A new method for wood recognition based on blocked HLAC

Author

Ma, Lin-jin ; Wang, Hang-jun

Author_Institution

Sch. of Inf. Sci. & Technol., ZheJiang Agric. & Forestry Univ., Linan, China

fYear

2012

fDate

29-31 May 2012

Firstpage

40

Lastpage

43

Abstract

This paper propose a new method for wood recognition based on texture analysis. At first, wood texture images are divided into several blocks in our method. Secondly, wood features are extracted from these blocked grey-scale images using different mask, which is knows as higher-order local autocorrelation (HLAC). Finally, Support Vector Machine (SVM) was used to verify the performance of the method. Experiments carried on the wood texture database demonstrate that our method outperforms the original HLAC method.

Keywords

feature extraction; image recognition; image texture; production engineering computing; support vector machines; wood processing; HLAC; blocked HLAC; blocked grey-scale images; higher-order local autocorrelation; support vector machine; texture analysis; wood features extraction; wood recognition; wood texture images; Correlation; Databases; Educational institutions; Feature extraction; Image recognition; Support vector machines; Training; SVM; Wood recognition; higher-order local autocorrelation;

fLanguage

English

Publisher

ieee

Conference_Titel

Natural Computation (ICNC), 2012 Eighth International Conference on

Conference_Location

Chongqing

ISSN

2157-9555

Print_ISBN

978-1-4577-2130-4

Type

conf

DOI

10.1109/ICNC.2012.6234674

Filename

6234674