A new sketch-based 3D model retrieval method by using composite features
| Autor: | Guoliang Luo, Yuhua Li, Shujin Lin, Haopeng Lei |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Current (mathematics)
Series (mathematics) Computer Networks and Communications Computer science Orientation (computer vision) business.industry Process (engineering) 020207 software engineering Pattern recognition 02 engineering and technology Filter (signal processing) computer.software_genre Sketch Hardware and Architecture Histogram Pyramid 0202 electrical engineering electronic engineering information engineering Media Technology 020201 artificial intelligence & image processing Pyramid (image processing) Artificial intelligence Data mining business computer Software |
| Zdroj: | Multimedia Tools and Applications. 77:2921-2944 |
| ISSN: | 1573-7721 1380-7501 |
| DOI: | 10.1007/s11042-017-4446-y |
| Popis: | With the rapid growth of available 3D models in various areas, effective methods to search 3D models are becoming increasingly important. In this paper, we propose a new method for sketch-based 3D model retrieval. Different from current methods that make use of either global or local features, the proposed method uses composite features combining global and local features extracted from representative 2D views of 3D models. The global features, shape strings, represent exterior boundary shape of the views and the local features, improved Pyramid of Histograms of Orientation Gradients (iPHOG), represent their interior details. Specifically, a global feature based filtering step is adopted to select more relevant candidate models to the query sketch and a local feature based process is used to refine chosen candidates. To evaluate the performance of the proposed method with that of other previous ones, we conducted a series of experiments on public standard 3D model databases. Experimental results are presented and indicate the effectiveness of the new approach for sketch-based 3D model retrieval. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink