Analysis of Ultra Sound Kidney Image Features for Image Retrieval by Gray Level Co-Occurrence Matrices

Abstract

Abstract-Medical imaging is though expensive because of capital costs, is easy to perform because of its noninvasive nature. In order to provide better analysis and diagnosis, various features have been extracted from any images. In this paper many important features of the ultra sound kidney images have been extracted and analysis has been made for the proposed image retrieval from the image database. Quantitative establishment of use the features for detection of abnormalities in Ultra sound kidney images have been made. Here, we made an analysis that the texture has been used to discriminate among the various types of tissue in image applications. Various important features namely contrast, homogeneity, correlation, energy, autocorrelation, variance, co-variance, inertia, promenance, shade, dissimilarity, inverse difference moment (IDM), maximum probability and entropy have been extracted and analyzed for the application in connection of a image database for the image retrieval process.Index Terms-Extraction, features, statistical test image retrieval, ultra sound kidney image.I.