Heritage Debris Classification Based on 3D Texture Feature and SVM

Author

Li, Meng ; Huang, Canjie ; Fu, Ping ; Yue, Suyan

Author_Institution

Dept. Autom. Test & Control, Harbin Inst. of Technol., Harbin

fYear

2008

fDate

15-17 Aug. 2008

Firstpage

756

Lastpage

759

Abstract

A heritage debris classification based on 3D texture feature and SVM is proposed in this paper. We compute the bidirectional histogram and correlation function of Lambertian, isotropic, randomly rough surfaces which are common in real-world scenes firstly, and final classification results are gained with SVM. Performance is evaluated by employing 600 texture images corresponding to 61 real-world surface samples extracted from the Columbia-Utrecht reflectance and texture (CUReT) database. The experiments produce good classification results, and we discuss the advantages and disadvantages of this methods and its scope of application.

Keywords

correlation methods; feature extraction; image classification; image texture; support vector machines; 3D texture feature; Columbia-Utrecht reflectance and texture database; SVM; bidirectional histogram; correlation function; heritage debris classification; randomly rough surfaces; Automatic control; Automatic testing; Histograms; Image texture; Rough surfaces; Signal processing; Support vector machine classification; Support vector machines; Surface roughness; Surface texture; 3D texture; SVM; heritage debris;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Information Hiding and Multimedia Signal Processing, 2008. IIHMSP '08 International Conference on

Conference_Location

Harbin

Print_ISBN

978-0-7695-3278-3

Type

conf

DOI

10.1109/IIH-MSP.2008.251

Filename

4604164