Papers by Yoanna Martínez-Díaz
2020 25th International Conference on Pattern Recognition (ICPR)
Lecture Notes in Computer Science, 2012
Face representation is one of the open problems in face detection. The recently proposed Multi-Bl... more Face representation is one of the open problems in face detection. The recently proposed Multi-Block Local Binary Patterns (MB-LBP) representation has shown good results for this purpose. Although dissimilarity representation has proved to be effective in a variety of pattern recognition problems, to the best of our knowledge, it has never been used for face detection. In this paper, we propose new dissimilarity representations based on MB-LBP features for this task. Different experiments conducted on a public database, showed that the proposed representations are more discriminative than the original MB-LBP representation when classifying faces. Using the dissimilarity representations, a good classification accuracy is achieved even when less training data is available.
Lecture Notes in Computer Science, 2012
Traditional appearance-based methods for face recognition represent raw face images of size u × v... more Traditional appearance-based methods for face recognition represent raw face images of size u × v as vectors in a u × v-dimensional space. However in practice, this space can be too large to perform classification. For that reason, dimensionality reduction techniques are usually employed. Most of those traditional approaches do not take advantage of the spatial correlation of pixels in the image, considering them as independent. In this paper, we proposed a new representation of face images that takes into account the smoothness and continuity of the face image and at the same time deals with the dimensionality of the problem. This representation is based on Functional Data Analysis so, each face image is represented by a function and a recognition algorithm for functional spaces is formulated. The experiments on the AT&T and Yale B facial databases show the effectiveness of the proposed method.
2013 International Conference on Biometrics (ICB), 2013
In the last years spatio-temporal representations have shown to be successful for the analysis of... more In the last years spatio-temporal representations have shown to be successful for the analysis of video sequences in applications such as event detection, action and face recognition in videos. In this paper, we propose the use of local spatio-temporal features for the faces/non-faces classification stage, in the process of face detection in videos. Specifically, the extension of the Local Binary Patterns operator to the spatio-temporal domain is evaluated and compared with other schemes based on the same operator without considering the temporal information. The obtained results in the very challenged YouTube Faces database show that combining local appearance with motion can help to discriminate between faces and non-faces in the context of video applications.
2013 International Conference on Biometrics (ICB), 2013
ABSTRACT It has been shown in different studies the benefits of using spatio-temporal information... more ABSTRACT It has been shown in different studies the benefits of using spatio-temporal information for video face recognition. However, most of the existing spatio-temporal representations do not capture the local discriminative information present in human faces. In this paper we introduce a new local spatio-temporal descriptor, based on structured ordinal features, for video face recognition. The proposed method not only encodes jointly the local spatial and temporal information, but also extracts the most discriminative facial dynamic information while trying to discard spatio-temporal features related to intra-personal variations. Besides, a similarity measure based on a set of background samples is proposed to be used with our descriptor, showing to boost its performance. Extensive experiments conducted on the recent but difficult YouTube Faces database demonstrate the good performance of our proposal, achieving state-of-the-art results.
IEEE Access
Given the current COVID-19 pandemic, most people wear a mask to effectively prevent the spread of... more Given the current COVID-19 pandemic, most people wear a mask to effectively prevent the spread of the contagious disease. This sanitary measure has caused a significant drop in the effectiveness of current face recognition methods when handling masked faces on practical applications such as face access control, face attendance, and face authentication-based mobile payment. Under this situation, recent efforts have been focused on boosting the performance of the existing face recognition technology on masked faces. Some solutions trying to tackle this issue fine-tune the existing deep learning face recognition models on synthetic masked images, while others use the periocular region as a naive manner to eliminate the adverse effect of COVID-19 masks. Although the accuracy of masked face recognition remains an important issue, in the last few years, the development of efficient and lightweight face recognition methods has received an increased attention in the research community. In this paper, we study the effectiveness of three state-of-the-art lightweight face recognition models for addressing accurate and efficient masked face recognition, considering both fine-tuning on masked faces and periocular images. For the experimental evaluation, we create both real and simulated masked face databases as well as periocular datasets. Extensive experiments are conducted to determine the most effective solution and state further steps for the research community. The obtained results disclose that fine-tuning existing state-of-the-art face models on masked images achieve better performance than using periocular-based models. Besides, we evaluate and analyze the effectiveness of the trained masked-based models on well-established unmasked benchmarks for face recognition and assess the efficiency of the used lightweight architectures in comparison with state-of-theart face models.
The use of the ear in biometric recognition has been widely covered in controlled environments. H... more The use of the ear in biometric recognition has been widely covered in controlled environments. However, the advantages of the ear as a biometric characteristic impose the need to know how it behaves in unconstrained scenarios, where it is common the presence of occlusions, pose variations, illumination changes and different resolutions. According to this challenge and considering the experience in other biometric recognition processes, the alignment has shown to be a key step. In this work, we carry out an exhaustive and detailed study of the impact of the alignment on the performance of several state-of-the-art ear descriptors, when the images are captured in uncontrolled conditions. Our analysis is based on identification experiments against different types of variations in ears image of the challenging UERC dataset. The obtained results corroborate the hypothesis of the alignment also improves the efficacy of the ear recognition process and show how this improvement behaves for ...
Deep Convolutional Neural Networks (DCNN) are the state-of-the-art in face recognition. In this p... more Deep Convolutional Neural Networks (DCNN) are the state-of-the-art in face recognition. In this paper, we study different representations obtained from a pre-trained DCNN, in order to determine the best way in which they can be used in different tasks. In particular, we evaluate the use of intermediate representations independently or combined with a Fisher Vector approach, or with a Bilinear model. From our study, we found that convolutional features may be more suitable than the features obtained from the last fully connected layers for different applications.
We conduct an ISO/IEC Standards 24745 and 30136 compliant assessment of block-based warping sampl... more We conduct an ISO/IEC Standards 24745 and 30136 compliant assessment of block-based warping sample transformation techniques aiming for template protection. Particular focus is laid on the results' evaluation considering the evolution of face recognition technology ranging from more “historic” hand-crafted features to state-of-the-art deep-learning (DL) based schemes. It turns out that the high robustness of todays face recognition technology can handle geometrical distortions introduced by warping as another form of variability like pose, illumination, and expression variations, thereby disabling the intended protection functionality of warping. Therefore, block-based warping sample transformation must not be used as template protection technique for todays state-of-the-art face recognition schemes, while some settings could be identified providing template protection to some extent for less recent face recognition technology.
When biometric databases grow larger, a security breach or leak can affect millions. In order to ... more When biometric databases grow larger, a security breach or leak can affect millions. In order to protect against such a threat, the use of encryption is a natural choice. However, a biometric identification attempt then requires the decryption of a potential huge database, making a traditional approach potentially unfeasible. The use of selective JPEG2000 encryption can reduce the encryption’s computational load and enable a secure storage of biometric sample data. In this paper we will show that selective encryption of face biometric samples is secure. We analyze various encoding settings of JPEG2000, selective encryption parameters on the "Labeled Faces in the Wild" database and apply several traditional and deep learning based face recognition methods.
La alineacion de imagenes es un paso crucial en los sistemas de reconocimiento basado en imagenes... more La alineacion de imagenes es un paso crucial en los sistemas de reconocimiento basado en imagenes biometricas, ya que facilita su analisis y comparacion. En particular, las imagenes de la oreja pueden presentar problemas de oclusion por el pelo, pendientes o sombreros. Estas oclusiones disminuyen la zona de reconocimiento de este objeto biometrico; asi como la variacion de la iluminacion en el proceso de captura aumenta la dificultad de extraccion de rasgos o puntos fiduciales. La informacion mutua es una tecnica estadistica basada en la informacion proporcionada por la distribucion de las intensidades en las imagenes. El metodo propuesto basado en esta tecnica no depende de los valores reales de los pixeles sino de como estan distribuidos en la imagen, esto le permite enfrentar problemas de oclusion, efectos de la iluminacion, y ruido. En este trabajo, mostraremos la utilidad de la informacion mutua entre las imagenes de orejas para su alineacion. Para ello, se realizaron varios ex...
Artificial Intelligence Review
This paper studies the impact of lightweight face models on real applications. Lightweight archit... more This paper studies the impact of lightweight face models on real applications. Lightweight architectures proposed for face recognition are analyzed and evaluated on different scenarios. In particular, we evaluate the performance of five recent lightweight architectures on five face recognition scenarios: image and video based face recognition, cross-factor and heterogeneous face recognition, as well as active authentication on mobile devices. In addition, we show the lacks of using common lightweight models unchanged for specific face recognition tasks, by assessing the performance of the original lightweight versions of the lightweight face models considered in our study. We also show that the inference time on different devices and the computational requirements of the lightweight architectures allows their use on real-time applications or computationally limited platforms. In summary, this paper can serve as a baseline in order to select lightweight face architectures depending on the practical application at hand. Besides, it provides some insights about the remaining challenges and possible future research topics.
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
publication descriptionProceedings of the 25th International Conference on Pattern Recognition (ICPR 2020), 2021
Typically, real-world requirements to deploy face recognition models in unconstrained surveillanc... more Typically, real-world requirements to deploy face recognition models in unconstrained surveillance scenarios demand to identify low-resolution faces with extremely low computational cost. In the last years, several methods based on complex deep learning models have been proposed with promising recognition results but at a high computational cost. Inspired by the compactness and computation efficiency of lightweight deep face networks and their high accuracy on general face recognition tasks, in this work we propose to benchmark two recently introduced lightweight face models on low-resolution surveillance imagery to enable efficient system deployment. In this way, we conduct a comprehensive evaluation on the two typical settings: LR-to-HR and LR-to-LR matching. In addition, we investigate the effect of using trained models with down-sampled synthetic data from high-resolution images, as well as the combination of different models, for face recognition on real low-resolution images. Ex...
2016 23rd International Conference on Pattern Recognition (ICPR), 2016
One of the main problems of recognizing faces in videos is to achieve accurate algorithms which c... more One of the main problems of recognizing faces in videos is to achieve accurate algorithms which can be used in real-time applications. Recently, Fisher Vector representation of local descriptors (e.g., SIFT) has gained widespread popularity, achieving good recognition rates. In this work, we propose to use Fisher Vector encoding of binary features for video face recognition, in order to speed up the computation time of the representation. The experimental evaluation was conducted on the challenging YouTube Faces database, showing that the proposed method is very efficient, and has an accuracy comparable with state-of-the-art methods.
IEEE Access
In the past decade, research in the face recognition area has advanced tremendously, particularly... more In the past decade, research in the face recognition area has advanced tremendously, particularly in uncontrolled scenarios (face recognition in the wild). This advancement has been achieved partly due to the massive popularity and effectiveness of deep convolutional neural networks and the availability of larger unconstrained datasets. However, several face recognition challenges remain in the context of very low resolution homogeneous (same domain) and heterogeneous (different domain) face recognition. In this survey, we study the seminal and novel methods to tackle the very low resolution face recognition problem and provide an in-depth analysis of their design, effectiveness, and efficiency for a real-time surveillance application. Furthermore, we analyze the advantage of employing deep learning convolutional neural networks, while presenting future research directions for effective deep learning network design in this context.
2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)
The recent success of convolutional neural networks has led to the development of a variety of ne... more The recent success of convolutional neural networks has led to the development of a variety of new effective and efficient architectures. However, few of them have been designed for the specific case of face recognition. Inspired on the state-of-the-art ShuffleNetV2 model, a lightweight face architecture is presented in this paper. The proposal, named ShuffleFaceNet, introduces significant modifications in order to improve face recognition accuracy. First, the Global Average Pooling layer is replaced by a Global Depth-wise Convolution layer, and Parametric Rectified Linear Unit is used as a non-linear activation function. Under the same experimental conditions, ShuffleFaceNet achieves significantly superior accuracy than the original ShuffleNetV2, maintaining the same speed and compact storage. In addition, extensive experiments conducted on three challenging benchmark face datasets, show that our proposal improves not only state-of-the-art lightweight models but also very deep face recognition models.
Lecture Notes in Computer Science, 2017
Intelligent Data Analysis, 2016
Uploads
Papers by Yoanna Martínez-Díaz