Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
K-region-based Clustering Algorithm for Image Segmentation
Abstract In this paper, authors have proposed K-region-based clustering algorithm which is based on performing the clustering techniques in K number of regions of given image of size N × N. The K and N are power of 2 and K < N. The authors have divided the given image into 4 regions, 16 regions, 64 regions, 256 regions, 1024 regions, 4096 regions and 16384 regions based on the value of K. Authors have grouped the adjacent pixels of similar intensity value into same cluster in each region. The clusters of similar values in each adjacent region are grouped together to form the bigger clusters. The authors have obtained the different segmented images based on the K number of regions. These segmented images are useful for image understanding. The authors have been taken four parameters: Probabilistic rand index, variation of information, global consistency error and boundary displacement error. These parameters have used to evaluate and analyze the performance of the K-region-based clustering algorithm.
K-region-based Clustering Algorithm for Image Segmentation
Abstract In this paper, authors have proposed K-region-based clustering algorithm which is based on performing the clustering techniques in K number of regions of given image of size N × N. The K and N are power of 2 and K < N. The authors have divided the given image into 4 regions, 16 regions, 64 regions, 256 regions, 1024 regions, 4096 regions and 16384 regions based on the value of K. Authors have grouped the adjacent pixels of similar intensity value into same cluster in each region. The clusters of similar values in each adjacent region are grouped together to form the bigger clusters. The authors have obtained the different segmented images based on the K number of regions. These segmented images are useful for image understanding. The authors have been taken four parameters: Probabilistic rand index, variation of information, global consistency error and boundary displacement error. These parameters have used to evaluate and analyze the performance of the K-region-based clustering algorithm.
K-region-based Clustering Algorithm for Image Segmentation
Kumar, R. (Autor:in) / Arthanariee, A. M. (Autor:in)
Journal of The Institution of Engineers (India): Series B ; 94 ; 221-229
01.12.2013
9 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
A Region-Based Image Fusion Algorithm Using Multiresolution Segmentation
| British Library Conference Proceedings | 2003
| Trans Tech Publications | 2014
Spectral Clustering Ensemble Applied to SAR Image Segmentation
| Online Contents | 2008