Detection of Lung Tumor in MR Images using Modified Pillar K-Means Algorithm with Gabor Filter and Color Mapping

This paper presents an approach to image segmentation using Modified Pillar K-Means algorithm. This segmentation method includes a new mechanism for distance metric and grouping the elements of high resolution images in order to improve accuracy. The system uses modified Pillar K-means algorithm for optimized image segmentation. The Pillar algorithm considers the placement of pillars that should be located as far from each other to resist the pressure distribution of a roof 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. This algorithm distributes all initial centroids according to the Accumulated Distance Metric (ADM)& the distance is calculated by Chessboard distance measure. This paper evaluates the proposed approach for image segmentation with Gabor filter, Modified Pillar K-Means clustering algorithm and Marker controlled Watershed Transform with different samples of MR Images for Accuracy, Precision, Sensitivity Factor, Specificity Factor F-Factor& Success rate. Experimental results clarify the effectiveness of our approach to improve the segmentation quality.