Application of color change feature in gastroscopic image retrieval

Authors:
Chengyu Wu;Xiaoying Tai
Affiliations:
Ningbo Institute of Technology, Zhejiang University, Zhejiang, China and Zhejiang Provincial Key Laboratory of Information Network Technology, China;Zhejiang Provincial Key Laboratory of Information Network Technology, China and Institute of Information Science and Engineering, Ningbo University, Zhejiang, China
Venue:
FSKD'09 Proceedings of the 6th international conference on Fuzzy systems and knowledge discovery - Volume 3
Year:
2009

Citing 5
Cited 0

Temporal Color Correlograms for Video Retrieval

ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 1 - Volume 1
A study of methods for normalizing user ratings in collaborative filtering

Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval
Image Retrieval Based on Color and Texture

FSKD '07 Proceedings of the Fourth International Conference on Fuzzy Systems and Knowledge Discovery - Volume 02
Color image segmentation using morphological clustering and fusion with automatic scale selection

Pattern Recognition Letters
Kullback-Leibler approximation of spectral density functions

IEEE Transactions on Information Theory

Quantified Score

Hi-index	0.02

Visualization

Abstract

Content-based medical image retrieval is getting more and more importance in aspect of clinical assistant diagnose. In this paper a new method based on the characters of color change is proposed. First a color clustering technique is used for image segmentation in CIE L*a*b* color space. And then color change feature is extracted from the binary edge image. Kullback-Leibler distance is used to calculate the dissimilarity. Meanwhile, a method combining both color change feature and dominant color information is proposed to carry out integrate retrieval. Finally, a system for gastroscopic image retrieval is developed which is available to support clinical decision making. Some contrast experiments are designed in the retrieval accuracies, the rank and the execution time. The comparison of the experimental results shows that the approach proposed in this paper is effective.