Abstract: Image segmentation plays a vital role in medical imaging applications. Image processing techniques provide a good tool for improving the manual screening of CT samples of lung. Developing a robust and efficient algorithm for medical image segmentation has been a demanding area of growing research of interest during the last two decades. This research reports on Estimation of objects by segmenting Computer Tomography (CT) lung images using supervised contextual clustering method. Matlab Software regionprops function has been used as one of the criteria to show the performance of Contextual Clustering (CC). The CC segmentation shows more segmented objects with least discontinuity within the objects in the CT lung image. The segmented results are compared with the conventional algorithms such as Sobel, Prewitt, Roberts, Log and Zero crossing. The results obtained from the experiments show that the proposed approach is found to be efficient and robust against segmentation faults when compared to the existing methods.
Z. Faizal Khan and V. Kavitha, 2012. Estimation of Objects in Computer Tomography Lung Images Using Supervised Contextual Clustering. Research Journal of Applied Sciences, 7: 494-499.