Article
Automation & Control Systems
Rifat Kurban, Ali Durmus, Ercan Karakose
Summary: This study uses multiple metaheuristic algorithms for multilevel color image thresholding, with MPA and TFWO outperforming other algorithms in terms of image quality evaluation and CPU time consumption.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2021)
Article
Computer Science, Artificial Intelligence
Caijie Shang, Dong Zhang, Yan Yang
Summary: A gradient-based method different from bionic algorithms is proposed in this paper for optimal multilevel thresholds search in image segmentation. Experiments show that this method is efficient in computation and has equal or better performance of segmentation compared to other algorithms.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Essam H. Houssein, Kashif Hussain, Laith Abualigah, Mohamed Abd Elaziz, Waleed Alomoush, Gaurav Dhiman, Youcef Djenouri, Erik Cuevas
Summary: The paper introduces an enhanced version of the Marine Predators Algorithm (MPA) called MPA-OBL, which incorporates Opposition-Based Learning (OBL) to improve search efficiency and convergence. Through comprehensive experiments, MPA-OBL is shown to outperform other algorithms in solving complex optimization problems, demonstrating superior quality of solutions and faster convergence speed.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Mathematical & Computational Biology
Shikai Wang, Kangjian Sun, Wanying Zhang, Heming Jia
Summary: The paper proposes a modified ant lion optimizer algorithm based on opposition-based learning for optimizing multilevel thresholding in image segmentation, and experimental results show that the method outperforms others in terms of segmentation performance.
MATHEMATICAL BIOSCIENCES AND ENGINEERING
(2021)
Article
Computer Science, Artificial Intelligence
Mohamed Abdel-Basset, Victor Chang, Reda Mohamed
Summary: Image segmentation is a crucial step in image analysis and research, with various techniques proposed to improve the quality of segmentation. A novel meta-heuristic equilibrium algorithm was introduced to find the optimal threshold for grayscale image segmentation, showing enhanced accuracy in research analysis. Comparative performance evaluation with other algorithms demonstrated superior results in fitness values, peak signal-to-noise ratio, structured similarity index, maximum absolute error, and signal-to-noise ratio.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
J. Anitha, S. Immanuel Alex Pandian, S. Akila Agnes
Summary: This paper proposes a modified whale optimization algorithm for optimizing the selection of multilevel color image thresholds. The algorithm achieves a proper balance between exploration and exploitation phases, thus avoiding the issue of local optima.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Mohamed Abdel-Basset, Reda Mohamed, Mohamed Abouhawwash
Summary: This paper proposes an Improved Whale Optimization Algorithm (IWOA) based on Kapur's entropy for multi-threshold segmentation of gray level images. It supports performance using linearly convergence increasing, local minima avoidance technique (LCMA), and ranking-based updating method (RUM). LCMA accelerates convergence speed towards the optimal solution and helps avoid local minima, while RUM replaces unbeneficial solutions with a novel updating scheme.
ARTIFICIAL INTELLIGENCE REVIEW
(2022)
Article
Computer Science, Information Systems
K. P. Baby Resma, Madhu S. Nair
Summary: A novel multilevel thresholding algorithm utilizing the meta-heuristic Krill Herd Optimization algorithm is proposed for image segmentation, reducing computational time and demonstrating superior performance through comparative analysis with other bio-inspired techniques.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2021)
Article
Computer Science, Artificial Intelligence
Dong Zhao, Lei Liu, Fanhua Yu, Ali Asghar Heidari, Mingjing Wang, Guoxi Liang, Khan Muhammad, Huiling Chen
Summary: By enhancing the selection mechanism of the ACOR method and introducing random spare strategy and chaotic intensification strategy, the convergence speed and accuracy can be significantly improved, effectively avoiding local optima. Through a series of experiments, these improved methods demonstrate superior performance in problem-solving, and compared to other techniques, RCACO has a more reliable ability to step out of local optima.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Biology
Hongliang Guo, Hanbo Liu, Ahong Zhu, Mingyang Li, Helong Yu, Yun Zhu, Xiaoxiao Chen, Yujia Xu, Lianxing Gao, Qiongying Zhang, Yangping Shentu
Summary: In this paper, a BDSMA-based image segmentation method is proposed, which improves the limitations of the original algorithm by combining SMA with DE and introducing a cooperative mixing model. The experimental results demonstrate the superiority of this method in terms of convergence speed and precision compared to other methods, and its successful application to brain tumor medical images.
COMPUTERS IN BIOLOGY AND MEDICINE
(2024)
Article
Biology
Sanjoy Chakraborty, Apu Kumar Saha, Sukanta Nama, Sudhan Debnath
Summary: The COVID-19 pandemic has had a significant impact on various aspects of human life, highlighting the importance of rapid diagnosis and treatment. This research focuses on developing a computational tool to improve diagnostic accuracy by enhancing the whale optimization method and evaluating its efficiency through population reduction.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Computer Science, Artificial Intelligence
Essam H. Houssein, Marwa M. Emam, Abdelmgeid A. Ali
Summary: The paper presents the IChOA algorithm for breast cancer segmentation using thermography images and achieves valuable and accurate results in the optimization process.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Mohamed Abdel-Basset, Reda Mohamed, Mohamed Abouhawwash
Summary: In this paper, a new image segmentation algorithm based on the improved marine predators algorithm (MPA) is proposed, incorporating a strategy to find the worst solutions and gradually improve them towards the best solutions to avoid local optima, known as linearly increased worst solutions improvement strategy (LIS), and a ranking-based updating strategy (RUS) to update solutions with potential for improvement. These strategies are integrated into a new segmentation meta-heuristic algorithm, MPALS, which is further combined with RUS to address the image segmentation problem in a variant algorithm, HMPA. Experimental results show the effectiveness of HMPA in improving segmentation accuracy with increasing threshold levels compared to state-of-the-art algorithms.
ARTIFICIAL INTELLIGENCE REVIEW
(2022)
Article
Chemistry, Analytical
Wysterlanya K. P. Barros, Leonardo A. Dias, Marcelo A. C. Fernandes
Summary: This study implements the Otsu automatic image thresholding algorithm on FPGA for real-time processing of high-resolution images. By optimizing processing time through parallelization, the proposed hardware achieved a high speedup compared to similar works.
Article
Multidisciplinary Sciences
Chuang Zhang, Yue-Han Pei, Xiao-Xue Wang, Hong-Yu Hou, Li-Hua Fu
Summary: To tackle the issues of low accuracy and slow convergence in traditional multilevel image segmentation methods, a symmetric cross-entropy multilevel thresholding image segmentation method (MSIPOA) with a multi-strategy improved pelican optimization algorithm is proposed. The algorithm enhances the initial population quality and distribution uniformity using Sine chaotic mapping, improves search diversity and convergence accuracy with a spiral search mechanism based on the sine cosine optimization algorithm, and further increases the ability to escape local minima using a levy flight strategy. Experimental results demonstrate that the MSIPOA algorithm outperforms other optimization algorithms in terms of convergence speed and accuracy, and achieves good performance in image segmentation tasks.
Article
Computer Science, Information Systems
Gong Cheng, Ruimin Li, Chunbo Lang, Junwei Han
Summary: Meta-learning is a general framework for few-shot learning, but challenges remain in making the base-learner task-specific and extracting more specific and complete information for different tasks. New modules like Task-Wise Attention (TWA) and Part Complementary Learning (PCL) have been proposed to address these challenges effectively.
SCIENCE CHINA-INFORMATION SCIENCES
(2021)
Article
Computer Science, Artificial Intelligence
Heming Jia, Chunbo Lang
Summary: SSACL algorithm, with crossover scheme and Levy flight strategy introduced, outperforms other algorithms in precision, stability, and efficiency, as demonstrated in experiments on various test functions.
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Heming Jia, Xiaoxu Peng, Chunbo Lang
Summary: The Remora Optimization Algorithm (ROA) is proposed in this paper, inspired by the parasitic behavior of remora. ROA mimics the behavior of remora by updating different hosts globally or locally, providing a new idea for memetic algorithm.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Geochemistry & Geophysics
Gong Cheng, Liming Cai, Chunbo Lang, Xiwen Yao, Jinyong Chen, Lei Guo, Junwei Han
Summary: SPNet is a lightweight and effective few-shot image classification model, utilizing prototype self-calibration and intercalibration methods to generate more accurate prototypes and predictions through optimizing three loss functions, demonstrating competitive performance compared with other advanced few-shot image classification approaches.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Computer Science, Artificial Intelligence
Chunbo Lang, Gong Cheng, Binfei Tu, Chao Li, Junwei Han
Summary: This paper proposes a fresh and powerful scheme called BAM to tackle the issue of low generalization capability in most previous works when dealing with hard query samples. The scheme combines an auxiliary branch and a meta learner to identify regions that do not need segmentation and derive accurate segmentation predictions by adaptively integrating the results of the two learners.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Chunbo Lang, Gong Cheng, Binfei Tu, Junwei Han
Summary: Few-Shot segmentation (FSS) is a challenging task that aims to identify unseen classes with only a few annotated samples. Current approaches based on prototype learning fail to fully utilize support image-mask pairs, leading to segmentation failures. To address this, we propose a flexible framework that divides the segmentation mask, generates support-induced proxies, and incorporates parallel decoding and semantic consistency regularization.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2023)
Article
Geochemistry & Geophysics
Chunbo Lang, Gong Cheng, Binfei Tu, Junwei Han
Summary: Most existing few-shot segmentation (FSS) methods are designed for natural images and rarely investigate more realistic and challenging applications like remote sensing image understanding. In this study, we propose a novel and powerful remote sensing FSS framework, R(2)Net, that utilizes dynamically updated global prototypes and decoupled registration to improve segmentation accuracy. Extensive experiments on the iSAID-5(i) benchmark dataset demonstrate the superiority of R(2)Net over state-of-the-art FSS models.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Geochemistry & Geophysics
Chunbo Lang, Junyi Wang, Gong Cheng, Binfei Tu, Junwei Han
Summary: In recent years, few-shot segmentation (FSS) has gained attention for its advantages in low-data regimes. However, most research has focused on natural image processing, neglecting the challenges of remote sensing image understanding. This article proposes a simple and easy-to-implement framework called PCNet, which addresses the problems faced in remote sensing image segmentation. Experimental results demonstrate that PCNet outperforms previous FSS approaches, achieving state-of-the-art performance.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Computer Science, Artificial Intelligence
Gong Cheng, Chunbo Lang, Junwei Han
Summary: Conventional deep CNN-based segmentation approaches are difficult to generalize to unseen categories, so few-shot segmentation is developed to handle this issue. However, existing methods often overfit base categories and produce inaccurate segmentation boundaries. In this paper, a Holistic Prototype Activation (HPA) network is proposed to alleviate these problems by introducing novel designs, such as a training-free scheme, a Prototype Activation Module (PAM), and a Cross-Referenced Decoder (CRD). Experimental results on standard few-shot segmentation benchmarks and extended tasks demonstrate the effectiveness, flexibility, and versatility of the proposed method. The code is publicly available.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Chunbo Lang, Gong Cheng, Binfei Tu, Chao Li, Junwei Han
Summary: In this paper, we propose a few-shot segmentation approach for dense prediction tasks, addressing the issue of information loss and demonstrating its effectiveness on multiple benchmarks.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Chunbo Lang, Gong Cheng, Binfei Tu, Junwei Han
Summary: This paper proposes a novel approach to address the bias issue in few-shot segmentation, where models are biased towards seen classes. By introducing an additional branch to explicitly identify the targets of base classes and integrating the results from two learners, the proposed method achieves significant performance improvements on different datasets.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2022)
Article
Geochemistry & Geophysics
Gong Cheng, Jiabao Wang, Ke Li, Xingxing Xie, Chunbo Lang, Yanqing Yao, Junwei Han
Summary: This article proposes a novel anchor-free oriented proposal generator (AOPG) to address issues in oriented object detection caused by the use of horizontal boxes. The effectiveness of AOPG is demonstrated through extensive experiments, and a new dataset, DIOR-R, is released to alleviate the problem of data insufficiency.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Mathematical & Computational Biology
Xiaoxu Peng, Heming Jia, Chunbo Lang
MATHEMATICAL BIOSCIENCES AND ENGINEERING
(2019)
Article
Computer Science, Information Systems
Xiaoli Bao, Heming Jia, Chunbo Lang
Article
Computer Science, Information Systems
Heming Jia, Jinduo Li, Wenlong Song, Xiaoxu Peng, Chunbo Lang, Yao Li