• Dr. Ch. Raja

The primary goal of Content Based Medical Image Retrieval (CBMIR) is not to burden a physician and to accomplish the same action by a computer. This helps the doctor and radiologist in understanding and analysing the case and leads to automatic medical image annotation. The choice of image attributes have crucial role in retrieving similar X-Ray images of various anatomic regions. In this paper we presented an empirical analysis of an X-Ray image retrieval system with spatial (intensity, statistical) and frequency domain (DFT, DWT) and Eigen value (SVD) attributes were computed for five different regular and irregular zones of the image. In our previous work we proved that analysing the image with local attributes result in better retrieval efficiency and hence in this paper we computed the attributes by dividing the image into 64 regular and irregular zones. For this experimentation IRMA 2008 and IRMA 2009 X-Ray data sets were used. With this work we come up with wonderful conclusions by stating that wavelet based textural attributes, intensity features and Eigen values extracted from different regular zones that worked well in excellent retrieval of different anatomy X-Ray images.

Medical Image Retrieval, Region based retrieval, Regular zoning, Irregular zoning, intensity attributes, statistical attributes, DFT, DWT, SVD.

"Optimal Feature Selection for Zone Based Medical Image Retrieval ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 2, page no.1103-1110, February 2018, Available :http://www.jetir.org/papers/JETIR1802235.pdf

"Optimal Feature Selection for Zone Based Medical Image Retrieval ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 2, page no. pp1103-1110, February 2018, Available at : http://www.jetir.org/papers/JETIR1802235.pdf