首页|A novel image segmentation approach for wood plate surface defect classification through convex optimization

A novel image segmentation approach for wood plate surface defect classification through convex optimization

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
  • 维普
Detection of wood plate surface defects using image processing is a complicated problem in the forest industry as the image of the wood surface contains dif-ferent kinds of defects. In order to obtain complete defect images, we used convex optimization (CO) with different weights as a pretreatment method for smoothing and the Otsu segmentation method to obtain the target defect area images. Structural similarity (SSIM) results between orig-inal image and defect image were calculated to evaluate the performance of segmentation with different convex opti-mization weights. The geometric and intensity features of defects were extracted before constructing a classification and regression tree (CART) classifier. The average accu-racy of the classifier is 94.1％with four types of defects on Xylosma congestum wood plate surface: pinhole, crack, live knot and dead knot. Experimental results showed that CO can save the edge of target defects maximally, SSIM can select the appropriate weight for CO, and the CART classifier appears to have the advantages of good adapt-ability and high classification accuracy.

Convex optimizationThreshold segmentationStructure similarityDecision treeDefect recognition

Zhanyuan Chang、Jun Cao、Yizhuo Zhang

展开 >

College of Mechanical and Electrical Engineering, Northeast Forestry University, Harbin 150040, People's Republic of China

College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai 200234, People's Republic of China

work was supported by the Fund of Forestry 948 projectFundamental Research Funds for the Central Universitiesand the Natural Science Foundation of Heilongjiang Province

2015-4-522572017DB05C2017005

2018

林业研究(英文版)
东北林业大学,中国生态学学会

林业研究(英文版)

CSTPCDCSCDSCI
影响因子：0.365
ISSN：1007-662X
年,卷(期)：2018.29(6)
  • 11
  • 2