A Study of Shape-Based Image Retrieval

Authors:
Hwei-Jen Lin;Yang-Ta Kao;Shwu-Huey Yen;Chia-Jen Wang
Affiliations:
-;-;-;-
Venue:
ICDCSW '04 Proceedings of the 24th International Conference on Distributed Computing Systems Workshops - W7: EC (ICDCSW'04) - Volume 7
Year:
2004

Citing 2
Cited 4

Nearest neighbor queries

SIGMOD '95 Proceedings of the 1995 ACM SIGMOD international conference on Management of data
Extensive partition operators, gray-level connected operators, and region merging/classification segmentation algorithms: theoretical links

IEEE Transactions on Image Processing

Classify By Representative Or Associations (CBROA): a hybrid approach for image classification

MDM '05 Proceedings of the 6th international workshop on Multimedia data mining: mining integrated media and complex data
Utilizing venation features for efficient leaf image retrieval

Journal of Systems and Software
Decomposition of two-dimensional shapes for efficient retrieval

Image and Vision Computing
Hierarchical Salient Point Selection for image retrieval

Pattern Recognition Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

Content-based image retrieval (CBIR) workincludes feature selection, object representation, andmatching. If a shape is used as feature, edge detectionmight be the first step to extract that feature.Invariance to translation, rotation, and scale isrequired by a good shape representation. Sustainingdeformation contour matching is an important issue atthe matching process.In this paper, an efficient and robust shape-basedimage retrieval system is proposed. We use the Promptedge detection method [18] to detect edge points,which is compared with the Sobel edge detectionmethod. We also introduce a shape representationmethod, the mountain-climbing sequence (MCS), thatis invariant to translation, rotation, and scale problems.The results of our proposed method show a superiormatching ratio even in the presence of a modest levelof deformation.