Combining Color and Shape Features for Image Retrieval

Authors:
Xiaofu Lee;Qian Yin
Affiliations:
Image Processing and Pattern Recognition Laboratory, Beijing Normal University, Beijing, China 100875;Image Processing and Pattern Recognition Laboratory, Beijing Normal University, Beijing, China 100875
Venue:
UAHCI '09 Proceedings of the 5th International Conference on Universal Access in Human-Computer Interaction. Part III: Applications and Services
Year:
2009

Citing 10
Cited 1

Color indexing

International Journal of Computer Vision
Video parsing, retrieval and browsing: an integrated and content-based solution

Proceedings of the third ACM international conference on Multimedia
Comparing images using color coherence vectors

MULTIMEDIA '96 Proceedings of the fourth ACM international conference on Multimedia
Pairwise classification and support vector machines

Advances in kernel methods
Color image processing and applications

Color image processing and applications
Content-Based Image Retrieval Systems

Computer
Similar-Shape Retrieval In Shape Data Management

Computer
Image Retrieval Evaluation

CBAIVL '98 Proceedings of the IEEE Workshop on Content - Based Access of Image and Video Libraries
A survey of content-based image retrieval with high-level semantics

Pattern Recognition
Region-Based image retrieval with perceptual colors

PCM'04 Proceedings of the 5th Pacific Rim Conference on Advances in Multimedia Information Processing - Volume Part II

Research of image retrieval algorithms based on color

AICI'11 Proceedings of the Third international conference on Artificial intelligence and computational intelligence - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a method for extracting and combining features from image that can be used to perform effective image retrieval. First, we use a method of diamond segmentation for all images in database. Then, in HSV color space, we extract color vectors of 256 dimensions for both the segments in and out the diamond. At last, we extract shape feature from all images with the method of moment invariants. Then we compare our method with single color feature and shape feature, as well as two contrast combining methods. Experiments show that our method has better effectiveness and feasibility.