A retrieval technique for similar shapes
SIGMOD '91 Proceedings of the 1991 ACM SIGMOD international conference on Management of data
International Journal of Computer Vision
Color matching for image retrieval
Pattern Recognition Letters
Computer Vision
FOCUS: Searching for Multi-colored Objects in a Diverse Image Database
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Schwarz Representation for Matching and Similarity Analysis
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
| Hi-index | 0.00 |
Retrieval efficiency and accuracy are two important issues in designing a content based database retrieval system. In order to retrieve efficiently, we must extract feature to build index. Recently intensive research focused on how to extract one-dimensional features and calculate the distance between them, such as color histogram, Fourier descriptor, image shape spectrum (ISS). We develop a new method to match one-dimensional feature function in multiscale space using Schwarz representation. It can obtain closed form match function and similarity measure instead of traditional optimization. Thus we can calculate the global distance when the local information of feature function is matched. In this paper, we use the center distance function of shape as the feature functions. We calculate their Schwarz representation as indices, and calculate the optimal distance as similarity measure to sort the images. Experimental results show its efficiency and accuracy.