期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2014
卷号：68
期号：3
出版社：Journal of Theoretical and Applied
摘要：Segmentation is an important step for finding out the different portions of an image. Existing segmentation algorithms have involved many stages like elimination of blood vessels, tissues and finally showing the nodule in the segmented image. This paper proposes new segmentation technique using recurrent Echo State Neural Network (ESNN) method on computer tomography (CT) lung image. ESNN has been chosen in this work since it reduces the number of steps in segmentation to identify the presence of nodules in the CT lung image. The performance of ESNN segmentation has been shown to be the best when compared with other conventional segmentation algorithms like �Sobel�, �Prewitt�, �Robertz�, �Log�, �Zerocross�, �Canny� and Contextual clustering. Matlab regionprops function has been used as one of the criteria to show the performance of segmentation algorithms. From this research work, it has been observed that the segmentation accuracy of the proposed algorithm has been achieved to 84.40%.
