Title :
3D model retrieval using 2D cepstral features
Author :
Lee, Chang-Hsing ; Shih, Jau-Ling ; Chou, Chih-Hsun ; Yu, Kung-Ming ; Hung, Chuan-Yen
Author_Institution :
Dept. of Comput. Sci. & Inf. Eng., Chung Hua Univ., Hsinchu, Taiwan
Abstract :
In this paper, we will propose a 3D model retrieval approach using 2D cepstral features. First, six projection planes representing the elevation (depth) value are generated. Then, 2D cepstral features are extracted from each projection plane for searching similar 3D models. Experiments conducted on the Princeton Shape Benchmark (PSB) database have shown that the proposed 2D cepstral features outperforms other state-of-the-art descriptors in terms of the DCG score.
Keywords :
feature extraction; information retrieval; solid modelling; 2D cepstral feature extraction; 3D model retrieval; Princeton Shape Benchmark database; depth value; elevation value; projection plane; Cepstral analysis; Computational modeling; Databases; Feature extraction; Shape; Solid modeling; Vectors; 2D cepstral feature; 3D model retrieval;
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on
Conference_Location :
Kyoto
Print_ISBN :
978-1-4673-0045-2
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2012.6288390
