A Comparative Study of Enhanced ROI Techniques
Navneet Kaur Kang, Sanyam Anand · 2015
In medical imaging system, image compression is the important task. Economic and effective image compression techniques are needed to minimize the storage volume of medical database in hospitals while maintain the image quality. There are certain regions in an image which demands high quality where small quality reduction might alter subsequent diagnosis. A Region Of Interest (ROI) - based approach is used to separate the important medical data and the background data. This paper proposes four enhanced ROI techniques having common objective to separate the image as foreground and background to improve the compression process. The four techniques are Mixed Raster Contour layering, block-based, region growing and hybrid active contour algorithms. Various experiments performed revealed that all the techniques are efficient to separate the input image into IR and NIR.