Scale-Based Description and Recognition of Planar Curves and Two-Dimensional Shapes
IEEE Transactions on Pattern Analysis and Machine Intelligence
International Journal of Computer Vision
Handbook of pattern recognition & computer vision
Image Indexing Using Color Correlograms
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Histogram refinement for content-based image retrieval
WACV '96 Proceedings of the 3rd IEEE Workshop on Applications of Computer Vision (WACV '96)
Image indexing using moments and wavelets
IEEE Transactions on Consumer Electronics
Hi-index | 0.00 |
There are various kinds' methods to method that image retrieval based on shape feature. In this paper, an efficient content-based image information retrieval method which utilizes shape information and color information is proposed. CSS(Curvature Scale Space) space is used to extract shape information. HSI(Hue Saturation Intensity) space is used to extract color information. This method expresses contours of the object which is binarized through pre-processes in CSS space, then extract shape features of the object in this space. CSS space is a space that expresses curvatures of contours in multiple resolutions, which offers shape features invariant to shift, scale, and skew of the object. HSI color space offers hue and saturation information which is less affected by change of brightness of image. This method gets histogram of the object's color, and then applies histogram intersection degree to the matching metric in searching process. Show result that image object retrieval being based on process and this that draw CSS information from reflex because an experiment uses ICSS method, and estimate performance by comparing old method and method that propose. The results of experiments show that the proposed method is better in accuracy of searching than existing methods.