Name
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. |
Year | DOI | Venue |
|---|---|---|
2004 | 10.1109/ICDCSW.2004.1284018 | ICDCS Workshops |
Keywords | Field | DocType |
promptedge detection method,shape representationmethod,good shape representation,object representation,workincludes feature selection,content-based image retrieval,edge point,shape-based image,sustainingdeformation contour matching,sobel edge detectionmethod,noise shaping,data mining,feature extraction,shape,robustness,information retrieval,edge detection,feature selection,image retrieval,computer vision | Template matching,Computer vision,Image gradient,Feature detection (computer vision),Pattern recognition,Feature (computer vision),Computer science,Edge detection,Scale space,Histogram of oriented gradients,Artificial intelligence,Visual Word | Conference |
ISBN | Citations | PageRank |
0-7695-2087-1 | 10 | 0.68 |
References | Authors | |
12 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hwei-jen Lin | 1 | 59 | 8.91 |
| Yang-Ta Kao | 2 | 37 | 4.47 |
| Shwu-huey Yen | 3 | 42 | 9.07 |
| Chia-Jen Wang | 4 | 17 | 3.25 |