A5032963762- Video Surveillance and Tracking Methods
- AI in cancer detection
- Anomaly Detection Techniques and Applications
- Advanced Vision and Imaging
- COVID-19 diagnosis using AI
- Image Enhancement Techniques
- Advanced Image and Video Retrieval Techniques
- Advanced Image Processing Techniques
- Image and Signal Denoising Methods
- Remote-Sensing Image Classification
- Image Retrieval and Classification Techniques
- Radiomics and Machine Learning in Medical Imaging
- Image Processing Techniques and Applications
- Advanced Neural Network Applications
- Artificial Intelligence in Healthcare
- Neural Networks and Applications
- Learning Styles and Cognitive Differences
- Machine Learning and Data Classification
- Cell Image Analysis Techniques
- Cardiac Imaging and Diagnostics
- Student Assessment and Feedback
- Online Learning and Analytics
- Educational Technology and Assessment
- Air Quality Monitoring and Forecasting
- Domain Adaptation and Few-Shot Learning
Universidad de Málaga
2016-2025
Instituto de Investigación Biomédica de Málaga
2019-2025
Software (Spain)
2024-2025
Andalusian Centre for Nanomedicine and Biotechnology
2023
The automatic detection and classification of vehicles in traffic sequences is a typical task which carried out many practical video surveillance systems. advent deep learning has facilitated the design these However, limitat
In this work we implement a COVID-19 infection detection system based on chest X-ray images with uncertainty estimation. Uncertainty estimation is vital for safe usage of computer aided diagnosis tools in medical applications. Model estimations high should be carefully analyzed by trained radiologist. We aim to improve using unlabelled data through the MixMatch semi-supervised framework. test popular approaches, comprising Softmax scores, Monte-Carlo dropout and deterministic quantification....
Data analysis can unearth important insights like patterns, trends, and deductions. In education, it be utilized to tailor teaching methods suit student traits or devise new activities foster different skills reinforce existing ones, for example. Understanding the particular context past experiences aid in this endeavor. Surveys questionnaires yield a wealth of data. Yet, sheer volume questions lead challenges data management teachers decline interest due time-consuming nature fulfilling...
Support Vector Machines (SVMs) are still one of the most popular and precise classifiers. The Radial Basis Function (RBF) kernel has been used in SVMs to separate among classes with considerable success. However, there is an intrinsic dependence on initial value hyperparameter. In this work, we propose OKSVM, algorithm that automatically learns RBF hyperparameter adjusts SVM weights simultaneously. proposed optimization technique based a gradient descent method. We analyze performance our...
The application of deep learning to image and video processing has become increasingly popular nowadays. Employing well-known pre-trained neural networks for detecting classifying objects in images is beneficial a wide range fields. However, diverse impediments may degrade the performance achieved by those networks. Particularly, Gaussian noise brightness, among others, be presented on as sensor due limitations acquisition devices. In this work, we study effect most representative types...
Ensemble learning has demonstrated its efficiency in many computer vision tasks. In this paper, we address paradigm within content based image retrieval (CBIR). We propose to build an ensemble of convolutional neural networks (CNNs), either by training the CNNs on different bags images, or using trained same dataset, but having architectures. Each network is used extract class probability vectors from images use them as representations. The final representation then generated combining...
Coronavirus (Covid-19) is spreading fast, infecting people through contact in various forms including droplets from sneezing and coughing. Therefore, the detection of infected subjects an early, quick cheap manner urgent. Currently available tests are scarce limited to danger serious illness. The application deep learning chest X- ray images for Covid-19 attractive approach. However, this technology usually relies on availability large labelled datasets, a requirement hard meet context virus...
Video feeds from traffic cameras can be useful for many purposes, the most critical of which are related to monitoring road safety. Vehicle trajectory is a key element in dangerous behavior and accidents. In this respect, it crucial detect those anomalous vehicle trajectories, that is, trajectories depart usual paths. work, model proposed automatically address by using video sequences cameras. The proposal detects vehicles frame frame, tracks their across frames, estimates velocity vectors,...
Abstract Coronary artery disease (CAD) remains the leading cause of death globally and invasive coronary angiography (ICA) is considered gold standard anatomical imaging evaluation when CAD suspected. However, risk based on ICA has several limitations, such as visual assessment stenosis severity, which significant interobserver variability. This motivates to development a lesion classification system that can support specialists in their clinical procedures. Although deep learning methods...
In medical imaging, the lack of high-quality images is present in many areas such as magnetic resonance (MR). Due to acquisition impediments, generated have not enough resolution carry out an adequate diagnosis. Image super-resolution (SR) ill-posed problem that tries fer information from image enhance its resolution. Nowadays, deep learning techniques become a powerful tool extract features and infer new information. MR, most recent works are based on minimization errors between input...
One of the most important challenges in computer vision applications is background modeling, especially when dynamic and input distribution might not be stationary, i.e. data could change with time (e.g. changing illuminations, waving trees, water, etc.). In this work, an unsupervised learning neural network proposed which able to cope progressive changes distribution. It based on a dual mechanism manages separately from cluster detection. The proposal adequate for scenes where varies...
Computer aided diagnosis for mammogram images have seen positive results through the usage of deep learning architectures. However, limited sample sizes target datasets might prevent a model under real world scenarios. The unlabeled data to improve accuracy can be an approach tackle lack data. Moreover, important attributes medical domain as uncertainty improved Therefore, in this work we explore impact using implementation recent known MixMatch, images. We evaluate improvement on and...
Breast cancer is the second most common worldwide, primarily affecting women, while histopathological image analysis one of possibilities used to determine tumor malignancy. Regarding analysis, application deep learning has become increasingly prevalent in recent years. However, a significant issue unbalanced nature available datasets, with some classes having more images than others, which may impact performance models due poorer generalisability. A possible strategy avoid this problem...
Air quality and reduction of emissions in the transport sector are determinant factors achieving a sustainable global climate. The monitoring traffic routes can help to improve route planning design strategies that may make pollution levels be reduced. In this work, method which detects vehicles from images IP cameras by means computer vision techniques neural networks is proposed. Specifically, for each sequence images, homography calculated correct camera perspective determine real...
Coronary artery disease (CAD) remains the leading cause of death globally and invasive coronary angiography (ICA) is considered gold standard anatomical imaging evaluation when CAD suspected. However, risk based on ICA has several limitations, such as visual assessment stenosis severity, which significant interobserver variability. This motivates to development a lesion classification system that can support specialists in their clinical procedures. Although deep learning methods are...
Breast cancer is the second most common worldwide, primarily affecting women, while histopathological image analysis one of possibile methods used to determine tumor malignancy. Regarding analysis, application deep learning has become increasingly prevalent in recent years. However, a significant issue unbalanced nature available datasets, with some classes having more images than others, which may impact performance models due poorer generalizability. A possible strategy avoid this problem...