A New Method for Initialising the K-Means Clustering Algorithm

Xiao-ping, Qin; Zheng, Shijue

doi:10.1109/kam.2009.20

Cited by 10 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unfortunately, Kmeans algorithm is extremely sensitive to the initial choice of cluster centers, and a poor choice of centers may lead to a local optimum that is quite inferior to the global optimum. [8,9].…”

Section: Clustering Analysismentioning

confidence: 99%

Applying New Method for Computing Initial Centers of k-Means Clustering with Color Image Segmentation

2019

University of Thi-Qar Journal of Science

View full text Add to dashboard Cite

Image segmentation is the first step of the most critical tasks of image analysis, as shown in Figure (1). It is used either to distinguish objects from their background or to partition an image onto the related regions. There are different techniques that would help solve the image segmentation problem.Jeon el al. [1] in his review of the previous related studies, categorized these techniques into the following: thresholding approaches, contour based approaches, region based approaches, clustering based approaches and other optimization based approaches using a Bayesian framework and neural networks. The clustering approaches can be categorized into two general groups: partitional and hierarchical clustering algorithms.

show abstract

Section: Clustering Analysismentioning

confidence: 99%

Applying New Method for Computing Initial Centers of k-Means Clustering with Color Image Segmentation

2019

University of Thi-Qar Journal of Science

View full text Add to dashboard Cite

show abstract

“…Many papers proposed new ideas for initializing the centroids in K-means to make good results [4] [11].…”

Section: Related Workmentioning

confidence: 99%

Avoiding Objects with few Neighbors in the KMeans Process and Adding ROCK Links to Its Distance

Alnabriss¹,

Ashour²

2011

IJCA

View full text Add to dashboard Cite

K-means is considered as one of the most common and powerful algorithms in data clustering, in this paper we're going to present new techniques to solve two problems in the K-means traditional clustering algorithm, the 1 st problem is its sensitivity for outliers, in this part we are going to depend on a function that will help us to decide if this object is an outlier or not, if it was an outlier it will be expelled from our calculations, that will help the K-means to make good results even if we added more outlier points; in the second part we are going to make K-means depend on Rock links in addition to its traditional distance, Rock links takes into account the number of common neighbors between two objects, that will make the K-means able to detect shapes that can't be detected by the traditional K-means.

show abstract

“…The conventional K-means algorithm is sensitive to the selection of the initial cluster centroids, which will make the algorithm 1 converge to the local optima [1] . Fuzzy C-Means (FCM) algorithm is only fit in special shape and size for image clustering, and also in c-means algorithms there is the danger to come into local minima [2] .…”

Section: Introductionmentioning

confidence: 99%

Phishing web image segmentation based on improving spectral clustering

Zhao

Jiao

2011

J. Electron.(China)

View full text Add to dashboard Cite

This paper proposes a novel phishing web image segmentation algorithm which based on improving spectral clustering. Firstly, we construct a set of points which are composed of spatial location pixels and gray levels from a given image. Secondly, the data is clustered in spectral space of the similar matrix of the set points, in order to avoid the drawbacks of K-means algorithm in the conventional spectral clustering method that is sensitive to initial clustering centroids and convergence to local optimal solution, we introduce the clone operator, Cauthy mutation to enlarge the scale of clustering centers, quantum-inspired evolutionary algorithm to find the global optimal clustering centroids. Compared with phishing web image segmentation based on K-means, experimental results show that the segmentation performance of our method gains much improvement. Moreover, our method can convergence to global optimal solution and is better in accuracy of phishing web segmentation.

show abstract

A New Method for Initialising the K-Means Clustering Algorithm

Cited by 10 publications

References 8 publications

Applying New Method for Computing Initial Centers of k-Means Clustering with Color Image Segmentation

Applying New Method for Computing Initial Centers of k-Means Clustering with Color Image Segmentation

Avoiding Objects with few Neighbors in the KMeans Process and Adding ROCK Links to Its Distance

Phishing web image segmentation based on improving spectral clustering

Contact Info

Product

Resources

About