文章基本信息

标题：Systematic feature analysis on timber defect images
本地全文：下载
作者：Ummi Rabaah Hashim ; Siti Zaiton Mohd Hashim ; Azah Kamilah Muda 等
期刊名称：IJAIN (International Journal of Advances in Intelligent Informatics)
印刷版ISSN：2442-6571
电子版ISSN：2548-3161
出版年度：2017
卷号：3
期号：2
页码：56-67
DOI：10.26555/ijain.v3i2.94
语种：English
出版社：Universitas Ahmad Dahlan
摘要：Feature extraction is unquestionably an important process in a pattern recognition system. A defined set of features makes the identification task more efficiently. This paper addresses the extraction and analysis of features based on statistical texture to characterize images of timber defects. A series of procedures including feature extraction and feature analysis was executed to construct an appropriate feature set that could significantly separate amongst defects and clear wood classes. The feature set aimed for later use in a timber defect detection system. For Accessing the discrimination capability of the features extracted, visual exploratory analysis and confirmatory statistical analysis were performed on defect and clear wood images of Meranti (Shorea spp.) timber species. Results from the analysis demonstrated that there was a significant distinction between defect classes and clear wood utilizing the proposed set of texture features.
关键词：texture;feature extraction;timber surface;automated vision inspection;feature selection