Article
Mathematics, Interdisciplinary Applications
Xiaohong Zhang, Mengyuan Li, Hui Liu
Summary: Overlap functions were used in this study to propose two new groups of fuzzy mathematical morphology (FMM) operators, which were applied to image processing and achieved better results than existing algorithms. The first group of operators, called OSFMM operators, was based on overlap functions and structuring elements, and their properties were systematically analyzed. The OSFMM operators were used in combination with the fuzzy C-means (FCM) algorithm to propose a new image edge extraction algorithm (OS-FCM algorithm). The second group of operators, called ORFMM operators, was proposed based on overlap functions and fuzzy relations. Another image edge extraction algorithm (OR-FCM algorithm) was proposed by using ORFMM operators and the FCM algorithm. The results of edge segmentation experiments on multiple standard images showed that the proposed algorithms can extract the complete edge of foreground objects with minimal noise.
FRACTAL AND FRACTIONAL
(2023)
Article
Mathematics
Nina S. T. Hirata, George A. Papakostas
Summary: Morphological operators are nonlinear transformations commonly used in image processing, based on lattice theory. Erosions and dilations are two basic operators that can be combined to build useful operators. Machine learning approaches are being used to design morphological image operators, with recent studies focusing on deep-learning frameworks.
Article
Computer Science, Information Systems
De Rosal Ignatius Moses Setiadi
Summary: This research proposed a dilated hybrid edge detection method for image steganography, which aims to increase the data embedding capacity by expanding the edge area. The results showed that this technique improved the quality and imperceptibility of the stego image.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Maria Herrera-Arellano, Hayde Peregrina-Barreto, Ivan Terol-Villalobos
Summary: This study proposes a method of selective Visible-NIR fusion using top-hat transform, with experimental results showing a high degree of detail preservation in edges while maintaining the color of the image. The method also demonstrates that improvements in image quality were not significantly affected by a change in the color space.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Materials Science, Textiles
Xinxin Li, Meiling Tian, Jinyu He, Jiaqi Di, Aijun Zhang, Xiaohong Qin
Summary: This paper proposes an image-based method to simulate and evaluate high-quality fabric structural features by comparing morphological features from both simulation results and real fabric photographs, effectively avoiding the drawbacks of subjective and visual judgment.
JOURNAL OF ENGINEERED FIBERS AND FABRICS
(2022)
Article
Computer Science, Artificial Intelligence
Mohsine Elkhayati, Youssfi Elkettani, Mohammed Mourchid
Summary: The paper proposes a method based on CNN and MMO to segment handwritten Arabic words into graphemes. It addresses issues related to connections, provides a robust algorithm for diacritics extraction, and utilizes a PD-GE technique for segmentation to combat information loss.
PATTERN RECOGNITION
(2022)
Article
Engineering, Multidisciplinary
Suresh Kumar Tummala, T. Indira Priyadarshini
Summary: Characterization of materials/elements requires SEM analysis, but the accuracy of the captured images may be affected by non-conduction or technical issues. This paper proposes using Python programming to process SEM images for histogram analysis and morphological operations.
INDIAN JOURNAL OF ENGINEERING AND MATERIALS SCIENCES
(2022)
Article
Computer Science, Interdisciplinary Applications
E. Josiah Lutton, Sharon Collier, Till Bretschneider
Summary: This work focuses on detailed 3D segmentation of Dictyostelium cells using high-resolution 3D microscopy, proposing a novel random walker-based method with a curvature enhancement term. Experimental results demonstrate the method's superior performance in segmentation of 3D images, accurately capturing cell features, and also introducing an automated seeding method to facilitate the process.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2021)
Article
Geochemistry & Geophysics
Jieyu Yuan, Wei Cao, Zhanchuan Cai, Binghua Su
Summary: The proposed method in this study aims to enhance underwater images by conducting multiple morphological operations and normalization processes, resulting in improved visibility and detail representation. Experimental results demonstrate that the proposed method effectively enhances the visibility of undersea creatures and improves color balance in the images.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2021)
Article
Computer Science, Artificial Intelligence
Yan Mo, Xudong Kang, Puhong Duan, Bin Sun, Shutao Li
Summary: A novel infrared and visible image fusion method is proposed in this paper, which considers the attributes of objects in source images and utilizes edge-preserving filters and weight-based pyramid fusion strategy to achieve more natural fusion results. Experimental results demonstrate that the proposed method achieves state-of-the-art fusion performance in terms of both visual and objective evaluations. The algorithm is also implemented in an infrared-visible dual sensor system, showing the practicality of the fusion method.
INFORMATION FUSION
(2021)
Article
Computer Science, Information Systems
Bin Zhang
Summary: Grayscale morphology is a powerful tool in image processing, and a reconfigurable processor with a combination of a reconfigurable grayscale processing module and peripheral circuits has been proposed for high-performance embedded systems.
Article
Computer Science, Information Systems
R. Janefer Beula, A. Boyed Wesley
Summary: This study proposes a lung nodule segmentation scheme based on least weight navigation (LWN) to accurately segment lung nodules with low contrast boundaries. The scheme includes three stages: lung segmentation, coarse segmentation of nodules, and fine segmentation of nodules. The proposed approach performs accurate segmentation by accurately detecting boundaries using the LWN algorithm.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Energy & Fuels
Keshav Panthi, Giacomo Valerio Iungo
Summary: This study quantifies the effects of leading-edge erosion on horizontal axis wind turbines using infrared thermographic imaging, meteorological data, and SCADA data. It is found that leading-edge erosion can cause an average annual energy production loss of 3% to 8%. The impact of erosion is higher at lower wind speeds and turbulence intensity.
Article
Chemistry, Multidisciplinary
Jose Luis Sanchez-Salvador, Cristina Campano, Patricio Lopez-Exposito, Quim Tarres, Pere Mutje, Marc Delgado-Aguilar, M. Concepcion Monte, Angeles Blanco
Summary: This study presents a novel approach for the morphological characterization of cellulose nano and microfibers suspensions using eroded microscopy images, which helps discern the mode of fibrillation associated with different extraction conditions. By analyzing skeleton images and aspect ratio data, this method allows for the quantification of various fiber modifications induced by different pretreatment methods, providing a tool for monitoring and controlling CMF/CNF quality and homogeneity in industrial production.
Article
Green & Sustainable Science & Technology
Akshay Koodly Ravishankara, Huseyin Ozdemir, Edwin van der Weide
Summary: Surface degradation of wind turbine blades due to exposure to elements like rain, hail, and insects can lead to aerodynamic performance reduction and power losses. Roughness models are used to study the effect of erosion on flow quantities without the need to accurately model the degraded surface. Different roughness models are evaluated against theoretical models to quantify the reduction in performance of airfoils due to leading edge roughness.
Article
Instruments & Instrumentation
Zengrun Wen, Xiulin Fan, Kaile Wang, Weiming Wang, Song Gao, Wenjing Hao, Yuanmei Gao, Yangjian Cai, Liren Zheng
Summary: This study presents a transition from Q-switched state to continuous wave state in an erbium-doped fiber laser, accompanied by irregular mode-hopping. The results showed that the transition between these two states can be achieved by adjusting the pump power. Modulation peaks were observed on both the Q-switched pulse train and the continuous wave background, and the central wavelength fluctuated.
INFRARED PHYSICS & TECHNOLOGY
(2024)