Detalhes
Nome
António CunhaCargo
Investigador SéniorDesde
01 janeiro 2014
Nacionalidade
PortugalContactos
+351222094106
antonio.cunha@inesctec.pt
2024
Autores
Santos, T; Oliveira, H; Cunha, A;
Publicação
COMPUTER SCIENCE REVIEW
Abstract
In recent years, the number of crimes with weapons has grown on a large scale worldwide, mainly in locations where enforcement is lacking or possessing weapons is legal. It is necessary to combat this type of criminal activity to identify criminal behavior early and allow police and law enforcement agencies immediate action.Despite the human visual structure being highly evolved and able to process images quickly and accurately if an individual watches something very similar for a long time, there is a possibility of slowness and lack of attention. In addition, large surveillance systems with numerous equipment require a surveillance team, which increases the cost of operation. There are several solutions for automatic weapon detection based on computer vision; however, these have limited performance in challenging contexts.A systematic review of the current literature on deep learning-based weapon detection was conducted to identify the methods used, the main characteristics of the existing datasets, and the main problems in the area of automatic weapon detection. The most used models were the Faster R-CNN and the YOLO architecture. The use of realistic images and synthetic data showed improved performance. Several challenges were identified in weapon detection, such as poor lighting conditions and the difficulty of small weapon detection, the last being the most prominent. Finally, some future directions are outlined with a special focus on small weapon detection.
2024
Autores
Fontes, M; De Almeida, JDS; Cunha, A;
Publicação
IEEE Access
Abstract
Explainable Artificial Intelligence (XAI) is an area of growing interest, particularly in medical imaging, where example-based techniques show great potential. This paper is a systematic review of recent example-based XAI techniques, a promising approach that remains relatively unexplored in clinical practice and medical image analysis. A selection and analysis of recent studies using example-based XAI techniques for interpreting medical images was carried out. Several approaches were examined, highlighting how each contributes to increasing accuracy, transparency, and usability in medical applications. These techniques were compared and discussed in detail, considering their advantages and limitations in the context of medical imaging, with a focus on improving the integration of these technologies into clinical practice and medical decision-making. The review also pointed out gaps in current research, suggesting directions for future investigations. The need to develop XAI methods that are not only technically efficient but also ethically responsible and adaptable to the needs of healthcare professionals was emphasised. Thus, the paper sought to establish a solid foundation for understanding and advancing example-based XAI techniques in medical imaging, promoting a more integrated and patient-centred approach to medicine. © 2013 IEEE.
2023
Autores
Pereira, T; Cunha, A; Oliveira, HP;
Publicação
APPLIED SCIENCES-BASEL
Abstract
2023
Autores
Machado, C; Cunha, A; Gouveia, AJ;
Publicação
Procedia Computer Science
Abstract
2023
Autores
Mendes, J; Pereira, T; Silva, F; Frade, J; Morgado, J; Freitas, C; Negrao, E; de Lima, BF; da Silva, MC; Madureira, AJ; Ramos, I; Costa, JL; Hespanhol, V; Cunha, A; Oliveira, HP;
Publicação
EXPERT SYSTEMS WITH APPLICATIONS
Abstract
Biomedical engineering has been targeted as a potential research candidate for machine learning applications, with the purpose of detecting or diagnosing pathologies. However, acquiring relevant, high-quality, and heterogeneous medical datasets is challenging due to privacy and security issues and the effort required to annotate the data. Generative models have recently gained a growing interest in the computer vision field due to their ability to increase dataset size by generating new high-quality samples from the initial set, which can be used as data augmentation of a training dataset. This study aimed to synthesize artificial lung images from corresponding positional and semantic annotations using two generative adversarial networks and databases of real computed tomography scans: the Pix2Pix approach that generates lung images from the lung segmentation maps; and the conditional generative adversarial network (cCGAN) approach that was implemented with additional semantic labels in the generation process. To evaluate the quality of the generated images, two quantitative measures were used: the domain-specific Frechet Inception Distance and Structural Similarity Index. Additionally, an expert assessment was performed to measure the capability to distinguish between real and generated images. The assessment performed shows the high quality of synthesized images, which was confirmed by the expert evaluation. This work represents an innovative application of GAN approaches for medical application taking into consideration the pathological findings in the CT images and the clinical evaluation to assess the realism of these features in the generated images.
Teses supervisionadas
2022
Autor
Ana Sofia Correia Ferreira
Instituição
UTAD
2022
Autor
Ana Cláudia Carvalhais Teixeira
Instituição
UTAD
2022
Autor
Meltem Esengönül
Instituição
UTAD
2021
Autor
Sara Pires da Nóbrega
Instituição
2021
Autor
Dibet Garcia Gonzalez
Instituição
The access to the final selection minute is only available to applicants.
Please check the confirmation e-mail of your application to obtain the access code.