A new image segmentation method via fusing NCut eigenvectors maps

摘要

This paper presents a new image segmentation method via fusing Normalized Cut (NCut) eigenvector maps. In thismethod, we fuse the eigenvector maps by maximizing the salient contour signals and suppress the non-maximum ones.Then, we use OWT-UCM method to produce the image segmentation from the soft contour map generated from thefused eigenvector maps and local contour cues. We evaluate our segmentation method based on BSDS500 database.Experimental results show that the proposed segmentation method is more accurate and preserve large meaningful region.© (2012) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.