Página 1 dos resultados de 30 itens digitais encontrados em 0.010 segundos

Learning person-specific face representations = : Aprendendo representações específicas para a face de cada pessoa; Aprendendo representações específicas para a face de cada pessoa

Giovani Chiachia
Fonte: Biblioteca Digital da Unicamp Publicador: Biblioteca Digital da Unicamp
Tipo: Tese de Doutorado Formato: application/pdf
Publicado em 27/08/2013 PT
Relevância na Pesquisa
66.31%
Os seres humanos são especialistas natos em reconhecimento de faces, com habilidades que excedem em muito as dos métodos automatizados vigentes, especialmente em cenários não controlados, onde não há a necessidade de colaboração por parte do indivíduo sendo reconhecido. No entanto, uma característica marcante do reconhecimento de face humano é que nós somos substancialmente melhores no reconhecimento de faces familiares, provavelmente porque somos capazes de consolidar uma grande quantidade de experiência prévia com a aparência de certo indivíduo e de fazer uso efetivo dessa experiência para nos ajudar no reconhecimento futuro. De fato, pesquisadores em psicologia têm até mesmo sugeridos que a representação interna que fazemos das faces pode ser parcialmente adaptada ou otimizada para rostos familiares. Enquanto isso, a situação análoga no reconhecimento facial automatizado | onde um grande número de exemplos de treinamento de um indivíduo está disponível | tem sido muito pouco explorada, apesar da crescente relevância dessa abordagem na era das mídias sociais. Inspirados nessas observações, nesta tese propomos uma abordagem em que a representação da face de cada pessoa é explicitamente adaptada e realçada com o intuito de reconhecê-la melhor. Apresentamos uma coleção de métodos de aprendizado que endereça e progressivamente justifica tal abordagem. Ao aprender e operar com representações específicas para face de cada pessoa...

A fast and robust negative mining approach for user enrollment in face recognition systems = : Uma abordagem eficiente e robusta de mineração de negativos para cadastramento de novos usuários em sistemas de reconhecimento facial; Uma abordagem eficiente e robusta de mineração de negativos para cadastramento de novos usuários em sistemas de reconhecimento facial

Samuel Botter Martins
Fonte: Biblioteca Digital da Unicamp Publicador: Biblioteca Digital da Unicamp
Tipo: Dissertação de Mestrado Formato: application/pdf
Publicado em 13/03/2015 PT
Relevância na Pesquisa
56.42%
Sistemas automáticos de reconhecimento de faces tem atraído a atenção da indústria e da academia, devido à gama de possíveis aplicações, tais como vigilância, controle de acesso, etc. O recente progresso em tais sistemas motiva o uso de técnicas de aprendizado em profundidade e classificadores específicos para cada usuário em cenários de operação não-controlado, que apresentam variações consideráveis em pose, iluminação, etc. Sistemas automáticos de reconhecimento de faces possibilitam construir bases de imagens anotadas por meio do processo de cadastramento de novos usuários. Porém, à medida que as bases de dados crescem, torna-se crucial reduzir o número de amostras negativas usadas para treinar classificadores específicos para cada usuário, devido às limitações de processamento e tempo de resposta. Tal processo de aprendizado discriminativo durante o cadastramento de novos indivíduos tem implicações no projeto de sistemas de reconhecimento de faces. Apesar deste processo poder aumentar o desempenho do reconhecimento, ele também pode afetar a velocidade do cadastramento, prejudicando, assim, a experiência do usuário. Neste cenário, é importante selecionar as amostras mais informativas buscando maximizar o desempenho do classificador. Este trabalho resolve tal problema propondo um método de aprendizado discriminativo durante o cadastramento de usuários com o objetivo de não afetar a velocidade e a confiabilidade do processo. Nossa solução combina representações de alta dimensão com um algoritmo que rapidamente minera imagens faciais negativas de um conjunto de minerção grande para assim construir um classificador específico para cada usuário...

Generic Learning-Based Ensemble Framework for Small Sample Size Face Recognition in Multi-Camera Networks

Zhang, Cuicui; Liang, Xuefeng; Matsuyama, Takashi
Fonte: MDPI Publicador: MDPI
Tipo: Artigo de Revista Científica
Publicado em 08/12/2014 EN
Relevância na Pesquisa
46.11%
Multi-camera networks have gained great interest in video-based surveillance systems for security monitoring, access control, etc. Person re-identification is an essential and challenging task in multi-camera networks, which aims to determine if a given individual has already appeared over the camera network. Individual recognition often uses faces as a trial and requires a large number of samples during the training phrase. This is difficult to fulfill due to the limitation of the camera hardware system and the unconstrained image capturing conditions. Conventional face recognition algorithms often encounter the “small sample size” (SSS) problem arising from the small number of training samples compared to the high dimensionality of the sample space. To overcome this problem, interest in the combination of multiple base classifiers has sparked research efforts in ensemble methods. However, existing ensemble methods still open two questions: (1) how to define diverse base classifiers from the small data; (2) how to avoid the diversity/accuracy dilemma occurring during ensemble. To address these problems, this paper proposes a novel generic learning-based ensemble framework, which augments the small data by generating new samples based on a generic distribution and introduces a tailored 0–1 knapsack algorithm to alleviate the diversity/accuracy dilemma. More diverse base classifiers can be generated from the expanded face space...

Face Averages Enhance User Recognition for Smartphone Security

Robertson, David J.; Kramer, Robin S. S.; Burton, A. Mike
Fonte: Public Library of Science Publicador: Public Library of Science
Tipo: Artigo de Revista Científica
Publicado em 25/03/2015 EN
Relevância na Pesquisa
36.27%
Our recognition of familiar faces is excellent, and generalises across viewing conditions. However, unfamiliar face recognition is much poorer. For this reason, automatic face recognition systems might benefit from incorporating the advantages of familiarity. Here we put this to the test using the face verification system available on a popular smartphone (the Samsung Galaxy). In two experiments we tested the recognition performance of the smartphone when it was encoded with an individual’s ‘face-average’ – a representation derived from theories of human face perception. This technique significantly improved performance for both unconstrained celebrity images (Experiment 1) and for real faces (Experiment 2): users could unlock their phones more reliably when the device stored an average of the user’s face than when they stored a single image. This advantage was consistent across a wide variety of everyday viewing conditions. Furthermore, the benefit did not reduce the rejection of imposter faces. This benefit is brought about solely by consideration of suitable representations for automatic face recognition, and we argue that this is just as important as development of matching algorithms themselves. We propose that this representation could significantly improve recognition rates in everyday settings.

Face Identification in the Internet Era

Stone, Zachary
Fonte: Harvard University Publicador: Harvard University
Tipo: Thesis or Dissertation
EN_US
Relevância na Pesquisa
56.31%
Despite decades of effort in academia and industry, it is not yet possible to build machines that can replicate many seemingly-basic human perceptual abilities. This work focuses on the problem of face identification that most of us effortlessly solve daily. Substantial progress has been made towards the goal of automatically identifying faces under tightly controlled conditions; however, in the domain of unconstrained face images, many challenges remain. We observe that the recent combination of widespread digital photography, inexpensive digital storage and bandwidth, and online social networks has led to the sudden creation of repositories of billions of shared photographs and opened up an important new domain for unconstrained face identification research. Drawing upon the newly-popular phenomenon of “tagging,” we construct some of the first face identification datasets that are intended to model the digital social spheres of online social network members, and we examine various qualitative and quantitative properties of these image sets. The identification datasets we present here include up to 100 individuals, making them comparable to the average size of members’ networks of “friends” on a popular online social network...

Variability compensation using NAP for unconstrained face recognition

Tomé González, Pedro; Vera-Rodríguez, Rubén; Fiérrez, Julián; Ortega-García, Javier
Fonte: Springer Berlin Heidelberg Publicador: Springer Berlin Heidelberg
Tipo: conferenceObject; bookPart
ENG
Relevância na Pesquisa
56.32%
The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-642-28765-7_17; Proceedings of the International Symposium on Distributed Computing and Artificial Intelligence 2012 (DCAI 2012), Salamanca, Spain.; The variability presented in unconstrained environments represents one of the open challenges in automated face recognition systems. Several techniques have been proposed in the literature to cope with this problem, most of them tailored to compensate one specific source of variability, e.g., illumination or pose. In this paper we present a general variability compensation scheme based on the Nuisance Attribute Projection (NAP) that can be applied to compensate for any kind of variability factors that affects the face recognition performance. Our technique reduces the intra-class variability by finding a low dimensional variability subspace. This approach is assessed on a database from the NIST still face recognition challenge “The Good, the Bad, and the Ugly” (GBU). The results achieved using our implementation of a state-of-the-art system based on sparse representation are improved significantly by incorporating our variability compensation technique. These results are also compared to the GBU challenge results...

A Cognitively-Motivated Framework for Partial Face Recognition in Unconstrained Scenarios

Monteiro, João C.; Cardoso, Jaime S.
Fonte: MDPI Publicador: MDPI
Tipo: Artigo de Revista Científica
Publicado em 16/01/2015 EN
Relevância na Pesquisa
46.14%
Humans perform and rely on face recognition routinely and effortlessly throughout their daily lives. Multiple works in recent years have sought to replicate this process in a robust and automatic way. However, it is known that the performance of face recognition algorithms is severely compromised in non-ideal image acquisition scenarios. In an attempt to deal with conditions, such as occlusion and heterogeneous illumination, we propose a new approach motivated by the global precedent hypothesis of the human brain's cognitive mechanisms of perception. An automatic modeling of SIFT keypoint descriptors using a Gaussian mixture model (GMM)-based universal background model method is proposed. A decision is, then, made in an innovative hierarchical sense, with holistic information gaining precedence over a more detailed local analysis. The algorithm was tested on the ORL, ARand Extended Yale B Face databases and presented state-of-the-art performance for a variety of experimental setups.

A comparative study of thermal face recognition methods in unconstrained environments

Ruiz del Solar, Javier; Verschae, Rodrigo; Correa, Mauricio; Hermosilla, Gabriel
Fonte: Elsevier Publicador: Elsevier
Tipo: Artículo de revista
EN
Relevância na Pesquisa
66.39%
Artículo de publicación ISI; The recognition of faces in unconstrained environments is a challenging problem. The aim of this work is to carry out a comparative study of face recognition methods working in the thermal spectrum (8-12 mu m) that are suitable for working properly in these environments. The analyzed methods were selected by considering their performance in former comparative studies, in addition to being real-time, to requiring just one image per person, and to being fully online (no requirements of offline enrollment). Thus, in this study three local-matching methods based on histograms of Local Binary Pattern (LBP) features, on histograms of Weber Linear Descriptors (WLD), and on Gabor Jet Descriptors (GJD), as well as two global image-matching method based on Scale-Invariant Feature Transform (SIFT) Descriptors, and Speeded Up Robust Features (SURF) Descriptors, are analyzed. The methods are compared using the Equinox and UCHThermalFace databases. The use of these databases allows evaluating the methods in real-world conditions that include natural variations in illumination, indoor/outdoor setup, facial expression, pose, accessories, occlusions, and background. The UCHThermalFace database is described for the first time in this article and WLD is used for the first time in face recognition. The results of this comparative study are intended to be a guide for developers of face recognition systems. The main conclusions of this study are: (i) all analyzed methods perform very well under the conditions in which they were evaluated...

Face Recognition in Unconstrained Environments: A Comparative Study

Ruiz del Solar, Javier; Correa, Mauricio; Verschae, Rodrigo
Fonte: Universidade do Chile Publicador: Universidade do Chile
Tipo: Artículo de revista
EN
Relevância na Pesquisa
76.46%
The development of face recognition methods for unconstrained environments is a challenging problem. The aim of this work is to carry out a comparative study of existing face recognition methods that are suitable to work properly in these environments. The analyzed methods are selected by considering their performance in former comparative studies, in addition to be real-time, to require just one image per person, and to be fully online (no requirements of offline enrollment). The methods are compared using the LFW database, which was built to evaluate face recognition methods in real-world conditions. The results of this comparative study are intended to be a guide for developers of face recognition systems.

Multi-Directional Multi-Level Dual-Cross Patterns for Robust Face Recognition

Ding, Changxing; Choi, Jonghyun; Tao, Dacheng; Davis, Larry S.
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Relevância na Pesquisa
66.21%
To perform unconstrained face recognition robust to variations in illumination, pose and expression, this paper presents a new scheme to extract "Multi-Directional Multi-Level Dual-Cross Patterns" (MDML-DCPs) from face images. Specifically, the MDMLDCPs scheme exploits the first derivative of Gaussian operator to reduce the impact of differences in illumination and then computes the DCP feature at both the holistic and component levels. DCP is a novel face image descriptor inspired by the unique textural structure of human faces. It is computationally efficient and only doubles the cost of computing local binary patterns, yet is extremely robust to pose and expression variations. MDML-DCPs comprehensively yet efficiently encodes the invariant characteristics of a face image from multiple levels into patterns that are highly discriminative of inter-personal differences but robust to intra-personal variations. Experimental results on the FERET, CAS-PERL-R1, FRGC 2.0, and LFW databases indicate that DCP outperforms the state-of-the-art local descriptors (e.g. LBP, LTP, LPQ, POEM, tLBP, and LGXP) for both face identification and face verification tasks. More impressively, the best performance is achieved on the challenging LFW and FRGC 2.0 databases by deploying MDML-DCPs in a simple recognition scheme.; Comment: accepted version to IEEE TPAMI

Automatic Face Recognition from Video

Arandjelovic, Ognjen
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 21/04/2015
Relevância na Pesquisa
56.14%
The objective of this work is to automatically recognize faces from video sequences in a realistic, unconstrained setup in which illumination conditions are extreme and greatly changing, viewpoint and user motion pattern have a wide variability, and video input is of low quality. At the centre of focus are face appearance manifolds: this thesis presents a significant advance of their understanding and application in the sphere of face recognition. The two main contributions are the Generic Shape-Illumination Manifold recognition algorithm and the Anisotropic Manifold Space clustering. The Generic Shape-Illumination Manifold is evaluated on a large data corpus acquired in real-world conditions and its performance is shown to greatly exceed that of state-of-the-art methods in the literature and the best performing commercial software. Empirical evaluation of the Anisotropic Manifold Space clustering on a popular situation comedy is also described with excellent preliminary results.; Comment: Doctor of Philosophy (PhD) dissertation, University of Cambridge, 2007

Face Search at Scale: 80 Million Gallery

Wang, Dayong; Otto, Charles; Jain, Anil K.
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Relevância na Pesquisa
56.36%
Due to the prevalence of social media websites, one challenge facing computer vision researchers is to devise methods to process and search for persons of interest among the billions of shared photos on these websites. Facebook revealed in a 2013 white paper that its users have uploaded more than 250 billion photos, and are uploading 350 million new photos each day. Due to this humongous amount of data, large-scale face search for mining web images is both important and challenging. Despite significant progress in face recognition, searching a large collection of unconstrained face images has not been adequately addressed. To address this challenge, we propose a face search system which combines a fast search procedure, coupled with a state-of-the-art commercial off the shelf (COTS) matcher, in a cascaded framework. Given a probe face, we first filter the large gallery of photos to find the top-k most similar faces using deep features generated from a convolutional neural network. The k candidates are re-ranked by combining similarities from deep features and the COTS matcher. We evaluate the proposed face search system on a gallery containing 80 million web-downloaded face images. Experimental results demonstrate that the deep features are competitive with state-of-the-art methods on unconstrained face recognition benchmarks (LFW and IJB-A). Further...

Effective Face Frontalization in Unconstrained Images

Hassner, Tal; Harel, Shai; Paz, Eran; Enbar, Roee
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 28/11/2014
Relevância na Pesquisa
46.41%
"Frontalization" is the process of synthesizing frontal facing views of faces appearing in single unconstrained photos. Recent reports have suggested that this process may substantially boost the performance of face recognition systems. This, by transforming the challenging problem of recognizing faces viewed from unconstrained viewpoints to the easier problem of recognizing faces in constrained, forward facing poses. Previous frontalization methods did this by attempting to approximate 3D facial shapes for each query image. We observe that 3D face shape estimation from unconstrained photos may be a harder problem than frontalization and can potentially introduce facial misalignments. Instead, we explore the simpler approach of using a single, unmodified, 3D surface as an approximation to the shape of all input faces. We show that this leads to a straightforward, efficient and easy to implement method for frontalization. More importantly, it produces aesthetic new frontal views and is surprisingly effective when used for face recognition and gender estimation.

A Fast and Accurate Unconstrained Face Detector

Liao, Shengcai; Jain, Anil K.; Li, Stan Z.
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Relevância na Pesquisa
56.32%
We propose a method to address challenges in unconstrained face detection, such as arbitrary pose variations and occlusions. First, a new image feature called Normalized Pixel Difference (NPD) is proposed. NPD feature is computed as the difference to sum ratio between two pixel values, inspired by the Weber Fraction in experimental psychology. The new feature is scale invariant, bounded, and is able to reconstruct the original image. Second, we propose a deep quadratic tree to learn the optimal subset of NPD features and their combinations, so that complex face manifolds can be partitioned by the learned rules. This way, only a single soft-cascade classifier is needed to handle unconstrained face detection. Furthermore, we show that the NPD features can be efficiently obtained from a look up table, and the detection template can be easily scaled, making the proposed face detector very fast. Experimental results on three public face datasets (FDDB, GENKI, and CMU-MIT) show that the proposed method achieves state-of-the-art performance in detecting unconstrained faces with arbitrary pose variations and occlusions in cluttered scenes.; Comment: This paper has been accepted by TPAMI. The source code is available on the project page http://www.cbsr.ia.ac.cn/users/scliao/projects/npdface/index.html

Unsupervised learning of clutter-resistant visual representations from natural videos

Liao, Qianli; Leibo, Joel Z.; Poggio, Tomaso
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Relevância na Pesquisa
45.94%
Populations of neurons in inferotemporal cortex (IT) maintain an explicit code for object identity that also tolerates transformations of object appearance e.g., position, scale, viewing angle [1, 2, 3]. Though the learning rules are not known, recent results [4, 5, 6] suggest the operation of an unsupervised temporal-association-based method e.g., Foldiak's trace rule [7]. Such methods exploit the temporal continuity of the visual world by assuming that visual experience over short timescales will tend to have invariant identity content. Thus, by associating representations of frames from nearby times, a representation that tolerates whatever transformations occurred in the video may be achieved. Many previous studies verified that such rules can work in simple situations without background clutter, but the presence of visual clutter has remained problematic for this approach. Here we show that temporal association based on large class-specific filters (templates) avoids the problem of clutter. Our system learns in an unsupervised way from natural videos gathered from the internet, and is able to perform a difficult unconstrained face recognition task on natural images: Labeled Faces in the Wild [8].

Can a biologically-plausible hierarchy effectively replace face detection, alignment, and recognition pipelines?

Liao, Qianli; Leibo, Joel Z; Mroueh, Youssef; Poggio, Tomaso
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Relevância na Pesquisa
56.44%
The standard approach to unconstrained face recognition in natural photographs is via a detection, alignment, recognition pipeline. While that approach has achieved impressive results, there are several reasons to be dissatisfied with it, among them is its lack of biological plausibility. A recent theory of invariant recognition by feedforward hierarchical networks, like HMAX, other convolutional networks, or possibly the ventral stream, implies an alternative approach to unconstrained face recognition. This approach accomplishes detection and alignment implicitly by storing transformations of training images (called templates) rather than explicitly detecting and aligning faces at test time. Here we propose a particular locality-sensitive hashing based voting scheme which we call "consensus of collisions" and show that it can be used to approximate the full 3-layer hierarchy implied by the theory. The resulting end-to-end system for unconstrained face recognition operates on photographs of faces taken under natural conditions, e.g., Labeled Faces in the Wild (LFW), without aligning or cropping them, as is normally done. It achieves a drastic improvement in the state of the art on this end-to-end task, reaching the same level of performance as the best systems operating on aligned...

A Deep Pyramid Deformable Part Model for Face Detection

Ranjan, Rajeev; Patel, Vishal M.; Chellappa, Rama
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 18/08/2015
Relevância na Pesquisa
46.16%
We present a face detection algorithm based on Deformable Part Models and deep pyramidal features. The proposed method called DP2MFD is able to detect faces of various sizes and poses in unconstrained conditions. It reduces the gap in training and testing of DPM on deep features by adding a normalization layer to the deep convolutional neural network (CNN). Extensive experiments on four publicly available unconstrained face detection datasets show that our method is able to capture the meaningful structure of faces and performs significantly better than many competitive face detection algorithms.

Leveraging Billions of Faces to Overcome Performance Barriers in Unconstrained Face Recognition

Taigman, Yaniv; Wolf, Lior
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 04/08/2011
Relevância na Pesquisa
66.11%
We employ the face recognition technology developed in house at face.com to a well accepted benchmark and show that without any tuning we are able to considerably surpass state of the art results. Much of the improvement is concentrated in the high-valued performance point of zero false positive matches, where the obtained recall rate almost doubles the best reported result to date. We discuss the various components and innovations of our system that enable this significant performance gap. These components include extensive utilization of an accurate 3D reconstructed shape model dealing with challenges arising from pose and illumination. In addition, discriminative models based on billions of faces are used in order to overcome aging and facial expression as well as low light and overexposure. Finally, we identify a challenging set of identification queries that might provide useful focus for future research.; Comment: 7 pages

Beyond Frontal Faces: Improving Person Recognition Using Multiple Cues

Zhang, Ning; Paluri, Manohar; Taigman, Yaniv; Fergus, Rob; Bourdev, Lubomir
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Relevância na Pesquisa
36.29%
We explore the task of recognizing peoples' identities in photo albums in an unconstrained setting. To facilitate this, we introduce the new People In Photo Albums (PIPA) dataset, consisting of over 60000 instances of 2000 individuals collected from public Flickr photo albums. With only about half of the person images containing a frontal face, the recognition task is very challenging due to the large variations in pose, clothing, camera viewpoint, image resolution and illumination. We propose the Pose Invariant PErson Recognition (PIPER) method, which accumulates the cues of poselet-level person recognizers trained by deep convolutional networks to discount for the pose variations, combined with a face recognizer and a global recognizer. Experiments on three different settings confirm that in our unconstrained setup PIPER significantly improves on the performance of DeepFace, which is one of the best face recognizers as measured on the LFW dataset.

Unconstrained Face Verification using Deep CNN Features

Chen, Jun-Cheng; Patel, Vishal M.; Chellappa, Rama
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 07/08/2015
Relevância na Pesquisa
56.24%
In this paper, we present an algorithm for unconstrained face verification based on deep convolutional features and evaluate it on the newly released IARPA Janus Benchmark A (IJB-A) dataset. The IJB-A dataset includes real-world unconstrained faces from 500 subjects with full pose and illumination variations which are much harder than the traditional Labeled Face in the Wild (LFW) and Youtube Face (YTF) datasets. The deep convolutional neural network (DCNN) is trained using the CASIA-WebFace dataset. Extensive experiments on the IJB-A dataset are provided.