José María Buades Rubio

Fernando Alonso-Fernandez, Kevin Hernandez-Diaz, Jose M. Buades et al.

This paper describes an adaptation of the Local Interpretable Model-Agnostic Explanations (LIME) AI method to operate under a biometric verification setting. LIME was initially proposed for networks with the same output classes used for training, and it employs the softmax probability to determine which regions of the image contribute the most to classification. However, in a verification setting, the classes to be recognized have not been seen during training. In addition, instead of using the softmax output, face descriptors are usually obtained from a layer before the classification layer. The model is adapted to achieve explainability via cosine similarity between feature vectors of perturbated versions of the input image. The method is showcased for face biometrics with two CNN models based on MobileNetv2 and ResNet50.

Fernando Alonso-Fernandez, Kevin Hernandez-Diaz, Jose Maria Buades Rubio et al.

The widespread use of mobile devices for various digital services has created a need for reliable and real-time person authentication. In this context, facial recognition technologies have emerged as a dependable method for verifying users due to the prevalence of cameras in mobile devices and their integration into everyday applications. The rapid advancement of deep Convolutional Neural Networks (CNNs) has led to numerous face verification architectures. However, these models are often large and impractical for mobile applications, reaching sizes of hundreds of megabytes with millions of parameters. We address this issue by developing SqueezerFaceNet, a light face recognition network which less than 1M parameters. This is achieved by applying a network pruning method based on Taylor scores, where filters with small importance scores are removed iteratively. Starting from an already small network (of 1.24M) based on SqueezeNet, we show that it can be further reduced (up to 40%) without an appreciable loss in performance. To the best of our knowledge, we are the first to evaluate network pruning methods for the task of face recognition.

F. Xavier Gaya-Morey, Cristina Manresa-Yee, Jose M. Buades-Rubio

As the percentage of elderly people in developed countries increases worldwide, the healthcare of this collective is a worrying matter, especially if it includes the preservation of their autonomy. In this direction, many studies are being published on Ambient Assisted Living (AAL) systems, which help to reduce the preoccupations raised by the independent living of the elderly. In this study, a systematic review of the literature is presented on fall detection and Human Activity Recognition (HAR) for the elderly, as the two main tasks to solve to guarantee the safety of elderly people living alone. To address the current tendency to perform these two tasks, the review focuses on the use of Deep Learning (DL) based approaches on computer vision data. In addition, different collections of data like DL models, datasets or hardware (e.g. depth or thermal cameras) are gathered from the reviewed studies and provided for reference in future studies. Strengths and weaknesses of existing approaches are also discussed and, based on them, our recommendations for future works are provided.

Álvaro Sabater-Gárriz, F. Xavier Gaya-Morey, José María Buades-Rubio et al.

Background: Pain assessment in individuals with neurological conditions, especially those with limited self-report ability and altered facial expressions, presents challenges. Existing measures, relying on direct observation by caregivers, lack sensitivity and specificity. In cerebral palsy, pain is a common comorbidity and a reliable evaluation protocol is crucial. Thus, having an automatic system that recognizes facial expressions could be of enormous help when diagnosing pain in this type of patient. Objectives: 1) to build a dataset of facial pain expressions in individuals with cerebral palsy, and 2) to develop an automated facial recognition system based on deep learning for pain assessment addressed to this population. Methods: Ten neural networks were trained on three pain image databases, including the UNBC-McMaster Shoulder Pain Expression Archive Database, the Multimodal Intensity Pain Dataset, and the Delaware Pain Database. Additionally, a curated dataset (CPPAIN) was created, consisting of 109 preprocessed facial pain expression images from individuals with cerebral palsy, categorized by two physiotherapists using the Facial Action Coding System observational scale. Results: InceptionV3 exhibited promising performance on the CP-PAIN dataset, achieving an accuracy of 62.67% and an F1 score of 61.12%. Explainable artificial intelligence techniques revealed consistent essential features for pain identification across models. Conclusion: This study demonstrates the potential of deep learning models for robust pain detection in populations with neurological conditions and communication disabilities. The creation of a larger dataset specific to cerebral palsy would further enhance model accuracy, offering a valuable tool for discerning subtle and idiosyncratic pain expressions. The insights gained could extend to other complex neurological conditions.

José María Buades Rubio, Antoni Jaume-i-Capó, David López González et al.

Nonograms are logic puzzles in which cells in a grid must be colored or left blank according to the numbers that are located in its headers. In this study, we analyze different techniques to solve this type of logical problem using an Heuristic Algorithm, Genetic Algorithm, and Heuristic Algorithm with Neural Network. Furthermore, we generate a public dataset to train the neural networks. We published this dataset and the code of the algorithms. Combination of the heuristic algorithm with a neural network obtained the best results. From state of the art review, no previous works used neural network to solve nonograms, nor combined a network with other algorithms to accelerate the resolution process.

F. Xavier Gaya-Morey, Silvia Ramis-Guarinos, Cristina Manresa-Yee et al.

Facial expression recognition is vital for human behavior analysis, and deep learning has enabled models that can outperform humans. However, it is unclear how closely they mimic human processing. This study aims to explore the similarity between deep neural networks and human perception by comparing twelve different networks, including both general object classifiers and FER-specific models. We employ an innovative global explainable AI method to generate heatmaps, revealing crucial facial regions for the twelve networks trained on six facial expressions. We assess these results both quantitatively and qualitatively, comparing them to ground truth masks based on Friesen and Ekman's description and among them. We use Intersection over Union (IoU) and normalized correlation coefficients for comparisons. We generate 72 heatmaps to highlight critical regions for each expression and architecture. Qualitatively, models with pre-trained weights show more similarity in heatmaps compared to those without pre-training. Specifically, eye and nose areas influence certain facial expressions, while the mouth is consistently important across all models and expressions. Quantitatively, we find low average IoU values (avg. 0.2702) across all expressions and architectures. The best-performing architecture averages 0.3269, while the worst-performing one averages 0.2066. Dendrograms, built with the normalized correlation coefficient, reveal two main clusters for most expressions: models with pre-training and models without pre-training. Findings suggest limited alignment between human and AI facial expression recognition, with network architectures influencing the similarity, as similar architectures prioritize similar facial regions.

F. Xavier Gaya-Morey, Jose M. Buades-Rubio, Philippe Palanque et al.

The rapid aging of the global population has highlighted the need for technologies to support elderly, particularly in healthcare and emotional well-being. Facial expression recognition (FER) systems offer a non-invasive means of monitoring emotional states, with applications in assisted living, mental health support, and personalized care. This study presents a systematic review of deep learning-based FER systems, focusing on their applications for the elderly population. Following a rigorous methodology, we analyzed 31 studies published over the last decade, addressing challenges such as the scarcity of elderly-specific datasets, class imbalances, and the impact of age-related facial expression differences. Our findings show that convolutional neural networks remain dominant in FER, and especially lightweight versions for resource-constrained environments. However, existing datasets often lack diversity in age representation, and real-world deployment remains limited. Additionally, privacy concerns and the need for explainable artificial intelligence emerged as key barriers to adoption. This review underscores the importance of developing age-inclusive datasets, integrating multimodal solutions, and adopting XAI techniques to enhance system usability, reliability, and trustworthiness. We conclude by offering recommendations for future research to bridge the gap between academic progress and real-world implementation in elderly care.

F. Xavier Gaya-Morey, Cristina Manresa-Yee, Célia Martinie et al.

This study investigates the key characteristics and suitability of widely used Facial Expression Recognition (FER) datasets for training deep learning models. In the field of affective computing, FER is essential for interpreting human emotions, yet the performance of FER systems is highly contingent on the quality and diversity of the underlying datasets. To address this issue, we compiled and analyzed 24 FER datasets, including those targeting specific age groups such as children, adults, and the elderly, and processed them through a comprehensive normalization pipeline. In addition, we enriched the datasets with automatic annotations for age and gender, enabling a more nuanced evaluation of their demographic properties. To further assess dataset efficacy, we introduce three novel metricsLocal, Global, and Paired Similarity, which quantitatively measure dataset difficulty, generalization capability, and cross-dataset transferability. Benchmark experiments using state-of-the-art neural networks reveal that large-scale, automatically collected datasets (e.g., AffectNet, FER2013) tend to generalize better, despite issues with labeling noise and demographic biases, whereas controlled datasets offer higher annotation quality but limited variability. Our findings provide actionable recommendations for dataset selection and design, advancing the development of more robust, fair, and effective FER systems.

José María Buades Rubio, Gabriel Moyà-Alcover, Antoni Jaume-i-Capó et al.

In this paper, we present a human-based computation approach for the analysis of peripheral blood smear (PBS) images images in patients with Sickle Cell Disease (SCD). We used the Mechanical Turk microtask market to crowdsource the labeling of PBS images. We then use the expert-tagged erythrocytesIDB dataset to assess the accuracy and reliability of our proposal. Our results showed that when a robust consensus is achieved among the Mechanical Turk workers, probability of error is very low, based on comparison with expert analysis. This suggests that our proposed approach can be used to annotate datasets of PBS images, which can then be used to train automated methods for the diagnosis of SCD. In future work, we plan to explore the potential integration of our findings with outcomes obtained through automated methodologies. This could lead to the development of more accurate and reliable methods for the diagnosis of SCD

F. Xavier Gaya-Morey, Silvia Ramis, Jose M. Buades-Rubio et al.

Facial expression recognition has gained significance as a means of imparting social robots with the capacity to discern the emotional states of users. The use of social robotics includes a variety of settings, including homes, nursing homes or daycare centers, serving to a wide range of users. Remarkable performance has been achieved by deep learning approaches, however, its direct use for recognizing facial expressions in individuals with intellectual disabilities has not been yet studied in the literature, to the best of our knowledge. To address this objective, we train a set of 12 convolutional neural networks in different approaches, including an ensemble of datasets without individuals with intellectual disabilities and a dataset featuring such individuals. Our examination of the outcomes, both the performance and the important image regions for the models, reveals significant distinctions in facial expressions between individuals with and without intellectual disabilities, as well as among individuals with intellectual disabilities. Remarkably, our findings show the need of facial expression recognition within this population through tailored user-specific training methodologies, which enable the models to effectively address the unique expressions of each user.

F. Xavier Gaya-Morey, Jose M. Buades-Rubio, I. Scott MacKenzie et al.

We developed REVEX, a removal-based video explanations framework. This work extends fine-grained explanation frameworks for computer vision data and adapts six existing techniques to video by adding temporal information and local explanations. The adapted methods were evaluated across networks, datasets, image classes, and evaluation metrics. By decomposing explanation into steps, strengths and weaknesses were revealed in the studied methods, for example, on pixel clustering and perturbations in the input. Video LIME outperformed other methods with deletion values up to 31\% lower and insertion up to 30\% higher, depending on method and network. Video RISE achieved superior performance in the average drop metric, with values 10\% lower. In contrast, localization-based metrics revealed low performance across all methods, with significant variation depending on network. Pointing game accuracy reached 53\%, and IoU-based metrics remained below 20\%. Drawing on the findings across XAI methods, we further examine the limitations of the employed XAI evaluation metrics and highlight their suitability in different applications.

Nataša Petrović, Gabriel Moyà-Alcover, Antoni Jaume-i-Capó et al.

This work presents a novel approach for selecting the optimal ensemble-based classification method and features with a primarly focus on achieving generalization, based on the state-of-the-art, to provide diagnostic support for Sickle Cell Disease using peripheral blood smear images of red blood cells. We pre-processed and segmented the microscopic images to ensure the extraction of high-quality features. To ensure the reliability of our proposed system, we conducted an in-depth analysis of interpretability. Leveraging techniques established in the literature, we extracted features from blood cells and employed ensemble machine learning methods to classify their morphology. Furthermore, we have devised a methodology to identify the most critical features for classification, aimed at reducing complexity and training time and enhancing interpretability in opaque models. Lastly, we validated our results using a new dataset, where our model overperformed state-of-the-art models in terms of generalization. The results of classifier ensembled of Random Forest and Extra Trees classifier achieved an harmonic mean of precision and recall (F1-score) of 90.71\% and a Sickle Cell Disease diagnosis support score (SDS-score) of 93.33\%. These results demonstrate notable enhancement from previous ones with Gradient Boosting classifier (F1-score 87.32\% and SDS-score 89.51\%). To foster scientific progress, we have made available the parameters for each model, the implemented code library, and the confusion matrices with the raw data.

F. Xavier Gaya-Morey, Julia Sanchez-Perez, Cristina Manresa-Yee et al.

Facial Expression Recognition (FER) systems based on deep learning have achieved impressive performance in recent years. However, these models often exhibit demographic biases, particularly with respect to age, which can compromise their fairness and reliability. In this work, we present a comprehensive study of age-related bias in deep FER models, with a particular focus on the elderly population. We first investigate whether recognition performance varies across age groups, which expressions are most affected, and whether model attention differs depending on age. Using Explainable AI (XAI) techniques, we identify systematic disparities in expression recognition and attention patterns, especially for "neutral", "sadness", and "anger" in elderly individuals. Based on these findings, we propose and evaluate three bias mitigation strategies: Multi-task Learning, Multi-modal Input, and Age-weighted Loss. Our models are trained on a large-scale dataset, AffectNet, with automatically estimated age labels and validated on balanced benchmark datasets that include underrepresented age groups. Results show consistent improvements in recognition accuracy for elderly individuals, particularly for the most error-prone expressions. Saliency heatmap analysis reveals that models trained with age-aware strategies attend to more relevant facial regions for each age group, helping to explain the observed improvements. These findings suggest that age-related bias in FER can be effectively mitigated using simple training modifications, and that even approximate demographic labels can be valuable for promoting fairness in large-scale affective computing systems.