Using computer vision and compressed sensing for wood plate surface detection

被引：13

作者：

Zhang, Yizhuo ^{[1
]}

Liu, Sijia ^{[1
]}

Tu, Wenjun ^{[1
]}

Yu, Huiling ^{[1
]}

Li, Chao ^{[1
]}

机构：

[1] Northeast Forestry Univ, Harbin 150040, Peoples R China

来源：

OPTICAL ENGINEERING | 2015年 / 54卷 / 10期

关键词：

comprehensive detection; computer vision; multiscaled feature; feature optimization; compressed sensing; AUTOMATED VISUAL INSPECTION; DEFECT CLASSIFICATION;

D O I：

10.1117/1.OE.54.10.103102

中图分类号：

O43 [光学];

学科分类号：

070207 [光学];

摘要：

Aiming at detecting the random and complicated characteristic of wood surface, we proposed a comprehensive detection algorithm based on computer vision and compressed sensing. First, integral projection method was used to trace and locate the position of a wood plate; then surface images were obtained by blocks. Second, multiscaled features were extracted from image to express the surface characteristic. Third, particle swarm optimization algorithm was used for multiscaled features selection. Finally, the defects and textures were detected by compressed sensing classifier. Five types of wood samples, including radial texture, tangential texture, wormhole, live knot, and dead knot, were used for tests, and the average classification accuracy was 94.7%. (C) 2015 Society of Photo-Optical Instrumentation Engineers (SPIE)

引用

页数：10

共 18 条

[1]

[Anonymous], 2010, ARTIF INTELL

[2]

Bai Xue-bing, 2005, Journal of the Harbin Institute of Technology, V37, P1667

[3]

Compressed sensing [J].