On ACO-Based Fuzzy Clustering for Image Segmentation

Yu, Zhiding; Yu, Weiyu; Zou, Ruobing; Yu, Simin

doi:10.1007/978-3-642-01510-6_81

Cited by 13 publications

(14 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Image segmentation plays an important task in image analysisandconsidering as one of the difficult and challenging problems in image processing technology [9]. Region growing is a modest region-based image segmentation techniques.…”

Section: Region Growingmentioning

confidence: 99%

Building Segmentation of Satellite Image based on Area and Perimeter using Region Growing

Yohannes

Utaminingrum

2016

IJEECS

View full text Add to dashboard Cite

show abstract

Section: Region Growingmentioning

confidence: 99%

Building Segmentation of Satellite Image based on Area and Perimeter using Region Growing

Yohannes

Utaminingrum

2016

IJEECS

View full text Add to dashboard Cite

show abstract

“…. Yu, Lee, Jeon (2014) reported that image segmentation has a wide range of applications such as image content analysis, object recognition and computer-assisted medical diagnosis.…”

Section: Introductionmentioning

confidence: 99%

Development of an Enhanced Fuzzy C-Means algorithm for Medical Image Segmentation using Ant Colony Optimization

Ajala¹

2018

Proceedings of the International Conference on Applied Research in Engineering, Science and Technology

View full text Add to dashboard Cite

Modified Fuzzy C-Means (MFCM) algorithm, which is a combination of fuzzy c means and k means, for medical image segmentation, suffers from high computational time and noise which lead to high memory consumption and low accuracy. Therefore, this paper presents an Enhanced MFCM algorithm (ACOMFCM), which has better accuracy and low memory consumption for medical image segmentation. Thirty medical images used in this work were pre-processed using Gaussian filtering method. ACOMFCM algorithm was developed using Ant Colony Optimization techniques to minimise the Euclidean distance between the data point and centre coordinate in the K-means algorithm characterizing the existing MFCM. Segmentation of the thirty images were carried out using the MFCM and ACOMFCM algorithms in Matrix Laboratory 7.1 (R0011a) environment. Performance of the MFCM and the ACOMFCM was evaluated using segmentation accuracy, segmentation time and memory consumption. The average result of MFCM algorithm for thirty images yielded segmentation accuracy, segmentation time and memory consumption of 7117992.29, 22.484s and 494161920bit, respectively while average result of the ACOMFCM algorithm for thirty images used yielded segmentation accuracy, segmentation time and memory consumption of 10590135.79, 6.649s and 502960128 bit, respectively.

show abstract

“…The aim of clustering analysis is to group objects so that those within a cluster are much more similar than those in different clusters. Clustering has been studied extensively in the statistics, data-mining and database communities, and numerous algorithms have been proposed (Schwenkera and Trentin, 2014;Sabit et al, 2011;Yu et al, 2012;Fukunaga, 2013;Cover and Hart, 1967;Derrac et al, 2012;Santos et al, 2013). It has been widely used for data analysis in many fields, including anthropology, biology, economics, marketing, and medicine.…”

Section: Introduction and Problem Statementmentioning

confidence: 99%

Holo-Entropy Based Categorical Data Hierarchical Clustering

Chen¹,

Qin²,

Wang³

2017

Informatica

View full text Add to dashboard Cite

Clustering high-dimensional data is a challenging task in data mining, and clustering high-dimensional categorical data is even more challenging because it is more difficult to measure the similarity between categorical objects. Most algorithms assume feature independence when computing similarity between data objects, or make use of computationally demanding techniques such as PCA for numerical data. Hierarchical clustering algorithms are often based on similarity measures computed on a common feature space, which is not effective when clustering highdimensional data. Subspace clustering algorithms discover feature subspaces for clusters, but are mostly partition-based; i.e. they do not produce a hierarchical structure of clusters. In this paper, we propose a hierarchical algorithm for clustering high-dimensional categorical data, based on a recently proposed information-theoretical concept named holo-entropy. The algorithm proposes new ways of exploring entropy, holo-entropy and attribute weighting in order to determine the feature subspace of a cluster and to merge clusters even though their feature subspaces differ. The algorithm is tested on UCI datasets, and compared with several state-of-the-art algorithms. Experimental results show that the proposed algorithm yields higher efficiency and accuracy than the competing algorithms and allows higher reproducibility.

show abstract

On ACO-Based Fuzzy Clustering for Image Segmentation

Cited by 13 publications

References 6 publications

Building Segmentation of Satellite Image based on Area and Perimeter using Region Growing

Building Segmentation of Satellite Image based on Area and Perimeter using Region Growing

Development of an Enhanced Fuzzy C-Means algorithm for Medical Image Segmentation using Ant Colony Optimization

Holo-Entropy Based Categorical Data Hierarchical Clustering

Contact Info

Product

Resources

About