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：2017
卷号：95
期号：22
页码：6042
出版社：Journal of Theoretical and Applied
摘要：Otsu s Method is a non parametric approach for image segmentation and is an attractive alternative to Bayes decision rule. Use of Nelder Mead for Otsus optimization has been used since long but cannot be seen in image segmentation literature. We in this paper address this gap in a novel way and revive classical literature of Otsu�s Image segmentation by experimenting it for voxel based tissue classification which then follows volume measurement of MRI base subjects. The other methods used to meet objective includes: spatial filtering, skull stripping and binarization of brain MR slices. The �goodness� of thresholds lies between 0.90<η^*<0.99 for every brain MR slice in the volume. Significant difference was found (p<0.01) and (F >>1) amongst mean gray level of tissues, mean tissue volume densities within slices of each subject and in average volume tissue density of all Ten subjects.
