Article
Computer Science, Artificial Intelligence
Yunyun Yang, Ruicheng Xie, Wenjing Jia, Gang Zhao
Summary: This paper introduces a double level set segmentation model based on mutual exclusion, which accurately and independently segments adjacent regions while maintaining their independence. Experimental results demonstrate the model's high accuracy in segmenting adjacent tissues in brain, as well as its robustness to intensity inhomogeneity and noise in synthetic images. Comparisons with other models show that the double level sets model outperforms classical models in segmenting adjacent tissues.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Engineering, Electrical & Electronic
Ming Dai, Zhiheng Zhou, Tianlei Wang, Yongfan Guo
Summary: In this paper, a novel segmentation model using generalized divergences is proposed based on the traditional level set method. The main advantage of generalized divergences is their smooth connection performance in measuring the discrepancy between two probability distributions of segmented image parts. Experimental results demonstrate the superior performance of the proposed method in both qualitative and quantitative aspects compared to previous active contour models.
CIRCUITS SYSTEMS AND SIGNAL PROCESSING
(2021)
Article
Computer Science, Information Systems
Xingyu Fu, Bin Fang, Mingliang Zhou, Sam Kwong
Summary: This paper presents a new method for image segmentation, using adaptively weighted signed pressure force and Legendre polynomial method to drive an active contour, ensuring high accuracy and computational efficiency for images with inhomogeneous intensity, blurred edges, low contrast, and noise problems.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Information Systems
Daniel Reska, Marek Kretowski
Summary: This paper presents a fast multi-stage image segmentation method that incorporates texture analysis into a level set-based active contour framework. It allows integrating multiple feature extraction methods without the need for prior knowledge of image patterns, and achieves high performance through GPU acceleration. The method is validated on synthetic and natural images and compared with similar algorithms.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Article
Engineering, Electrical & Electronic
Junwei Li, Peng Jiang, He Zhu
Summary: A new active contour model for image segmentation is proposed in this article, which includes local texture information and a Bayesian framework to counteract noise and boundary pollution, improving segmentation accuracy.
IEEE SENSORS JOURNAL
(2021)
Article
Engineering, Electrical & Electronic
Haochen Qi, Xiangwei Kong, Zhunan Shen, Zhitong Liu, Jianyi Gu
Summary: With continuous advancements in sensor technology and computer vision, automated surface defect detection has become an important problem in the modern manufacturing industry. This study introduces a weakly supervised defect segmentation framework called PLDL, which utilizes a progressive learning strategy and an innovative loss function to achieve efficient and accurate defect segmentation without the need for manual supervision or postprocessing steps.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Multidisciplinary Sciences
Mei Zhang, Dan Meng, Lingling Liu, Jinghua Wen
Summary: This paper proposes an improved algorithm based on the no-weight initialization level set model to address the shortcomings of the traditional level set model. The improved method introduces bilateral filters and uses implicit surface level sets to accurately extract and segment the original target image object. Experimental results demonstrate that the improved method achieves better edge contour extraction and noise reduction compared to the traditional non-reinitialized level set model.
Article
Computer Science, Artificial Intelligence
Elizangela de Souza Reboucas, Fatima Nelsizeuma Sombra de Medeiros, Regis Cristiano P. Marques, Joao Victor S. Chagas, Matheus T. Guimaraes, Lucas O. Santos, Aldisio G. Medeiros, Solon A. Peixoto
Summary: Scientific research on methodologies and algorithms to enhance medical diagnostic support remains a top priority, with computer-aided diagnostic systems utilizing the IoT showing promise in improving accessibility and integration. The proposed FLog Parzen Level Set method achieved stable and satisfactory results with low computational costs, demonstrating high accuracy, sensitivity, and MCC values across various datasets.
APPLIED SOFT COMPUTING
(2021)
Article
Chemistry, Analytical
Michal Bembenek, Teodor Mandziy, Iryna Ivasenko, Olena Berehulyak, Roman Vorobel, Zvenomyra Slobodyan, Liubomyr Ropyak
Summary: This paper presents a method for the combined detection of coating and rust damages on painted metal structures using multiclass image segmentation technique. The method utilizes SVM for preliminary classification and valley detection and multiclass level-set approach for advanced damage segmentation. The proposed approach is evaluated using a dataset with ground truth provided by experts, and its accuracy is quantitatively analyzed.
Article
Engineering, Electrical & Electronic
Wenxiu Zhao, Weiwei Wang, Xiangchu Feng, Yu Han
Summary: Selective segmentation is crucial in medical image analysis, and this paper presents a two-phase method using a new image smoothing model and a modified active contour method to achieve efficient and accurate segmentation outcomes. The proposed approach significantly improves existing methods and facilitates the segmentation process.
Article
Computer Science, Artificial Intelligence
Pengshuai Yin, Yanwu Xu, Jinhui Zhu, Jiang Liu, Chang'an Yi, Huichou Huang, Qingyao Wu
Summary: The study introduces a level set based deep learning method for optic disc and cup segmentation, addressing the challenge of injecting domain-specific knowledge into existing segmentation networks. By adding constraints and considering pixel relationships, the proposed method effectively solves the problem. Experimental results confirm the effectiveness of the approach.
Article
Engineering, Electrical & Electronic
Yanjun Ren, Dong Li, Liming Tang
Summary: A variational level set model based on additive decomposition is proposed in this paper to solve the limited performance issue of image segmentation when contaminated by noise and intensity inhomogeneity. The proposed model decomposes the image into three components and regularizes them by different metrics, resulting in improved accuracy and efficiency compared to other methods.
Article
Mathematics
Noor Ain Syazwani Mohd Ghani, Abdul Kadir Jumaat, Rozi Mahmud, Mohd Azdi Maasar, Farizuwana Akma Zulkifle, Aisyah Mat Jasin
Summary: This study proposes a new variational level set model incorporating Self-Organizing Map (SOM) algorithm and Gaussian function for mammography image segmentation. Experimental results indicate that this model achieves higher segmentation accuracy and faster computational speed compared to other iterative models.
Article
Computer Science, Artificial Intelligence
Xiaoliang Lei, Xiaosheng Yu, Jianning Chi, Ying Wang, Jingsi Zhang, Chengdong Wu
Summary: This study introduces an automatic sparse constrained level set method for brain tumor segmentation in MR images, achieving high accuracy and stability through the construction of a sparse representation model and an energy function based on the level set method.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Shuai Dong, Chen Chen, Yihui Liang, Kun Zou, Guisong Liu
Summary: This paper proposes a multi-task framework to address the challenge of defect detection in photovoltaic (PV) glass products. The framework uses an auxiliary semantic segmentation task to assist the main defective classification task, and introduces a new representation of contours called level set map (LSM) to further improve performance. Experimental results show that the proposed framework significantly improves the accuracy of PV glass defective detection.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Liyakathunisa, Abdullah Alsaeedi, Saima Jabeen, Hoshang Kolivand
Summary: Due to the increase in the global aging population, there is a need for continuous supervision and care. This research proposes an ambient assisted living system with the Internet of Medical Things and deep learning techniques to monitor and evaluate elderly activities and vital signs for clinical decision support.
JOURNAL OF AMBIENT INTELLIGENCE AND SMART ENVIRONMENTS
(2022)
Article
Computer Science, Information Systems
Muhammad Talha Ubaid, Tanzila Saba, Hafiz Umer Draz, Amjad Rehman, Muhammad Usman Ghani, Hoshang Kolivand
Summary: Traffic congestion in highly populated urban areas is a serious problem. To address this issue, we have developed a system that can detect and count vehicles in real-time and reduce congestion through signal automation.
Article
Computer Science, Hardware & Architecture
Tanzila Saba, Amjad Rehman, Tariq Sadad, Hoshang Kolivand, Saeed Ali Bahaj
Summary: The Internet of Things (IoT) has brought various smart devices and applications to enhance people's lives, but security threats remain the main challenge for devices in an IoT environment. This paper introduces a CNN-based anomaly-based intrusion detection system that takes advantage of IoT's capabilities to efficiently examine the entire IoT traffic and demonstrates a high accuracy in detecting intrusions.
COMPUTERS & ELECTRICAL ENGINEERING
(2022)
Article
Water Resources
Rab Nawaz Bashir, Imran Sarwar Bajwa, Muhammad Zahid Abbas, Amjad Rehman, Tanzila Saba, Saeed Ali Bahaj, Hoshang Kolivand
Summary: Soil salinity is a common problem in agriculture that interferes with plant growth. This study proposes a cost-effective and portable solution for quantifying and mapping soil salinity using Internet of Things (IoT) technology. The proposed IoT-assisted salinity mapping accurately measures the impact of reclamation activities on saline soil, making it useful for site-specific treatments and soil zone management.
APPLIED WATER SCIENCE
(2022)
Article
Computer Science, Artificial Intelligence
Hoshang Kolivand, Ainul Azura Binti Abdul Hamid, Shiva Asadianfam, Mohd Shafry Mohd Rahim
Summary: The article introduces an improved image enhancement method to improve the quality and accuracy of scarred fingerprint images. The method utilizes noise removal and ridge structure reconstruction to enhance the image. Evaluation of the method shows a 37% improvement in quality index compared to other related research, highlighting the significance of the approach in the field of fingerprint image enhancement.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Telecommunications
Pouya Demokri Dizji, Saba Joudaki, Hoshang Kolivand
Summary: This article introduces a traffic sign recognition algorithm that uses color segmentation, support vector machines, and histograms of oriented gradients. By employing meta-heuristic algorithms for image segmentation, significant improvements are achieved.
WIRELESS PERSONAL COMMUNICATIONS
(2022)
Article
Computer Science, Information Systems
Muhammad Usman Ghani Khan, Abdullah Tariq, Tanzila Saba, Amjad Rehman, Hoshang Kolivand
Summary: There is a growing demand for virtual cloth fitting networks due to the increasing trend of online shopping, where the goal is to map target clothes onto a reference subject. Previous research has shown limitations in generating deformed clothes on the wearer's body while preserving design features. The proposed model overcomes these limitations by learning thin-plate spline transformations and incorporating a try-on module, resulting in fine details and promising generalized results.
Review
Computer Science, Information Systems
Hoshang Kolivand, Shiva Asadianfam, Kayode Akinlekan Akintoye, Mohd Shafry Rahim
Summary: This paper provides a comprehensive review of previous research in the field of finger vein recognition system, focusing on the advancements and limitations of finger vein enhancements and features extraction. It discusses the biometric system as well as the finger vein identification process, including image acquisition, preprocessing, feature extraction, and vein matching. The study examines the related work and issues in the field, proposing solutions to each issue. It also presents a detailed analysis of existing techniques based on various qualities and features, facilitating the comparison and evaluation for new researchers in this area.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Hoshang Kolivand, Kayode Akinlekan Akintoye, Shiva Asadianfam, Mohd Shafry Rahim
Summary: This paper addresses the issue of low-quality data affecting finger vein identification by proposing a new image enhancement and feature extraction method. The new image enhancement method improves performance by enhancing image quality and preserving edges. The feature extraction method improves performance by fusing the Hierarchical Centroid Feature Method with the statistical pixel-based distribution feature method at the feature-level fusion.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Correction
Computer Science, Information Systems
Hoshang Kolivand, Kayode Akinlekan Akintoye, Shiva Asadianfam, Mohd Shafry Rahim
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Meshal Albeedan, Hoshang Kolivand, Ramy Hammady
Summary: This research explores the adoption of Mixed Reality headsets and their applications for investigation training practices. The results indicate that task technology fit has a positive impact on the perceived usefulness of MR headset applications, individual technology fit has a positive impact on the perceived ease of use, and the mobility of MR wearable devices positively influences the perceived ease of use and perceived usefulness for crime scene practices.
Proceedings Paper
Computer Science, Artificial Intelligence
Wasiq Khan, Bilal Muhammed Khan, Luke Topham, Salwa Yasen, Ahmed Al-Dahiri, Hoshang Kolivand, Marley M. B. R. Vellasco, Abir Hussain
Summary: Covid-19 vaccine acceptance for children varies significantly based on sociodemographic factors such as ethnicity, age group, and gender.
2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Hoshang Kolivand, Deepika Dhanabalan Kannan, Shiva Asadianfam
Summary: The use of sign language gestures is essential for communication among the hearing impaired or deaf individuals. British Sign Language (BSL) is popular in the UK for this purpose. Existing systems for translating natural language to sign language face challenges such as limited storage capacity, instability, and reduced performance. A proposed internet-based system aims to improve accuracy and efficiency of sign language translation by utilizing a database and online accessibility.
2022 FIFTH INTERNATIONAL CONFERENCE OF WOMEN IN DATA SCIENCE AT PRINCE SULTAN UNIVERSITY (WIDS-PSU 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Hoshang Kolivand, Shiva Asadianfam, Daniel Wrotkowski
Summary: Nowadays, one out of every four people in the world is a gamer, resulting in a massive gaming industry and frequent encounters with gaming-related content in everyday life. This project aims to minimize the negative impact of games, particularly those involving violence, on society. The main objective is to develop a program that can assess whether a person is suitable to play violent games. Additionally, materials will be shared to educate individuals about the negative effects of excessive gaming device usage and promote alternative ways to spend time without electronics.
EMERGING TECHNOLOGY TRENDS IN INTERNET OF THINGS AND COMPUTING, TIOTC 2021
(2022)
Proceedings Paper
Art
Hoshang Kolivand, Shiva Asadianfam, Daniel Wrotkowski
Summary: Video games, like books and movies, are often used in an antisocial way and do not provide a cure. However, they do allow players to learn and experience reality from a different perspective, enabling them to think, speak, and act in new ways.
INTELLIGENT TECHNOLOGIES FOR INTERACTIVE ENTERTAINMENT, INTETAIN 2021
(2022)