw ; 130: 238-252, 2020 Oct.
Artigo em Inglês | MEDLINE | ID: mdl-32707412

RESUMO

In the last few years, human age estimation from face images attracted the attention of many researchers in computer vision and machine learning fields. This is due to its numerous applications. In this paper, we propose a new architecture for age estimation based on facial images. It is mainly based on a cascade of classification trees ensembles, which are known recently as a Deep Random Forest. Our architecture is composed of two types of DRF. The first type extends and enhances the feature representation of a given facial descriptor. The second type operates on the fused form of all enhanced representations in order to provide a prediction for the age while taking into account the fuzziness property of the human age. While the proposed methodology is able to work with all kinds of image features, the face descriptors adopted in this work used off-the-shelf deep features allowing to retain both the rich deep features and the powerful enhancement and decision provided by the proposed architecture. Experiments conducted on six public databases prove the superiority of the proposed architecture over other state-of-the-art methods.


Assuntos
Envelhecimento , Identificação Biométrica/métodos , Aprendizado Profundo , Estimulação Luminosa/métodos , Bases de Dados Factuais , Humanos , Aprendizado de Máquina
6.
Neural Netw ; 129: 43-54, 2020 Sep.
Artigo em Inglês | MEDLINE | ID: mdl-32563024

RESUMO

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.


Assuntos
Identificação Biométrica/métodos , Aprendizado de Máquina não Supervisionado/normas , Identificação Biométrica/normas , Aprendizado de Máquina não Supervisionado/economia
8.
Neural Netw ; 128: 294-304, 2020 Aug.
Artigo em Inglês | MEDLINE | ID: mdl-32470795

RESUMO

RGB-Infrared (IR) person re-identification is very challenging due to the large cross-modality variations between RGB and IR images. Considering no correspondence labels between every pair of RGB and IR images, most methods try to alleviate the variations with set-level alignment by reducing marginal distribution divergence between the entire RGB and IR sets. However, this set-level alignment strategy may lead to misalignment of some instances, which limit the performance for RGB-IR Re-ID. Different from existing methods, in this paper, we propose to generate cross-modality paired-images and perform both global set-level and fine-grained instance-level alignments. Our proposed method enjoys several merits. First, our method can perform set-level alignment by disentangling modality-specific and modality-invariant features. Compared with conventional methods, ours can explicitly remove the modality-specific features and the modality variation can be better reduced. Second, given cross-modality unpaired-images of a person, our method can generate cross-modality paired images from exchanged features. With them, we can directly perform instance-level alignment by minimizing distances of every pair of images. Third, our method learns a latent manifold space. In the space, we can random sample and generate lots of images of unseen classes. Training with those images, the learned identity feature space is more smooth can generalize better when test. Finally, extensive experimental results on two standard benchmarks demonstrate that the proposed model favorably against state-of-the-art methods.


Assuntos
Identificação Biométrica/métodos , Aprendizado de Máquina , Raios Infravermelhos
9.
PLoS One ; 15(5): e0232319, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-32369515

RESUMO

Aiming at the problem of fast certification for a constrained iris in the same category caused by the unstable iris features caused by the change of the iris acquisition environment and shooting status under lightweight training samples, a one-to-one fast certification algorithm for constrained unsteady-state iris based on the scale change stable feature and multi-algorithm voting is proposed. Scale change stable features are found by constructing an isometric differential Gaussian space, and a local binary pattern algorithm with extended statistics (ES-LBP), the Haar wavelet with over threshold detection and the Gabor filter algorithm with immune particle swarm optimization (IPSO) are used to represent the stable features as binary feature codes. Iris certification is performed by the Hamming distance. According to the certification results of three algorithms, the final result is obtained by multi-algorithm voting. Experiments with the JLU and CASIA iris libraries under the iris prerequisite conditions show that the correct recognition rate of this algorithm can reach a high level of 98% or more, indicating that this algorithm can improve the operation speed, accuracy and robustness of certification.


Assuntos
Algoritmos , Identificação Biométrica/métodos , Iris , Reconhecimento Automatizado de Padrão/métodos , Humanos , Processamento de Imagem Assistida por Computador/métodos
10.
Neural Netw ; 127: 82-95, 2020 Jul.
Artigo em Inglês | MEDLINE | ID: mdl-32344155

RESUMO

Field classification is a new extension of traditional classification frameworks that attempts to utilize consistent information from a group of samples (termed fields). By forgoing the independent identically distributed (i.i.d.) assumption, field classification can achieve remarkably improved accuracy compared to traditional classification methods. Most studies of field classification have been conducted on traditional machine learning methods. In this paper, we propose integration with a Bayesian framework, for the first time, in order to extend field classification to deep learning and propose two novel deep neural network architectures: the Field Deep Perceptron (FDP) and the Field Deep Convolutional Neural Network (FDCNN). Specifically, we exploit a deep perceptron structure, typically a 6-layer structure, where the first 3 layers remove (learn) a 'style' from a group of samples to map them into a more discriminative space and the last 3 layers are trained to perform classification. For the FDCNN, we modify the AlexNet framework by adding style transformation layers within the hidden layers. We derive a novel learning scheme from a Bayesian framework and design a novel and efficient learning algorithm with guaranteed convergence for training the deep networks. The whole framework is interpreted with visualization features showing that the field deep neural network can better learn the style of a group of samples. Our developed models are also able to achieve transfer learning and learn transformations for newly introduced fields. We conduct extensive comparative experiments on benchmark data (including face, speech, and handwriting data) to validate our learning approach. Experimental results demonstrate that our proposed deep frameworks achieve significant improvements over other state-of-the-art algorithms, attaining new benchmark performance.


Assuntos
Identificação Biométrica/métodos , Aprendizado Profundo , Redes Neurais de Computação , Reconhecimento Automatizado de Padrão/métodos , Algoritmos , Teorema de Bayes , Identificação Biométrica/tendências , Aprendizado Profundo/tendências , Escrita Manual , Humanos , Aprendizado de Máquina/tendências , Reconhecimento Automatizado de Padrão/tendências
11.
Sci Rep ; 10(1): 6639, 2020 04 20.
Artigo em Inglês | MEDLINE | ID: mdl-32313164

RESUMO

Thanatotranscriptome studies involve the examination of mRNA transcript abundance and gene expression patterns in the internal organs of deceased humans. Postmortem gene expression is indicative of the cellular status of a corpse at the time of death, a portion of which may represent a cascade of molecular events occasioned by death. Specific gene biomarkers identify perceptible transcriptional changes induced by stochastic responses to the cessation of biological functions. Transcriptome analyses of postmortem mRNA from a tissue fragment may determine unique molecular identifiers for specific organs and demonstrate unique patterns of gene expression that can provide essential contextual anatomical information. We evaluated the impact of targeted transcriptome analysis using RNA sequencing to reveal global changes in postmortem gene expression in liver tissues from 27 Italian and United States corpses: 3.5-hour-old to 37-day-old. We found that our single blind study using eight liver tissue-specific gene biomarkers (e.g. AMBP and AHSG) is highly specific, with autopsy-derived organ samples correctly identified as tissues originating from postmortem livers. The results demonstrate that 98-100% of sequencing reads were mapped to these liver biomarkers. Our findings indicate that gene expression signatures of mRNA exposed up to 37 days of autolysis, can be used to validate the putative identity of tissue fragments.


Assuntos
Identificação Biométrica/métodos , Fígado/metabolismo , RNA Mensageiro/genética , Transcriptoma , Adulto , Idoso , Idoso de 80 Anos ou mais , Autopsia , Cadáver , Feminino , Ciências Forenses , Perfilação da Expressão Gênica , Marcadores Genéticos , Sequenciamento de Nucleotídeos em Larga Escala , Humanos , Fígado/química , Masculino , Pessoa de Meia-Idade , RNA Mensageiro/classificação , RNA Mensageiro/metabolismo
12.
Sensors (Basel) ; 20(5)2020 Feb 28.
Artigo em Inglês | MEDLINE | ID: mdl-32121182

RESUMO

Image quality is a key issue affecting the performance of biometric systems. Ensuring the quality of iris images acquired in unconstrained imaging conditions in visible light poses many challenges to iris recognition systems. Poor-quality iris images increase the false rejection rate and decrease the performance of the systems by quality filtering. Methods that can accurately predict iris image quality can improve the efficiency of quality-control protocols in iris recognition systems. We propose a fast blind/no-reference metric for predicting iris image quality. The proposed metric is based on statistical features of the sign and the magnitude of local image intensities. The experiments, conducted with a reference iris recognition system and three datasets of iris images acquired in visible light, showed that the quality of iris images strongly affects the recognition performance and is highly correlated with the iris matching scores. Rejecting poor-quality iris images improved the performance of the iris recognition system. In addition, we analyzed the effect of iris image quality on the accuracy of the iris segmentation module in the iris recognition system.


Assuntos
Iris/fisiologia , Reconhecimento Fisiológico de Modelo/fisiologia , Algoritmos , Identificação Biométrica/métodos , Biometria/métodos , Bases de Dados Factuais , Humanos , Processamento de Imagem Assistida por Computador/métodos , Luz
13.
Sensors (Basel) ; 20(5)2020 Mar 02.
Artigo em Inglês | MEDLINE | ID: mdl-32131494

RESUMO

Face recognition functions are today exploited through biometric sensors in many applications, from extended security systems to inclusion devices; deep neural network methods are reaching in this field stunning performances. The main limitation of the deep learning approach is an inconvenient relation between the accuracy of the results and the needed computing power. When a personal device is employed, in particular, many algorithms require a cloud computing approach to achieve the expected performances; other algorithms adopt models that are simple by design. A third viable option consists of model (oracle) distillation. This is the most intriguing among the compression techniques since it permits to devise of the minimal structure that will enforce the same I/O relation as the original model. In this paper, a distillation technique is applied to a complex model, enabling the introduction of fast state-of-the-art recognition capabilities on a low-end hardware face recognition sensor module. Two distilled models are presented in this contribution: the former can be directly used in place of the original oracle, while the latter incarnates better the end-to-end approach, removing the need for a separate alignment procedure. The presented biometric systems are examined on the two problems of face verification and face recognition in an open set by using well-agreed training/testing methodologies and datasets.


Assuntos
Face/fisiologia , Reconhecimento Facial/fisiologia , Algoritmos , Identificação Biométrica/métodos , Biometria/métodos , Confidencialidade , Bases de Dados Factuais , Destilação , Humanos , Aprendizado de Máquina , Redes Neurais de Computação
14.
Rev. esp. med. legal ; 46(1): 12-19, ene.-mar. 2020. tab, graf
Artigo em Espanhol | IBECS | ID: ibc-193985

RESUMO

INTRODUCCIÓN: El objetivo de este estudio fue la obtención de funciones discriminantes para estimación del sexo a partir de mediciones directas en metacarpos y metatarsos para contribuir en la identificación de individuos desconocidos. MATERIAL Y MÉTODOS: Se analizaron métricamente los metacarpos y metatarsos de 112 esqueletos adultos contemporáneos (49 femeninos y 63 masculinos) de la Colección-UNAM del Laboratorio de Antropología Física, Facultad de Medicina, UNAM. Empleando un vernier digital se tomaron 5 medidas (longitud máxima y 4 anchuras) en cada uno de los huesos del metacarpo y del metatarso. RESULTADOS: Se desarrollaron 14 funciones discriminantes para los metacarpos, con porcentajes del 79,5% a 85,3% de asignación sexual correcta, siendo el segundo metacarpo el hueso más dimórfico de la muestra. Para el caso de los metatarsos se obtuvieron 5 funciones que van del 77,8% al 83,2% de certidumbre, siendo el primer metatarso el hueso más dimórfico. De manera general, las anchuras en ambas epífisis fueron las medidas más dimórficas. CONCLUSIONES: Las funciones discriminantes de metacarpos y metatarsos obtenidas presentan, de manera general, porcentajes por encima del 80%, lo cual concuerda con lo reportado para otras poblaciones; por lo tanto, pueden ser utilizadas en contextos forenses para la identificación humana, en restos completos o fragmentados, en el caso de no contar con otro elemento óseo, como la pelvis


INTRODUCTION: The aim of this study was to obtain discriminant functions for estimating gender from direct measurements of the metacarpal and metatarsal bones for identification of unknown individuals. MATERIAL AND METHODS: An analysis was performed on metacarpal and metatarsals bones of 112 adult contemporary skeletons (49 females and 63 males). The sample belongs to the Autonomous University of Mexico (UNAM) Collection from the Physical Anthropology Laboratory, UNAM Faculty of Medicine. Five measurements were taken (maximum length and four widths) of each metacarpal and metatarsal bones employing a digital calliper. RESULTS: Fourteen discriminant functions were developed for metacarpals with percentages from 79.5% to 85.3% of correct gender classification. The second metacarpal was the most dimorphic of the sample. For metatarsals, five discriminant functions were obtained, ranging from 77.8% to 83.2% of certainty. In this case the first metatarsal was the most dimorphic. In general terms, the widths of both epiphyses were the most dimorphic measurements. CONCLUSIONS: The discriminant functions of metacarpal and metatarsal bones obtained are generally above 80%, which is similar to reports from other populations. Therefore, it can be used in forensic contexts for human identification with complete or fragmented remains, in the cases where no other bone element is available, such as the pelvis


Assuntos
Humanos , Masculino , Feminino , Determinação do Sexo pelo Esqueleto/métodos , Metacarpo/anatomia & histologia , Metatarso/anatomia & histologia , Antropometria/métodos , Identificação Biométrica/métodos , Antropologia Forense/métodos , Tamanho do Órgão , México , Reprodutibilidade dos Testes
15.
Neural Netw ; 124: 223-232, 2020 Apr.
Artigo em Inglês | MEDLINE | ID: mdl-32018160

RESUMO

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.


Assuntos
Identificação Biométrica/métodos , Processamento de Imagem Assistida por Computador/métodos , Aprendizado de Máquina , Identificação Biométrica/normas , Processamento de Imagem Assistida por Computador/normas
16.
Neural Netw ; 125: 41-55, 2020 May.
Artigo em Inglês | MEDLINE | ID: mdl-32070855

RESUMO

Chinese sign language (CSL) is one of the most widely used sign language systems in the world. As such, the automatic recognition and generation of CSL is a key technology enabling bidirectional communication between deaf and hearing people. Most previous studies have focused solely on sign language recognition (SLR), which only addresses communication in a single direction. As such, there is a need for sign language generation (SLG) to enable communication in the other direction (i.e., from hearing people to deaf people). To achieve a smoother exchange of ideas between these two groups, we propose a skeleton-based CSL recognition and generation framework based on a recurrent neural network (RNN), to support bidirectional CSL communication. This process can also be extended to other sequence-to-sequence information interactions. The core of the proposed framework is a two-level probability generative model. Compared with previous techniques, this approach offers a more flexible approximate posterior distribution, which can produce skeletal sequences of varying styles that are recognizable to humans. In addition, the proposed generation method compensated for a lack of training data. A series of experiments in bidirectional communication were conducted on the large 500 CSL dataset. The proposed algorithm achieved high recognition accuracy for both real and synthetic data, with a reduced runtime. Furthermore, the generated data improved the performance of the discriminator. These results suggest the proposed bidirectional communication framework and generation algorithm to be an effective new approach to CSL recognition.


Assuntos
Identificação Biométrica/métodos , Auxiliares de Comunicação para Pessoas com Deficiência , Reconhecimento Automatizado de Padrão/métodos , Línguas de Sinais , Algoritmos , Grupo com Ancestrais do Continente Asiático , Humanos
17.
Sensors (Basel) ; 20(4)2020 Feb 19.
Artigo em Inglês | MEDLINE | ID: mdl-32093028

RESUMO

In recent years, human-machine interactions encompass many avenues of life, ranging from personal communications to professional activities. This trend has allowed for person identification based on behavior rather than physical traits to emerge as a growing research domain, which spans areas such as online education, e-commerce, e-communication, and biometric security. The expression of opinions is an example of online behavior that is commonly shared through the liking of online images. Visual aesthetic is a behavioral biometric that involves using a person's sense of fondness for images. The identification of individuals using their visual aesthetic values as discriminatory features is an emerging domain of research. This paper introduces a novel method for aesthetic feature dimensionality reduction using gene expression programming. The proposed system is capable of using a tree-based genetic approach for feature recombination. Reducing feature dimensionality improves classifier accuracy, reduces computation runtime, and minimizes required storage. The results obtained on a dataset of 200 Flickr users evaluating 40,000 images demonstrate a 95% accuracy of identity recognition based solely on users' aesthetic preferences.


Assuntos
Identificação Biométrica/métodos , Estética , Regulação da Expressão Gênica , Humanos , Processamento de Imagem Assistida por Computador , Modelos Teóricos , Máquina de Vetores de Suporte
19.
Sci Justice ; 60(1): 79-85, 2020 01.
Artigo em Inglês | MEDLINE | ID: mdl-31924292

RESUMO

Gait is known to have been used as evidence since 1839, initially based on the apocryphal belief that a person can be identified by their gait. The potential uniqueness of gait has yet to be proven, and therefore gait is currently considered to be a contributor to identification rather than a method of identification. In 2013 Birch et al. [1] published the findings of an investigation into the ability of individuals with experience in gait analysis to identify people by observing features of gait recorded by closed circuit television cameras. The study showed that the participants made correct decisions in 71% of cases, significantly better than would have been expected to have occurred by chance. However, the presentation of gait evidence is not limited to witnesses with experience in gait analysis. This study compared the abilities and confidence of participants with experience in gait analysis with those of participants with no experience of gait analysis using the methodology of Birch et al. 2013 [1]. The results showed no statistically significant difference in the number of correct identification decisions made by the two groups of participants, although the participants with experience of gait analysis made slightly more false negative than false positive decisions, whereas the participants with no experience made more false positive than false negative decisions. The participants with no experience in gait analysis reported significantly more confidence in their decisions than did the participants with experience (p < 0.05). The results suggest that lay people giving gait based evidence are likely to be more confident in their assertions as to identity based on that evidence, than would a witness with experience of gait analysis. Careful consideration therefore needs to be given to the submission of gait based evidence by lay witnesses.


Assuntos
Identificação Biométrica/métodos , Prova Pericial/normas , Análise da Marcha , Competência Profissional/normas , Autoimagem , Humanos , Televisão , Gravação em Vídeo
20.
IEEE Trans Image Process ; 29(1): 2013-2025, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-31634836

RESUMO

Person re-identification (Re-ID) aims at matching person images captured in non-overlapping camera views. To represent person appearance, low-level visual features are sensitive to environmental changes, while high-level semantic attributes, such as "short-hair" or "long-hair", are relatively stable. Hence, researches have started to design semantic attributes to reduce the visual ambiguity. However, to train a prediction model for semantic attributes, it requires plenty of annotations, which are hard to obtain in practical large-scale applications. To alleviate the reliance on annotation efforts, we propose to incrementally generate Deep Hidden Attribute (DHA) based on baseline deep network for newly uncovered annotations. In particular, we propose an auto-encoder model that can be plugged into any deep network to mine latent information in an unsupervised manner. To optimize the effectiveness of DHA, we reform the auto-encoder model with additional orthogonal generation module, along with identity-preserving and sparsity constraints. 1) Orthogonally generating: In order to make DHAs different from each other, Singular Vector Decomposition (SVD) is introduced to generate DHAs orthogonally. 2) Identity-preserving constraint: The generated DHAs should be distinct for telling different persons, so we associate DHAs with person identities. 3) Sparsity constraint: To enhance the discriminability of DHAs, we also introduce the sparsity constraint to restrict the number of effective DHAs for each person. Experiments conducted on public datasets have validated the effectiveness of the proposed network. On two large-scale datasets, i.e., Market-1501 and DukeMTMC-reID, the proposed method outperforms the state-of-the-art methods.


Assuntos
Identificação Biométrica/métodos , Aprendizado Profundo , Processamento de Imagem Assistida por Computador/métodos , Feminino , Humanos , Masculino
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA