Description: This paper presents a new approach to image segmentation using Pillar K-means algorithm. This
segmentation method includes a new mechanism for grouping the elements of high resolution images in order to
improve accuracy and reduce the computation time. The system uses K-means for image segmentation optimized by
the algorithm after Pillar. The Pillar algorithm considers the placement of pillars should be located as far from each
other to resist the pressure distribution of a roof, as same as the number of centroids between the data distribution. This
algorithm is able to optimize the K-means clustering for image segmentation in the aspects of accuracy and
computation time. This algorithm distributes all initial centroids according to the maximum cumulative distance metric.
This paper evaluates the proposed approach for image segmentation by comparing with K-means clustering
algorithm and Gaussian mixture model and the participation of RGB, HSV, HSL and CIELAB color spaces.
To Search:
File list (Check if you may need any files):
images\abnormal\chronic infarct with gliosis and cystic formation.jpg
......\........\chronic infarct.0001.jpg
......\........\cystic necrosis of tumor.0001.jpg
......\........\dilated lateral ventricels in normal pressure hydrocephalous.0001 - Copy.jpg
......\........\metastases.0017.jpg
......\normal\normal t2w brain 2nd patient.0006.jpg
......\......\normal t2w brain 2nd patient.0003.jpg
......\......\normal t2w brain 2nd patient.0004.jpg
......\......\normal t2w brain 2nd patient.0005.jpg
Extract_Feature.m
feature_extract_nnt_training.m
gui1.fig
gui1.m
net.mat
images\abnormal
......\normal
images