Share Email Print

Proceedings Paper

Multiple object image segmentation algorithm based on wavelet theory
Author(s): W. Wang; Z. Wang
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

The colony characteristics are used for evaluating the quality of water and food. Auto-detecting colony in an image is a hard task. This paper proposes a new multi-scale segmentation technique based on wavelet decompositions and watersheds. Firstly, we dispose the tiny colonies by using a wavelet domain median filter. Secondly, wavelet transform is used to create multi-resolution images. Then watershed segmentation algorithm is applied to segment the lowestresolution image and obtain the initial watershed segmentation result. Finally, we do segmentation on the high-resolution image based on the low-resolution image. Experiments results show that the colony images can be well segmented by using the new algorithm.

Paper Details

Date Published: 17 June 2009
PDF: 9 pages
Proc. SPIE 7389, Optical Measurement Systems for Industrial Inspection VI, 73892R (17 June 2009); doi: 10.1117/12.827433
Show Author Affiliations
W. Wang, Hubei Univ. of Technology (China)
Z. Wang, Huawei Co. (China)

Published in SPIE Proceedings Vol. 7389:
Optical Measurement Systems for Industrial Inspection VI
Peter H. Lehmann, Editor(s)

© SPIE. Terms of Use
Back to Top