José L Alba-Castro - Profile on Academia.edu (original) (raw)
Papers by José L Alba-Castro
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2021
Isolated Sign Language Recognition (ISLR) fits nicely in the domain of problems that can be handl... more Isolated Sign Language Recognition (ISLR) fits nicely in the domain of problems that can be handled by graphstructured spatial-temporal algorithms. A recent multiscale spatial-temporal graph convolution operator, MS-G3D, takes advantage of the semantic connectivity among non-neighbor nodes of the graph in a flexible temporal scale, which results in improved performance in classical Human Action Recognition datasets. In this work, we present a solution for ISLR using a skeleton graph that includes body and finger joints and makes use of this specific property of MS-G3D, which seems crucial to capture the internal relationship among semantically connected distant nodes in sign language dynamics. To complete the analysis, we compare the results with a 3D-CNN architecture, S3D, already used for SLR, and fuse it with MS-G3D. The performance achieved on the AUTSL dataset shows that MS-G3D alone stands out as a viable technique for ISLR. In fact, the improvement after fusing with a 3D-CNN approach, at least on this medium-scale dataset, appears marginal. The transfer learning capability of the trained models is also explored using pre-training with the larger WLASL dataset and post-training with the smaller LSE UVIGO dataset. The classification performance based on the MS-G3D model over AUTSL does not benefit from pre-training with WLASL, but the performance on the more similarly acquired LSE UVIGO dataset improves significantly from fine-tuning the MS-G3D AUTSL model.
Soft-competitive-growing classifier with unsupervised fine-tuning
Proceedings of International Conference on Neural Networks (ICNN'97), 1997
ABSTRACT
CMHNN: a constructive modular hybrid neural network for classification
Proceedings of International Conference on Neural Networks (ICNN'96)
ABSTRACT
From Hard to Soft Biometrics Through DNN Transfer Learning
2018 IEEE 9th International Conference on Biometrics Theory, Applications and Systems (BTAS)
In this work we thoroughly study the well-known face verification Resnet model in dlib’s library ... more In this work we thoroughly study the well-known face verification Resnet model in dlib’s library to uncover inner features related to soft biometrics attributes like gender, race and age. The study makes use of the t-SNE technique to understand the evolution of clustering through the pretrained network layers and reveals an interesting property of t-SNE to spot separability of clusters in the original space. The performance of simple classifiers for the secondary soft-biometrics tasks through the network reinforce the findings about t-SNE. This study is extensible to any model that maps the input classes into an embedded low-dimensional space that learned to cluster them in task-meaningful sets. We conclude that a state of the art face verification model can be easily leveraged to state of the art soft biometrics model without resorting to fine-tuning convolutional weights, which also allows reducing the model size and inference time.
1996 8th European Signal Processing Conference (EUSIPCO 1996), 1996
This paper presents a novel architecture based on a constructive algorithm that allows the networ... more This paper presents a novel architecture based on a constructive algorithm that allows the network to grow attending to both supervised and unsupervised criteria. The main goal is to end up with a set of discriminant functions able to solve a multi-class classification problem. The main difference with well-known NN-classificators lean on the fact that training is performed over labeled sets of patterns that we call high-level-structures (HLS). Every set contain patterns linked each other by some physical evidence, like neighbor pixels in a subimage or a time-sequence of frequency vectors in a speech utterance, but the membership of every individual pattern in the high-level-structure can not be so clear. This architecture has been tested on a number of artificial data sets and real data sets with very good results. We are now applying the algorithm to classification of real images drawn from the DataBase created for the ALINSPEC project.
Interspeech 2005, 2005
Corpus-based speech synthesis performance depends on the skill to model and represent appropriate... more Corpus-based speech synthesis performance depends on the skill to model and represent appropriately all the characteristics of the speech units that serve as a basis for concatenation. Although there is usually general agreement in the set of essential features (fundamental frequency, duration, power and phonetic context), it is still an open question the proper way of modelling them and considering their respective contributions to the cost functions, specially with regards to those related to the phonetic context. Precisely, this paper presents a new approach for modeling the phonetic context that also simplifies the hard task of training the corresponding weights to the different features in the target cost function.
A growing classifier applied to partially labeled Landsat images
ABSTRACT
Efficient computation of face shape similarity using distance transform eigendecomposition and valleys
Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205), 2001
This paper presents a face recognition system based on the use of image ridges and valleys as fac... more This paper presents a face recognition system based on the use of image ridges and valleys as face shape descriptors and a supervised Hausdorff based measure as similarity criteria. The proposed measure is designed to decrease the distance measured between images of the same subject. This measure is approximated using eigendecomposition in order to obtain a computationally efficient recognition method
Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205), 2001
Ridges, Valleys and Hausdorff Based Similarity Measures for Face Description and Matching
Pattern Recognition in Information Systems, 2001
International Journal of Pattern Recognition and Artificial Intelligence, 2002
Hausdorff distance is a deformation tolerant measure between two sets of points. The main advanta... more Hausdorff distance is a deformation tolerant measure between two sets of points. The main advantage of this measure is that it does not need an explicit correspondence between the points of the two sets. This paper presents the application to automatic face recognition of a novel supervised Hausdorff-based measure. This measure is designed to minimize the distance between sets of the same class (subject) and at the same time maximize the distance of sets between different classes.
Reducing the complexity in a fractal-based image coder
Proceedings of IEEE 6th Digital Signal Processing Workshop
... FJ Gonzdez, D. Docampo and JL Alba Dept. ... A dimensionality-reduced subvec-tor is obtained ... more ... FJ Gonzdez, D. Docampo and JL Alba Dept. ... A dimensionality-reduced subvec-tor is obtained by extracting the coefficients of impor-tance, from a human visual point of view. Then, a candidate list of the nearest neighbors, in the trans-form domain, is stored. ...
Growing Gaussian mixtures network for classification applications
Signal Processing, 1999
In this paper a method to automatically generate a Gaussian mixture classifier is presented. The ... more In this paper a method to automatically generate a Gaussian mixture classifier is presented. The growing process is based on the iterative addition of Gaussian nodes. Each iteration takes place in two sequential steps: first, using the EM algorithm, we maximize the likelihood of the data under the current configuration of the classifier; then, a new Gaussian node is added
Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429), 2003
This paper introduces a supervised discriminant Hausdorff distance that fits into the framework f... more This paper introduces a supervised discriminant Hausdorff distance that fits into the framework for automatic face analysis and recognition proposed in [1]. Our proposal relies solely on face shape variation contrarily to most of the successful model-based approaches, and results show comparable performance to them. The whole framework is based in a new set of Hausdorff measures and defines face-shape based similarity measures and supervised criteria to add discriminant capabilities to the Hausdorff distance. The paper presents experimental results supporting the proposed methodologies.
Isolated Sign Language Recognition (ISLR) fits nicely in the domain of problems that can be handl... more Isolated Sign Language Recognition (ISLR) fits nicely in the domain of problems that can be handled by graphstructured spatial-temporal algorithms. A recent multiscale spatial-temporal graph convolution operator, MS-G3D, takes advantage of the semantic connectivity among non-neighbor nodes of the graph in a flexible temporal scale, which results in improved performance in classical Human Action Recognition datasets. In this work, we present a solution for ISLR using a skeleton graph that includes body and finger joints and makes use of this specific property of MS-G3D, which seems crucial to capture the internal relationship among semantically connected distant nodes in sign language dynamics. To complete the analysis, we compare the results with a 3D-CNN architecture, S3D, already used for SLR, and fuse it with MS-G3D. The performance achieved on the AUTSL dataset shows that MS-G3D alone stands out as a viable technique for ISLR. In fact, the improvement after fusing with a 3D-CNN approach, at least on this medium-scale dataset, appears marginal. The transfer learning capability of the trained models is also explored using pre-training with the larger WLASL dataset and post-training with the smaller LSE UVIGO dataset. The classification performance based on the MS-G3D model over AUTSL does not benefit from pre-training with WLASL, but the performance on the more similarly acquired LSE UVIGO dataset improves significantly from fine-tuning the MS-G3D AUTSL model.
Computer Vision and Image Understanding, Nov 1, 2020
This is a PDF file of an article that has undergone enhancements after acceptance, such as the ad... more This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.
Proceedings of SPIE, Nov 14, 2001
In this article we present an hybrid SOM+PCA approach for face identification that is based on se... more In this article we present an hybrid SOM+PCA approach for face identification that is based on separating shape and texture information. Shape will be processed by a modified Hausdorff distance SOM and texture processing relies on a modular PCA. In most successfully view-based recognition systems, shape and texture are jointly used to statistically model a linear or piecewise linear subspace that optimally explains the face space for a specific database. Our work is aimed to separate the influence that variance in face shape stamps on the set of eigenfaces in the classical PCA decomposition. In this sense we search for a more efficiently coded face-vector for identification. The ultimate goal consist of finding a non-linear transformation invariant to gesture changes and, in a larger extent, to pose changes. The first part of this paper is dedicated to the shape processor of the system, that is based on a novel shape-based Self Organizing Map, and the second part deals with the subspace PCA decomposition that relies on the SOM clustering. Results are reported by comparing face identification between PCA and the SOM-PCA approach.
Redes neuronales hibridas: variantes constructivas y probabilisticas aplicadas a la clasificacion de patrones
Esta tesis propone nuevas soluciones constructivas al problema del entrenamiento de una red neuro... more Esta tesis propone nuevas soluciones constructivas al problema del entrenamiento de una red neuronal hibrida aplicada a la clasificacion de patrones. El trabajo se plantea desde dos perspectivas distintas: una conexionista utilizando tecnicas fundamentadas en algoritmos propios del campo de las redes neuronales, y otra probabilistica, con soluciones mas afines al campo de la estadistica. Cada uno de estos dos planteamientos deriva en una arquitectura constructiva que es capaz de generar un clasificador de prestaciones comparables a modelos ampliamente difundidos, como el perceptron multicapa (mlp), las redes con funciones de base radial (rbf) o los clasificadores basados en la regla de los k vecinos mas proximos (k-nn). Ambas arquitecturas constructivas incorporan instrumentos para controlar la complejidad del modelo con el proposito de mantener una generalizacion adecuada. El control de la complejidad sirve asimismo, como una forma de detener el proceso de entrenamiento. A lo largo de la tesis se muestra un conjunto de experimentos con datos generados artificialmente que reflejan las prestaciones de ambas redes neuronales y permiten evaluar la influencia, en el crecimiento y en la tasa de error, de los distintos parametros incorporados en los algoritmos. Las pruebas realizadas con datos procedentes de aplicaciones reales corroboran las conclusiones extraidas a partir de las pruebas artificiales y de los teoricos que fundamentan los algoritmos.
IET Biometrics, Jun 28, 2021
Face recognition technology is now mature enough to reach commercial products, such as smart phon... more Face recognition technology is now mature enough to reach commercial products, such as smart phones or tablets. However, it still needs to increase robustness against imposter attacks. In this regard, face Presentation Attack Detection (face-PAD) is a key component in providing trustable facial access to digital devices. Despite the success of several face-PAD works in publicly available datasets, most of them fail to reach the market, revealing the lack of evaluation frameworks that represent realistic settings. Here, an extensive analysis of the generalisation problem in face-PAD is provided, jointly with an evaluation strategy based on the aggregation of most publicly available datasets and a set of novel protocols to cover the most realistic settings, including a novel demographic bias analysis. Besides, a new finegrained categorisation of presentation attacks and instruments is provided, enabling higher flexibility in assessing the generalisation of different algorithms under a common framework. As a result, GRAD-GPAD v2, a comprehensive and modular framework is presented to evaluate the performance of face-PAD approaches in realistic settings, enabling accountability and fair comparison of most face-PAD approaches in the literature. This is an open access article under the terms of the Creative Commons Attribution-NonCommercial License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.
Lecture Notes in Computer Science, 2005
In this paper, a combined shape-texture approach to discriminative face authentication is studied... more In this paper, a combined shape-texture approach to discriminative face authentication is studied. Facial texture information is captured through Gabor responses (jets), similarly to the Elastic Bunch Graph Matching approach, but the points where filters are applied are located over lines that sketch the face. In this way, textural information is "shape-driven" and unlike other Gabor-based approaches, it shows a person-dependent behaviour. For every pair of face images, the score obtained through jets is combined with 3 measurements of pair-wise shape distortion. Discriminative Fisher methods are applied at the shape algorithm level and at the score combination level, in order to get a unified score ready for classification. Face verification results are reported on configuration I of the XM2VTS database.
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2021
Isolated Sign Language Recognition (ISLR) fits nicely in the domain of problems that can be handl... more Isolated Sign Language Recognition (ISLR) fits nicely in the domain of problems that can be handled by graphstructured spatial-temporal algorithms. A recent multiscale spatial-temporal graph convolution operator, MS-G3D, takes advantage of the semantic connectivity among non-neighbor nodes of the graph in a flexible temporal scale, which results in improved performance in classical Human Action Recognition datasets. In this work, we present a solution for ISLR using a skeleton graph that includes body and finger joints and makes use of this specific property of MS-G3D, which seems crucial to capture the internal relationship among semantically connected distant nodes in sign language dynamics. To complete the analysis, we compare the results with a 3D-CNN architecture, S3D, already used for SLR, and fuse it with MS-G3D. The performance achieved on the AUTSL dataset shows that MS-G3D alone stands out as a viable technique for ISLR. In fact, the improvement after fusing with a 3D-CNN approach, at least on this medium-scale dataset, appears marginal. The transfer learning capability of the trained models is also explored using pre-training with the larger WLASL dataset and post-training with the smaller LSE UVIGO dataset. The classification performance based on the MS-G3D model over AUTSL does not benefit from pre-training with WLASL, but the performance on the more similarly acquired LSE UVIGO dataset improves significantly from fine-tuning the MS-G3D AUTSL model.
Soft-competitive-growing classifier with unsupervised fine-tuning
Proceedings of International Conference on Neural Networks (ICNN'97), 1997
ABSTRACT
CMHNN: a constructive modular hybrid neural network for classification
Proceedings of International Conference on Neural Networks (ICNN'96)
ABSTRACT
From Hard to Soft Biometrics Through DNN Transfer Learning
2018 IEEE 9th International Conference on Biometrics Theory, Applications and Systems (BTAS)
In this work we thoroughly study the well-known face verification Resnet model in dlib’s library ... more In this work we thoroughly study the well-known face verification Resnet model in dlib’s library to uncover inner features related to soft biometrics attributes like gender, race and age. The study makes use of the t-SNE technique to understand the evolution of clustering through the pretrained network layers and reveals an interesting property of t-SNE to spot separability of clusters in the original space. The performance of simple classifiers for the secondary soft-biometrics tasks through the network reinforce the findings about t-SNE. This study is extensible to any model that maps the input classes into an embedded low-dimensional space that learned to cluster them in task-meaningful sets. We conclude that a state of the art face verification model can be easily leveraged to state of the art soft biometrics model without resorting to fine-tuning convolutional weights, which also allows reducing the model size and inference time.
1996 8th European Signal Processing Conference (EUSIPCO 1996), 1996
This paper presents a novel architecture based on a constructive algorithm that allows the networ... more This paper presents a novel architecture based on a constructive algorithm that allows the network to grow attending to both supervised and unsupervised criteria. The main goal is to end up with a set of discriminant functions able to solve a multi-class classification problem. The main difference with well-known NN-classificators lean on the fact that training is performed over labeled sets of patterns that we call high-level-structures (HLS). Every set contain patterns linked each other by some physical evidence, like neighbor pixels in a subimage or a time-sequence of frequency vectors in a speech utterance, but the membership of every individual pattern in the high-level-structure can not be so clear. This architecture has been tested on a number of artificial data sets and real data sets with very good results. We are now applying the algorithm to classification of real images drawn from the DataBase created for the ALINSPEC project.
Interspeech 2005, 2005
Corpus-based speech synthesis performance depends on the skill to model and represent appropriate... more Corpus-based speech synthesis performance depends on the skill to model and represent appropriately all the characteristics of the speech units that serve as a basis for concatenation. Although there is usually general agreement in the set of essential features (fundamental frequency, duration, power and phonetic context), it is still an open question the proper way of modelling them and considering their respective contributions to the cost functions, specially with regards to those related to the phonetic context. Precisely, this paper presents a new approach for modeling the phonetic context that also simplifies the hard task of training the corresponding weights to the different features in the target cost function.
A growing classifier applied to partially labeled Landsat images
ABSTRACT
Efficient computation of face shape similarity using distance transform eigendecomposition and valleys
Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205), 2001
This paper presents a face recognition system based on the use of image ridges and valleys as fac... more This paper presents a face recognition system based on the use of image ridges and valleys as face shape descriptors and a supervised Hausdorff based measure as similarity criteria. The proposed measure is designed to decrease the distance measured between images of the same subject. This measure is approximated using eigendecomposition in order to obtain a computationally efficient recognition method
Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205), 2001
Ridges, Valleys and Hausdorff Based Similarity Measures for Face Description and Matching
Pattern Recognition in Information Systems, 2001
International Journal of Pattern Recognition and Artificial Intelligence, 2002
Hausdorff distance is a deformation tolerant measure between two sets of points. The main advanta... more Hausdorff distance is a deformation tolerant measure between two sets of points. The main advantage of this measure is that it does not need an explicit correspondence between the points of the two sets. This paper presents the application to automatic face recognition of a novel supervised Hausdorff-based measure. This measure is designed to minimize the distance between sets of the same class (subject) and at the same time maximize the distance of sets between different classes.
Reducing the complexity in a fractal-based image coder
Proceedings of IEEE 6th Digital Signal Processing Workshop
... FJ Gonzdez, D. Docampo and JL Alba Dept. ... A dimensionality-reduced subvec-tor is obtained ... more ... FJ Gonzdez, D. Docampo and JL Alba Dept. ... A dimensionality-reduced subvec-tor is obtained by extracting the coefficients of impor-tance, from a human visual point of view. Then, a candidate list of the nearest neighbors, in the trans-form domain, is stored. ...
Growing Gaussian mixtures network for classification applications
Signal Processing, 1999
In this paper a method to automatically generate a Gaussian mixture classifier is presented. The ... more In this paper a method to automatically generate a Gaussian mixture classifier is presented. The growing process is based on the iterative addition of Gaussian nodes. Each iteration takes place in two sequential steps: first, using the EM algorithm, we maximize the likelihood of the data under the current configuration of the classifier; then, a new Gaussian node is added
Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429), 2003
This paper introduces a supervised discriminant Hausdorff distance that fits into the framework f... more This paper introduces a supervised discriminant Hausdorff distance that fits into the framework for automatic face analysis and recognition proposed in [1]. Our proposal relies solely on face shape variation contrarily to most of the successful model-based approaches, and results show comparable performance to them. The whole framework is based in a new set of Hausdorff measures and defines face-shape based similarity measures and supervised criteria to add discriminant capabilities to the Hausdorff distance. The paper presents experimental results supporting the proposed methodologies.
Isolated Sign Language Recognition (ISLR) fits nicely in the domain of problems that can be handl... more Isolated Sign Language Recognition (ISLR) fits nicely in the domain of problems that can be handled by graphstructured spatial-temporal algorithms. A recent multiscale spatial-temporal graph convolution operator, MS-G3D, takes advantage of the semantic connectivity among non-neighbor nodes of the graph in a flexible temporal scale, which results in improved performance in classical Human Action Recognition datasets. In this work, we present a solution for ISLR using a skeleton graph that includes body and finger joints and makes use of this specific property of MS-G3D, which seems crucial to capture the internal relationship among semantically connected distant nodes in sign language dynamics. To complete the analysis, we compare the results with a 3D-CNN architecture, S3D, already used for SLR, and fuse it with MS-G3D. The performance achieved on the AUTSL dataset shows that MS-G3D alone stands out as a viable technique for ISLR. In fact, the improvement after fusing with a 3D-CNN approach, at least on this medium-scale dataset, appears marginal. The transfer learning capability of the trained models is also explored using pre-training with the larger WLASL dataset and post-training with the smaller LSE UVIGO dataset. The classification performance based on the MS-G3D model over AUTSL does not benefit from pre-training with WLASL, but the performance on the more similarly acquired LSE UVIGO dataset improves significantly from fine-tuning the MS-G3D AUTSL model.
Computer Vision and Image Understanding, Nov 1, 2020
This is a PDF file of an article that has undergone enhancements after acceptance, such as the ad... more This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.
Proceedings of SPIE, Nov 14, 2001
In this article we present an hybrid SOM+PCA approach for face identification that is based on se... more In this article we present an hybrid SOM+PCA approach for face identification that is based on separating shape and texture information. Shape will be processed by a modified Hausdorff distance SOM and texture processing relies on a modular PCA. In most successfully view-based recognition systems, shape and texture are jointly used to statistically model a linear or piecewise linear subspace that optimally explains the face space for a specific database. Our work is aimed to separate the influence that variance in face shape stamps on the set of eigenfaces in the classical PCA decomposition. In this sense we search for a more efficiently coded face-vector for identification. The ultimate goal consist of finding a non-linear transformation invariant to gesture changes and, in a larger extent, to pose changes. The first part of this paper is dedicated to the shape processor of the system, that is based on a novel shape-based Self Organizing Map, and the second part deals with the subspace PCA decomposition that relies on the SOM clustering. Results are reported by comparing face identification between PCA and the SOM-PCA approach.
Redes neuronales hibridas: variantes constructivas y probabilisticas aplicadas a la clasificacion de patrones
Esta tesis propone nuevas soluciones constructivas al problema del entrenamiento de una red neuro... more Esta tesis propone nuevas soluciones constructivas al problema del entrenamiento de una red neuronal hibrida aplicada a la clasificacion de patrones. El trabajo se plantea desde dos perspectivas distintas: una conexionista utilizando tecnicas fundamentadas en algoritmos propios del campo de las redes neuronales, y otra probabilistica, con soluciones mas afines al campo de la estadistica. Cada uno de estos dos planteamientos deriva en una arquitectura constructiva que es capaz de generar un clasificador de prestaciones comparables a modelos ampliamente difundidos, como el perceptron multicapa (mlp), las redes con funciones de base radial (rbf) o los clasificadores basados en la regla de los k vecinos mas proximos (k-nn). Ambas arquitecturas constructivas incorporan instrumentos para controlar la complejidad del modelo con el proposito de mantener una generalizacion adecuada. El control de la complejidad sirve asimismo, como una forma de detener el proceso de entrenamiento. A lo largo de la tesis se muestra un conjunto de experimentos con datos generados artificialmente que reflejan las prestaciones de ambas redes neuronales y permiten evaluar la influencia, en el crecimiento y en la tasa de error, de los distintos parametros incorporados en los algoritmos. Las pruebas realizadas con datos procedentes de aplicaciones reales corroboran las conclusiones extraidas a partir de las pruebas artificiales y de los teoricos que fundamentan los algoritmos.
IET Biometrics, Jun 28, 2021
Face recognition technology is now mature enough to reach commercial products, such as smart phon... more Face recognition technology is now mature enough to reach commercial products, such as smart phones or tablets. However, it still needs to increase robustness against imposter attacks. In this regard, face Presentation Attack Detection (face-PAD) is a key component in providing trustable facial access to digital devices. Despite the success of several face-PAD works in publicly available datasets, most of them fail to reach the market, revealing the lack of evaluation frameworks that represent realistic settings. Here, an extensive analysis of the generalisation problem in face-PAD is provided, jointly with an evaluation strategy based on the aggregation of most publicly available datasets and a set of novel protocols to cover the most realistic settings, including a novel demographic bias analysis. Besides, a new finegrained categorisation of presentation attacks and instruments is provided, enabling higher flexibility in assessing the generalisation of different algorithms under a common framework. As a result, GRAD-GPAD v2, a comprehensive and modular framework is presented to evaluate the performance of face-PAD approaches in realistic settings, enabling accountability and fair comparison of most face-PAD approaches in the literature. This is an open access article under the terms of the Creative Commons Attribution-NonCommercial License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.
Lecture Notes in Computer Science, 2005
In this paper, a combined shape-texture approach to discriminative face authentication is studied... more In this paper, a combined shape-texture approach to discriminative face authentication is studied. Facial texture information is captured through Gabor responses (jets), similarly to the Elastic Bunch Graph Matching approach, but the points where filters are applied are located over lines that sketch the face. In this way, textural information is "shape-driven" and unlike other Gabor-based approaches, it shows a person-dependent behaviour. For every pair of face images, the score obtained through jets is combined with 3 measurements of pair-wise shape distortion. Discriminative Fisher methods are applied at the shape algorithm level and at the score combination level, in order to get a unified score ready for classification. Face verification results are reported on configuration I of the XM2VTS database.