Article
Computer Science, Software Engineering
Kunal Pradhan, Swarnajyoti Patra
Summary: Based on recent developments, the challenge in texture filtering lies in removing irregular and varying scale texture while preserving structural contents with minimal distortion. To address this issue, we propose a semantic-aware structure-preserving filtering technique. This technique generates an edge-map using semantic information extracted from global and local morphological gradient histograms, and then utilizes the edge-map to implement an adaptive median morpho-filtering with a dynamic window that avoids overlapping of textural and structural contents. Experimental results with various images demonstrate the potential of our proposed technique compared to state-of-the-art methods.
Article
Engineering, Electrical & Electronic
David B. Tay
Summary: Graph wavelet transforms are effective in representing signals over irregular domains by encoding salient features. Nonlinear graph wavelets based on the median operator are proposed to construct more modular and edge-aware transforms. This nonlinear transform has similar spectral characteristics to the linear counterpart and can separate low-pass and high-pass features in a signal. It does not require preprocessing for edge detection and can be applied to nonlinear approximation and denoising.
IEEE TRANSACTIONS ON SIGNAL PROCESSING
(2023)
Article
Optics
Shuma Takeda, Mashiho Mukaida, Noriaki Suetake
Summary: In this letter, the authors propose a new edge-preserving smoothing filter called the cuboid filter. The cuboid filter calculates the mean of 3D neighboring pixels and achieves good performance in reducing small-amplitude noise and fast filtering. The effectiveness and validity of the cuboid filter are demonstrated through qualitative and quantitative evaluations.
Article
Engineering, Electrical & Electronic
Wei Cao, Shiqian Wu, Jiaxin Wu, Zhaoyi Liu, Yuwen Li
Summary: This paper introduces a relative bilateral filter with a conditional constraint (RBFC) to address the challenge of determining the tradeoff between over-smoothing and under-smoothing in image texture filtering. Inspired by scale-space theory and intensive experiments, the proposed method effectively captures and suppresses weak large-scale textures while also discovering and suppressing strong small-scale textures. Qualitative and quantitative experiments show the superior performance of the RBFC in preserving image smoothness compared to state-of-the-art methods.
IEEE SIGNAL PROCESSING LETTERS
(2021)
Article
Health Care Sciences & Services
Quan Yuan, Zhenyun Peng, Zhencheng Chen, Yanke Guo, Bin Yang, Xiangyan Zeng
Summary: A weighted coding algorithm based on edge-preserving median filtering and sparse nonlocal regularization was proposed to remove noise in CT images, showing superior denoising performance compared to using median filtering or sparse nonlocal regularization alone. The study highlighted the potential application value of this algorithm in low-dose CT image denoising.
JOURNAL OF HEALTHCARE ENGINEERING
(2021)
Proceedings Paper
Computer Science, Interdisciplinary Applications
Kunal Pradhan, Swarnajyoti Matra
Summary: In this work, a novel structure preserving texture filtering technique is proposed by detecting structural edges of the image. The technique utilizes Jensen Shannon Divergence to detect structural edges and defines a dynamic window for filtering with the help of the detected edges. Experimental results demonstrate the potential of the proposed technique.
2022 IEEE CALCUTTA CONFERENCE, CALCON
(2022)
Article
Geochemistry & Geophysics
Rong-Huo Dai, Yu-Pei Zhang, Fan-Chang Zhang, Cheng Yin
Summary: Seismic attributes, such as seismic impedance and AVO attributes, enhance geological interpretation, but their calculation may introduce noise. The edge-preserving smoothing method filters noise while preserving important stratigraphic features, but conventional methods may suppress small geological details. The adaptive EPS filter balances noise removal and geological information protection through using various window sizes.
JOURNAL OF SEISMIC EXPLORATION
(2021)
Article
Engineering, Multidisciplinary
Firas Mahmood Mustafa, Haval Sulaiman Abdullah, Atilla Elci
Summary: This study proposes a new method for image noise reduction using threshold and histogram equalization in the wavelet domain. Different wavelet filters were tested to achieve the best results for image noise reduction.
JOURNAL OF ENGINEERING RESEARCH
(2022)
Proceedings Paper
Computer Science, Software Engineering
Wenming Tang, Yuanhao Gong, Linyu Su, Wenhui Wu, Guoping Qiu
Summary: This paper introduces a new edge-preserving image smoothing technique by categorizing pixels and adaptively selecting support regions, showing significant effectiveness in experimental results.
IMAGE AND GRAPHICS (ICIG 2021), PT III
(2021)
Article
Medical Laboratory Technology
K. Durga Prasad, R. Ramadevi
Summary: This study aims to minimize noise in liver images using median filters and wiener filters, and analyzed the output of both filters based on their PSNR. The results show that the innovative median filter has a higher PSNR than the wiener filter in ultrasound liver pictures.
Article
Medical Laboratory Technology
K. Durga Prasad, R. Ramadevi
Summary: The goal of this study is to reduce noise in liver images using median filters and mask filters. The study compares the Peak Signal to Noise Ratio (PSNR) of both filters. The results show that the innovative median filter has a higher PSNR compared to the mask filter for enhancing ultrasound liver images.
Proceedings Paper
Automation & Control Systems
Aleksandra Kawala-Sterniuk, Amir F. Al-Bakri, Mariusz Pelc, Katarzyna Cichon, Wojciech Chlewicki, Stepan Ozana, Radek Martinek, Jakub Mozaryn, Volodymyr Khoma, Halyna Kenyo, Edward Jacek Gorzelanczyk, Michal Podpora, Jaroslaw Zygarlicki
Summary: This study researched the identification of bioimpedance spectroscopy parameters by implementing various smoothing filters, discussing their application in embedded systems. The results showed promising outcomes with the implementation of smoothing filters, but some were unsatisfactory.
Editorial Material
Health Care Sciences & Services
Orazio Gambino, Vincenzo Conti, Sergio Galdino, Cesare Fabio Valenti, Wellington Pinheiro dos Santos
JOURNAL OF HEALTHCARE ENGINEERING
(2019)
Article
Chemistry, Multidisciplinary
Hadi Hamad, Tahreer Dwickat, Domenico Tegolo, Cesare Valenti
Summary: The study developed an automated method for identifying exudates, allowing for disease warning and patient tracking. By using public domain datasets as benchmarks, the method achieved high levels of sensitivity, specificity, and accuracy through pixel-wise extraction of exudates.
APPLIED SCIENCES-BASEL
(2021)
Article
Environmental Sciences
Matia Fazio, Christian Lombardo, Giuseppe Marino, Anand Marya, Pietro Messina, Giuseppe Alessandro Scardina, Antonino Tocco, Francesco Torregrossa, Cesare Valenti
Summary: This paper presents an Android/iOS application for low-cost mobile devices that aids in dental diagnosis through questionnaires and photos. The main advantages of this app lie in its user-friendly interface even for inexperienced users, the low hardware requirements that allow for wide usage, and the ability to modify the questionnaire for different dental conditions.
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
(2022)
Article
Computer Science, Artificial Intelligence
Massimo Cossentino, Davide Guastella, Salvatore Lopes, Luca Sabatucci, Mario Tripiciano
Summary: Emergency response plans are complex collaborations that require clear roles and responsibilities. This paper proposes a method for converting free-form plan documents into structured versions, allowing for quick understanding and the potential for an automatic emergency support system.
INTELLIGENZA ARTIFICIALE
(2022)
Article
Immunology
Adriana Acquaro, Giorgia Brusca, Sofia Casella, Enzo Maria Cumbo, Antonio Valle, Mohmed Isaqali Karobari, Giuseppe Marino, Anand Marya, Pietro Messina, Giuseppe Alessandro Scardina, Domenico Tegolo, Antonino Tocco, Cesare Valenti
Summary: This study using capillaroscopy examined the changes in oral microcirculation after receiving a COVID-19 vaccine. The results indicated an increase in capillary density in the lips of vaccinated patients, which may be attributed to increased angiogenic activity.
Article
Computer Science, Information Systems
M. E. Tabacchi, D. Tegolo, D. Cascio, C. Valenti, S. Sorce, V Gentile, V Taormina, I Brusca, G. Magazzu, A. Giuliano, G. Raso
Summary: Coeliac disease is a common food intolerance affecting about 1% of the population, but it is often underdiagnosed. This paper presents a Clinical Decision Support System (CDSS) for CD diagnosis, using artificial intelligence techniques. The CDSS achieved high accuracy and sensitivity in diagnosing CD without the need for invasive techniques such as biopsy, based on analysis of virtual and real databases.
Article
Pediatrics
Giuseppe Magazzu, Samuel Aquilina, Christopher Barbara, Ramon Bondin, Ignazio Brusca, Jacqueline Bugeja, Mark Camilleri, Donato Cascio, Stefano Costa, Chiara Cuzzupe, Annalise Duca, Maria Fregapane, Vito Gentile, Angele Giuliano, Alessia Grifo, Anne-Marie Grima, Antonio Ieni, Giada Li Calzi, Fabiana Maisano, Giuseppinella Melita, Socrate Pallio, Ilenia Panasiti, Salvatore Pellegrino, Claudio Romano, Salvatore Sorce, Marco Elio Tabacchi, Vincenzo Taormina, Domenico Tegolo, Andrea Tortora, Cesare Valenti, Cecil Vella, Giuseppe Raso
Summary: This study conducted the largest screening project for coeliac disease in school children, aiming to evaluate the diagnostic accuracy of minimally invasive finger prick point-of-care tests and provide a better quality of life for patients by reducing the costs associated with coeliac disease diagnosis.
Proceedings Paper
Computer Science, Artificial Intelligence
Davide Andrea Guastella, Nicolas Verstaevel, Cesare Valenti, Bilal Arshad, Johan Barthelemy
Summary: This paper introduces a dataset of environmental information obtained through indoor and outdoor sensors, along with a novel approach based on an evolutionary algorithm for determining pairs of correlated sensors. Experimental results show that the evolutionary method achieves an average accuracy of about 62.92% and the computational time is evaluated for real-time applications.
ICAART: PROCEEDINGS OF THE 13TH INTERNATIONAL CONFERENCE ON AGENTS AND ARTIFICIAL INTELLIGENCE - VOL 1
(2021)
Article
Computer Science, Information Systems
Davide Andrea Guastella, Guilhem Marcillaud, Cesare Valenti
Summary: Smart cities utilize large amounts of data and decision support tools to monitor the urban environment and improve service quality. The increasing use of personal Internet of things devices allows for low-cost data acquisition but also presents challenges. Edge computing emerges as a solution to analyze data locally. Experiments confirm the effectiveness of the proposed method.
Article
Medicine, General & Internal
Giuseppe A. Scardina, Giovanni Guercio, Cesare F. Valenti, Domenico Tegolo, Pietro Messina
JOURNAL OF CLINICAL MEDICINE
(2020)
Article
Computer Science, Information Systems
Davide Andrea Guastella, Valerie Camps, Marie-Pierre Gleizes
Proceedings Paper
Computer Science, Artificial Intelligence
Davide Andrea Guastella, Valerie Camps, Marie-Pierre Gleizes
PRINCIPLES AND PRACTICE OF MULTI-AGENT SYSTEMS (PRIMA 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Giuseppa Sciortino, Domenico Tegolo, Cesare Valenti
PATTERN RECOGNITION (MCPR 2017)
(2017)
Proceedings Paper
Automation & Control Systems
Giuseppa Sciortino, Domenico Tegolo, Cesare Valenti
2017 XXVI INTERNATIONAL CONFERENCE ON INFORMATION, COMMUNICATION AND AUTOMATION TECHNOLOGIES (ICAT)
(2017)