A new image segmentation method via fusing NCut eigenvectors maps

Tiejun Zhang; Ahmed A. Abd El-Latif; Ning Wang; Qiong Li; Xiamu Niu

doi:10.1117/12.956472

1 June 2012 A new image segmentation method via fusing NCut eigenvectors maps

Tiejun Zhang, Ahmed A. Abd El-Latif, Ning Wang, Qiong Li, Xiamu Niu

Proceedings Volume 8334, Fourth International Conference on Digital Image Processing (ICDIP 2012); 833430 (2012) https://doi.org/10.1117/12.956472
Event: Fourth International Conference on Digital Image Processing (ICDIP 2012), 2012, Kuala Lumpur, Malaysia

Abstract

This paper presents a new image segmentation method via fusing Normalized Cut (NCut) eigenvector maps. In this method, 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 the fused 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.

Citation Download Citation

Tiejun Zhang, Ahmed A. Abd El-Latif, Ning Wang, Qiong Li, and Xiamu Niu "A new image segmentation method via fusing NCut eigenvectors maps", Proc. SPIE 8334, Fourth International Conference on Digital Image Processing (ICDIP 2012), 833430 (1 June 2012); https://doi.org/10.1117/12.956472

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available