基于Contourlet变换和隐朴素贝叶斯分类器的带钢表面检测技术研究
|
摘要
用于控制产品质量的表面检测技术在带钢的工业生产中起着关键作用,而特征提取是提高带钢表面缺陷识别率的关键步骤。为了克服小波变换在捕获平滑轮廓和方向边缘等图像信息方面存在的限制,本文提出了一种基于Contourlet变换的特征提取方法。Contourlet变换是一种新开发的利用多尺度和方向滤波器组的小波变换的二维扩展,它可以捕捉图像的内在几何结构和平滑轮廓。带钢表面图像经过Contourlet变换提取的特征向量输入隐朴素贝叶斯分类器,从而进行带钢表面缺陷的检测与识别。实验结果显示应用的方法可以提高带钢表面缺陷的分类正确率。
Surface inspection technology,used to control the product quality,plays a critical role in the industrial production of steel strip. Feature extraction is a crucial step to improve the defect recognition rate of steel strip. To overcome the limitations of wavelet transform in capturing directional information in images such as smooth contours and directional edges,a feature extraction method based on Contourlet transform is proposed in this paper. Contourlet transform is a newly developed two-dimensional extension of wavelet transform using multiscale and directional filter banks,which can capture the intrinsic geometric structures and smooth contours of surface image. The feature vector of the strip surface image extracted by the Contourlet transform is used as an input to the hidden naive Bayes classifier,to detect and identify the steel strip surface defects. The experimental results show that the proposed method can improve the classification accuracy of steel strip surface defects.
Surface inspection technology,used to control the product quality,plays a critical role in the industrial production of steel strip. Feature extraction is a crucial step to improve the defect recognition rate of steel strip. To overcome the limitations of wavelet transform in capturing directional information in images such as smooth contours and directional edges,a feature extraction method based on Contourlet transform is proposed in this paper. Contourlet transform is a newly developed two-dimensional extension of wavelet transform using multiscale and directional filter banks,which can capture the intrinsic geometric structures and smooth contours of surface image. The feature vector of the strip surface image extracted by the Contourlet transform is used as an input to the hidden naive Bayes classifier,to detect and identify the steel strip surface defects. The experimental results show that the proposed method can improve the classification accuracy of steel strip surface defects.
引文
[1]Kano M,Nakagawa Y. Data-based process monitoring,process control,and quality improvement:Recent developments and applications in steel industry[J]. Computers&Chemical Engineering,2008,32(1-2):12~24.
[2]Do M N,Vetterli M. The contourlet transform:an efficient directional multiresolution image representation[J]. IEEE Transactions on image processing,2005,14(12):2091~2106.
[3]Jiang L,Zhang H,Cai Z. A novel bayes model:Hidden naive bayes[J]. IEEE Transactions on knowledge and data engineering,2009,21(10):1361~1371.
[4]李炜,黄心汉,王敏,等.基于机器视觉的带钢表面缺陷检测系统[J].华中科技大学学报(自然科学版),2003,31(2):72~74.
[5]贾方庆.基于机器视觉的带钢表面缺陷检测系统研究[D].重庆大学,2007.
[6]Xie X. A review of recent advances in surface defect detection using texture analysis techniques[J]. ELCVIA Electronic Letters on Computer Vision and Image Analysis,2008,7(3).
[2]Do M N,Vetterli M. The contourlet transform:an efficient directional multiresolution image representation[J]. IEEE Transactions on image processing,2005,14(12):2091~2106.
[3]Jiang L,Zhang H,Cai Z. A novel bayes model:Hidden naive bayes[J]. IEEE Transactions on knowledge and data engineering,2009,21(10):1361~1371.
[4]李炜,黄心汉,王敏,等.基于机器视觉的带钢表面缺陷检测系统[J].华中科技大学学报(自然科学版),2003,31(2):72~74.
[5]贾方庆.基于机器视觉的带钢表面缺陷检测系统研究[D].重庆大学,2007.
[6]Xie X. A review of recent advances in surface defect detection using texture analysis techniques[J]. ELCVIA Electronic Letters on Computer Vision and Image Analysis,2008,7(3).