A5040216542- AI in cancer detection
- Face and Expression Recognition
- Anomaly Detection Techniques and Applications
- Video Surveillance and Tracking Methods
- Face recognition and analysis
- Cell Image Analysis Techniques
- Image Processing Techniques and Applications
- Advanced Image and Video Retrieval Techniques
- Image Retrieval and Classification Techniques
- Adversarial Robustness in Machine Learning
- Radiomics and Machine Learning in Medical Imaging
- Social Robot Interaction and HRI
- Human Pose and Action Recognition
- Digital Imaging for Blood Diseases
- Hand Gesture Recognition Systems
- Medical Image Segmentation Techniques
- Robotics and Automated Systems
- Diatoms and Algae Research
- Advanced Neural Network Applications
- Gaze Tracking and Assistive Technology
- Digital Radiography and Breast Imaging
- Water Quality Monitoring Technologies
- Digital Holography and Microscopy
- Advanced Optical Sensing Technologies
- Advanced Radiotherapy Techniques
University of Castilla-La Mancha
2016-2025
Istanbul Metropolitan Municipality
2025
Cascades (Canada)
2022
Camilo José Cela University
2022
Visma (Norway)
2021
Universidad de Las Palmas de Gran Canaria
2001-2010
Carnegie Mellon University
2009
<h3>Importance</h3> Application of deep learning algorithms to whole-slide pathology images can potentially improve diagnostic accuracy and efficiency. <h3>Objective</h3> Assess the performance automated at detecting metastases in hematoxylin eosin–stained tissue sections lymph nodes women with breast cancer compare it pathologists' diagnoses a setting. <h3>Design, Setting, Participants</h3> Researcher challenge competition (CAMELYON16) develop solutions for node (November 2015-November...
While action recognition has become an important line of research in computer vision, the particular events such as aggressive behaviors, or fights, been relatively less studied. These tasks may be extremely useful several video surveillance scenarios psychiatric wards, prisons even personal camera smartphones. Their potential usability led to a surge interest developing fight violence detectors. One key aspects this case is efficiency, that is, these methods should computationally fast....
Whereas the action recognition problem has become a hot topic within computer vision, detection of fights or in general aggressive behavior been comparatively less studied. Such capability may be extremely useful some video surveillance scenarios like prisons, psychiatric centers even embedded camera phones. Recent work considered well-known Bag-of-Words framework often used generic for specific fight detection. Under this framework, spatio-temporal features are extracted from sequences and...
Diatoms, a kind of algae microorganisms with several species, are quite useful for water quality determination, one the hottest topics in applied biology nowadays. At same time, deep learning and convolutional neural networks (CNN) becoming an extensively used technique image classification variety problems. This paper approaches diatom this technique, order to demonstrate whether it is suitable solving problem. An extensive dataset was specifically collected (80 types, 100 samples/type)...
Action recognition has become a hot topic within computer vision. However, the action community focused mainly on relatively simple actions like clapping, walking, jogging, etc. The detection of specific events with direct practical use such as fights or in general aggressive behavior been comparatively less studied. Such capability may be extremely useful some video surveillance scenarios prisons, psychiatric centers even embedded camera phones. As consequence, there is growing interest...
In an era where security concerns are ever-increasing, the need for advanced technology to detect visible and concealed weapons has become critical. This paper introduces a novel two-stage method handgun detection, leveraging thermal imaging deep learning, offering potential real-world solution law enforcement surveillance applications. The approach first detects firearms at frame level subsequently verifies their association with detected person, significantly reducing false positives...
This dataset comprises 38 breast ultrasound scans from patients, encompassing a total of 683 images. The were conducted using Siemens ACUSON S2000TM Ultrasound System 2022 to 2023. is specifically created for the purpose segmenting lesions, with goal identifying area and contour lesion, as well classifying it either benign or malignant. images can be classified into three categories based on their findings: 419 are normal, 174 benign, 90 ground truth given RGB segmentation masks in...
This paper deals with automatic taxa identification based on machine learning methods. The aim is therefore to automatically classify diatoms, in terms of pattern recognition terminology. Diatoms are a kind algae microorganism high biodiversity at the species level, which useful for water quality assessment. most relevant features diatom description and classification have been selected using an extensive dataset 80 minimum 100 samples/taxon augmented 300 samples/taxon. In addition published...
Introducing efficient automatic violence detection in video surveillance or audiovisual content monitoring systems would greatly facilitate the work of closed-circuit television (CCTV) operators, rating agencies those charge social network content. In this paper we present a new deep learning architecture, using an adapted version DenseNet for three dimensions, multi-head self-attention layer and bidirectional convolutional long short-term memory (LSTM) module, that allows encoding relevant...
Closed-circuit television (CCTV) systems are essential nowadays to prevent security threats or dangerous situations, in which early detection is crucial. Novel deep learning-based methods have allowed develop automatic weapon detectors with promising results. However, these approaches mainly based on visual appearance only. For handguns, body pose may be a useful cue, especially cases where the gun barely visible. In this work, novel method proposed combine, single architecture, both and...
An essential and indispensable component of automated microscopy framework is the automatic focusing system, which determines in-focus position a given field view by searching maximum value function over range z-axis positions. The focus its computation time are crucial to accuracy efficiency system. Sixteen algorithms were analyzed for histological histopathological images. In terms accuracy, results have shown an overall high performance most methods. However, we included in evaluation...
There is a great need to implement preventive mechanisms against shootings and terrorist acts in public spaces with large influx of people. While surveillance cameras have become common, the for monitoring 24/7 real-time response requires automatic detection methods. This paper presents study based on three convolutional neural network (CNN) models applied handguns video images. It aims investigate reduction false positives by including pose information associated way are held images...