A New Approach for Chest CT Image Retrieval

Authors:
Li-Dong Wang;Zhou-Xiang Shou
Affiliations:
College of Computer Science and Technology, Zhejiang University, Hangzhou, China 310027 and Hangzhou Normal University, Hangzhou, China 310012;College of Computer Science and Technology, Zhejiang University, Hangzhou, China 310027
Venue:
AICI '09 Proceedings of the International Conference on Artificial Intelligence and Computational Intelligence
Year:
2009

Citing 7
Cited 0

Supporting similarity queries in MARS

MULTIMEDIA '97 Proceedings of the fifth ACM international conference on Multimedia
ASSERT: a physician-in-the-loop content-based retrieval system for HRCT image databases

Computer Vision and Image Understanding - Special issue on content-based access for image and video libraries
Fast color texture recognition using chromaticity moments

Pattern Recognition Letters
Modern Information Retrieval

Modern Information Retrieval
Similar-Shape Retrieval In Shape Data Management

Computer
Image retrieval based on color distribution entropy

Pattern Recognition Letters
A survey of content-based image retrieval with high-level semantics

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

A new approach for chest CT image retrieval is presented. The proposed algorithm is based on a combination of low-level visual features and high-level semantic information. According to the new algorithm, wavelet coefficients of the image are computed first using a wavelet transform as texture feature vectors. The zernike moment is then used as an effective descriptor of global shape of chest CT images in database, and the semantic information is extracted to improve the accuracy of retrieval. Finally, index vectors are constructed by the combination of texture, shape and semantic information, and the technique of relevance feedback is used in the algorithm to enhance the effectiveness of retrieval. The retrieval results obtained by application of our new method demonstrate an improvement in effectiveness compared to other kinds of retrieval techniques.