Soft Image Segmentation by Weighted Linked Pyramid

This paper describes the use of weighted linked pyramid algorithms to achieve soft segmentation of images. A fundamental problem of region segmentation is that for many images no unique, correct region boundaries can be determined. In this situation the normal desire for a definitive crisp segmentation may be unreasonable. It is proposed that soft segmentation is a more natural way to segment digital image data than crisp segmentation. A method of deriving a soft segmentation from a weighted linked pyramid is shown. We introduce methods for comparing a soft segmentation with a crisp one and show that in some ways the soft segmentation is better. 1 Introduction One of the fundamental problems of region segmentation is that for many images no unique, correct placement of region boundaries can be determined. It is common in digital images to have pixels along a region boundary that are intermediate in value between the regions. This is increased with any blurring. Thus there are many pix..