Abstract | ||
---|---|---|
2D or 3D shapes are the most important visual information that we use to recognize an object. We propose a unified framework "ShapeLab" to search similar 2D or 3D shapes from an existing database. Users can search 3D shapes with a 2D input, and vice versa. ShapeLab is composed of four key components: (1) pose determination for 3D models; (2) 2D orthogonal view generation based on multiple levels of detail; (3) similarity measurement between 2D shapes; and (4) freehand sketch-based user interface. Key algorithms supporting the above components are briefly described. Experiments show ShapeLab can provide a better performance such as high accuracy, flexibility and scalability compared to the available methods. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1109/3DPVT.2006.128 | 3DPVT |
Keywords | Field | DocType |
shape retrieval,orthogonal view generation,important visual information,existing database,unified framework,multiple level,freehand sketch-based user interface,available method,better performance,key component,high accuracy,key algorithm,object recognition,image retrieval,graphical user interfaces,level of detail,pose estimation,user interface,information systems,information retrieval,robustness,scalability,user interfaces | Data mining,Computer science,Image retrieval,Robustness (computer science),Pose,Theoretical computer science,Graphical user interface,User interface,Sketch,Scalability,Cognitive neuroscience of visual object recognition | Conference |
ISBN | Citations | PageRank |
0-7695-2825-2 | 1 | 0.36 |
References | Authors | |
21 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jiantao Pu | 1 | 277 | 23.12 |
Karthik Ramani | 2 | 1328 | 81.38 |