scholarly journals Kapur's entropy for multilevel thresholding image segmentation based on moth-flame optimization

2021 ◽  
Vol 18 (6) ◽  
pp. 7110-7142
Author(s):  
Wenqi Ji ◽  
◽  
Xiaoguang He
Keyword(s):  
Image Segmentation ◽  
Critical Evaluation ◽  
Optimal Solution ◽  
Threshold Level ◽  
Multilevel Thresholding ◽  
Fitness Value ◽  
Kapur’S Entropy ◽  
Segmentation Accuracy ◽  
Overall Performance ◽  
Global Optimal

<abstract> <p>Multilevel thresholding is a reliable and efficacious method for image segmentation that has recently received widespread recognition. However, the computational complexity of the multilevel thresholding method increases as the threshold level increases, which causes the low segmentation accuracy of this method. To overcome this shortcoming, this paper presents a moth-flame optimization (MFO) established on Kapur's entropy to clarify the multilevel thresholding image segmentation. The MFO adjusts exploration and exploitation to achieve the best fitness value. To validate the overall performance, MFO is compared with other algorithms to realize the global optimal solution to maximize the target value of Kapur's entropy. Some critical evaluation indicators are used to determine the segmentation effect and optimization performance of each algorithm. The experimental results indicate that MFO has a faster convergence speed, higher calculation accuracy, better segmentation effect and better stability.</p> </abstract>

Moth-Flame Optimization Algorithm Based Multilevel Thresholding for Image Segmentation

2017 ◽  
Vol 8 (4) ◽  
pp. 58-83 ◽  
Author(s):  
Abdul Kayom Md Khairuzzaman ◽  
Saurabh Chaudhury
Keyword(s):  
Image Segmentation ◽  
Computational Complexity ◽  
Signal To Noise Ratio ◽  
Fitness Function ◽  
Multilevel Thresholding ◽  
Bacterial Foraging Optimization ◽  
Kapur’S Entropy ◽  
Moth Flame Optimization Algorithm ◽  
Popular Image ◽  
Better Than

Multilevel thresholding is a popular image segmentation technique. However, computational complexity of multilevel thresholding increases very rapidly with increasing number of thresholds. Metaheuristic algorithms are applied to reduce computational complexity of multilevel thresholding. A new method of multilevel thresholding based on Moth-Flame Optimization (MFO) algorithm is proposed in this paper. The goodness of the thresholds is evaluated using Kapur's entropy or Otsu's between class variance function. The proposed method is tested on a set of benchmark test images and the performance is compared with PSO (Particle Swarm Optimization) and BFO (Bacterial Foraging Optimization) based methods. The results are analyzed objectively using the fitness function and the Peak Signal to Noise Ratio (PSNR) values. It is found that MFO based multilevel thresholding method performs better than the PSO and BFO based methods.

Moth-Flame Optimization Algorithm Based Multilevel Thresholding for Image Segmentation

2018 ◽  
pp. 771-797
Author(s):  
Abdul Kayom Md Khairuzzaman ◽  
Saurabh Chaudhury
Keyword(s):  
Image Segmentation ◽  
Computational Complexity ◽  
Signal To Noise Ratio ◽  
Fitness Function ◽  
Multilevel Thresholding ◽  
Bacterial Foraging Optimization ◽  
Swarm Optimization ◽  
Kapur’S Entropy ◽  
Moth Flame Optimization Algorithm ◽  
Popular Image

Multilevel thresholding is a popular image segmentation technique. However, computational complexity of multilevel thresholding increases very rapidly with increasing number of thresholds. Metaheuristic algorithms are applied to reduce computational complexity of multilevel thresholding. A new method of multilevel thresholding based on Moth-Flame Optimization (MFO) algorithm is proposed in this paper. The goodness of the thresholds is evaluated using Kapur's entropy or Otsu's between class variance function. The proposed method is tested on a set of benchmark test images and the performance is compared with PSO (Particle Swarm Optimization) and BFO (Bacterial Foraging Optimization) based methods. The results are analyzed objectively using the fitness function and the Peak Signal to Noise Ratio (PSNR) values. It is found that MFO based multilevel thresholding method performs better than the PSO and BFO based methods.

Multilevel Thresholding for Image Segmentation Based on Cellular Metaheuristics

2018 ◽  
Vol 9 (4) ◽  
pp. 1-32 ◽  
Author(s):  
Mohamed Abdou Bouteldja ◽  
Mohamed Baadeche ◽  
Mohamed Batouche
Keyword(s):  
Genetic Algorithm ◽  
Image Segmentation ◽  
Multilevel Thresholding ◽  
Objective Functions ◽  
Swarm Optimization ◽  
Cellular Genetic Algorithm ◽  
Kapur’S Entropy ◽  
Computationally Expensive ◽  
Segmentation Problem ◽  
Nature Inspired Metaheuristics

This article describes how multilevel thresholding image segmentation is a process used to partition an image into well separated regions. It has various applications such as object recognition, edge detection, and particle counting, etc. However, it is computationally expensive and time consuming. To alleviate these limitations, nature inspired metaheuristics are widely used to reduce the computational complexity of such problem. In this article, three cellular metaheuristics namely cellular genetic algorithm (CGA), cellular particle swarm optimization (CPSO) and cellular differential evolution (CDE) are adapted to solve the multilevel thresholding image segmentation problem. Experiments are conducted on different test images to assess the performance of the cellular algorithms in terms of efficiency, quality and stability based on the between-class variance and Kapur's entropy as objective functions. The experimental results have shown that the proposed cellular algorithms compete with and even outperform existing methods for multilevel thresholding image segmentation.

Fuzzy Clustering Segmentation Algorithm Research on Sports Image

2013 ◽  
Vol 339 ◽  
pp. 297-300 ◽  
Author(s):  
Xue Jiao Dong ◽  
Xiao Yan Zhang
Keyword(s):  
Image Segmentation ◽  
Clustering Algorithm ◽  
Optimal Solution ◽  
Practical Method ◽  
Global Optimal Solution ◽  
Fcm Algorithm ◽  
Fast Convergence Rate ◽  
Fuzzy C Means Clustering ◽  
Global Optimal ◽  
Theory Research

In this paper, linking with the basic principle of FCM (Fuzzy c-means clustering) algorithm, on the basis of theory research, a method of the cluster analysis of FCM is proposed. Firstly, the approximate optimal solution obtained by the improved FCM algorithm is taken as the original value of the FCM algorithm, then carrying on the local search to obtain the global optimal solution, the final segmentation result is achieved at last. The experiment results prove that in the view of the flame image segmentation, this method shows the good clustering performance and fast convergence rate, and has the widespread serviceability, so it is the practical method in image segmentation.

Fuzzy C-Means Image Segmentation Algorithm Based on Chaotic Simulated Annealing

2014 ◽  
Vol 624 ◽  
pp. 536-539 ◽  
Author(s):  
Qing Yang ◽  
Zhi Qiang Wang ◽  
Yan Xu
Keyword(s):  
Image Segmentation ◽  
Simulated Annealing ◽  
Optimal Solution ◽  
Optimization Method ◽  
Segmentation Algorithm ◽  
Global Optimization Method ◽  
Fuzzy C Means ◽  
Global Optimal ◽  
Chaotic Simulated Annealing ◽  
Image Segmentation Algorithm

Considering the problem that the traditional fuzzy c-means (FCM) image segmentation algorithm is often caught in a specific range in local search and fails to get the globally optimal solution, this paper proposed a modified FCM algorithm based on chaotic simulated annealing (CSA). It traverse all the states without repetition within a certain range to calculate the optimal solution. Experimental results show that our method converges more quickly and accurately to the global optimal and proves a promise global optimization method of high adaptability and feasibility.

EVALD – a Pioneer Application for Automated Essay Scoring in Czech

2019 ◽  
Vol 113 (1) ◽  
pp. 9-30
Author(s):  
Kateřina Rysová ◽  
Magdaléna Rysová ◽  
Michal Novák ◽  
Jiří Mírovský ◽  
Eva Hajičová
Keyword(s):  
Czech Republic ◽  
Native Speakers ◽  
Threshold Level ◽  
Automated Essay Scoring ◽  
The Czech Republic ◽  
Linguistic Differences ◽  
Supervised Training ◽  
Language Data ◽  
Overall Performance ◽  
Essay Scoring

Abstract In the paper, we present EVALD applications (Evaluator of Discourse) for automated essay scoring. EVALD is the first tool of this type for Czech. It evaluates texts written by both native and non-native speakers of Czech. We describe first the history and the present in the automatic essay scoring, which is illustrated by examples of systems for other languages, mainly for English. Then we focus on the methodology of creating the EVALD applications and describe datasets used for testing as well as supervised training that EVALD builds on. Furthermore, we analyze in detail a sample of newly acquired language data – texts written by non-native speakers reaching the threshold level of the Czech language acquisition required e.g. for the permanent residence in the Czech Republic – and we focus on linguistic differences between the available text levels. We present the feature set used by EVALD and – based on the analysis – we extend it with new spelling features. Finally, we evaluate the overall performance of various variants of EVALD and provide the analysis of collected results.

AO-BBO: A Novel Optimization Algorithm and Its Application in Plant Drug Extraction

2019 ◽  
Vol 19 (2) ◽  
pp. 139-145 ◽  
Author(s):  
Bote Lv ◽  
Juan Chen ◽  
Boyan Liu ◽  
Cuiying Dong
Keyword(s):  
Optimization Algorithm ◽  
Learning Strategy ◽  
Optimal Solution ◽  
Population Diversity ◽  
Global Optimal Solution ◽  
Plant Medicine ◽  
Suitability Index ◽  
Sensing Model ◽  
Local Optimal Solution ◽  
Global Optimal

<P>Introduction: It is well-known that the biogeography-based optimization (BBO) algorithm lacks searching power in some circumstances. </P><P> Material & Methods: In order to address this issue, an adaptive opposition-based biogeography-based optimization algorithm (AO-BBO) is proposed. Based on the BBO algorithm and opposite learning strategy, this algorithm chooses different opposite learning probabilities for each individual according to the habitat suitability index (HSI), so as to avoid elite individuals from returning to local optimal solution. Meanwhile, the proposed method is tested in 9 benchmark functions respectively. </P><P> Result: The results show that the improved AO-BBO algorithm can improve the population diversity better and enhance the search ability of the global optimal solution. The global exploration capability, convergence rate and convergence accuracy have been significantly improved. Eventually, the algorithm is applied to the parameter optimization of soft-sensing model in plant medicine extraction rate. Conclusion: The simulation results show that the model obtained by this method has higher prediction accuracy and generalization ability.</P>

Sign in / Sign up

Export Citation Format

Share Document