SIGMOD '95 Proceedings of the 1995 ACM SIGMOD international conference on Management of data
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
Hi-index | 0.00 |
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.