Share Email Print

Proceedings Paper

Image segmentation by an encoder-segmented neural network
Author(s): Ning Li; Youfu Li
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Most of region-based image segmentation approaches suffered from the problem of different thresholds selecting for different images. In this paper, an new adaptive image segmentation approach based on an encoder-segmented neural network (ESNN) is presented. The novel ESNN combines the advantages of self-organizing feature map (SOFM) and fuzzy c- means clustering (FCM) algorithm. Feature encoder implemented by SOFM for vector quantization using the competitive learning where the feature vectors can be encoded as the definite sequence by which the most of the available feature vectors can be extracted for the final segmentation using encoded feature-based fuzzy c-means (EFFCM) algorithm. Since the contribution of feature encoder, ESNN can reduce the complexion of computation when processing a large number of multi-spectral images. ESNN have been applied for brain MRI segmentation. Comparing with FCM algorithm, experimental results have shown ESNN method for segmentation makes better performance on computation and adaptability.

Paper Details

Date Published: 31 July 1998
PDF: 12 pages
Proc. SPIE 3384, Photonic Processing Technology and Applications II, (31 July 1998); doi: 10.1117/12.317659
Show Author Affiliations
Ning Li, City Univ. of Hong Kong (China)
Youfu Li, City Univ. of Hong Kong (Hong Kong)

Published in SPIE Proceedings Vol. 3384:
Photonic Processing Technology and Applications II
Andrew R. Pirich; Michael A. Parker, Editor(s)

© SPIE. Terms of Use
Back to Top