
浏览全部资源
扫码关注微信
1. 东北林业大学 土木工程学院,黑龙江 哈尔滨,150040
2. 东北林业大学 信息与计算机工程学院,黑龙江 哈尔滨,150040
[ "任重昕(1977-),女,吉林长岭人,硕士,工程师,主要从事数字图像处理、计算机软件应用等方向研究。E-mail:renfishi2002@yeah.net" ]
[ "毕剑华(1990-),女,黑龙江大庆人,硕士研究生,主要从事数字图像处理、计算机模式识别等方向研究。" ]
[ "谢琳(1989-),女,黑龙江哈尔滨人,硕士研究生,主要从事数字图像处理、计算机模式识别等方向研究。" ]
[ "仉俊峰(1974-),女,黑龙江哈尔滨人,博士,副教授,主要从事数字图像处理、容错技术等方向研究。" ]
收稿日期:2014-04-30,
修回日期:2014-05-13,
网络出版日期:2014-06-02,
纸质出版日期:2014-10-05
移动端阅览
任重昕, 毕剑华, 谢琳, 仉俊峰. 采用图像分割方法进行木材表面缺陷的定量检测[J]. 液晶与显示, 2014,29(5): 785-792
REN Zhong-xin, BI Jian-hua, XIE Lin, ZHANG Jun-feng. Quantitative detection of wood surface defects by image segmentation method[J]. , 2014,29(5): 785-792
任重昕, 毕剑华, 谢琳, 仉俊峰. 采用图像分割方法进行木材表面缺陷的定量检测[J]. 液晶与显示, 2014,29(5): 785-792 DOI: 10.3788/YJYXS20142905.0785.
REN Zhong-xin, BI Jian-hua, XIE Lin, ZHANG Jun-feng. Quantitative detection of wood surface defects by image segmentation method[J]. , 2014,29(5): 785-792 DOI: 10.3788/YJYXS20142905.0785.
随着木材加工业的集约化发展以及对木材表面加工质量高水平的苛求,传统的人工检测方式已经难以满足木材产品的加工生产。在了解木材表面缺陷的分类、缺陷产生原因和木材缺陷表面图像的特征的基础上,对比分析平均值法、最大值法和加权平均值法3种图像灰度化方法效果,并选定加权平均值法对木材缺陷图像进行灰度化预处理。在Matlab 6.5 GUI编程框架下实现木材缺陷检测系统,通过选取Isodata聚类迭代法、Otsu最大方差法、最大熵法和Sobel边缘分割法为基础的4种阈值化图像分割方法对木材缺陷特征的分割效果和分割速率进行实验对比分析。实验结果表明,运用Isodata聚类迭代法的图像分割方法能够快速准确分割图像实现木材缺陷检测。
With the development of wood industry and the large requirement for the wood surface processing quality
traditional artificial detections have been difficult for satisfying wood processing production requirement. By knowing the classification of wood surface defects
defect causes and characteristics of wood surface defect images
we compare and analyze the average method
maximum method and the weighted average method on image gray effect
and the weighted average method is selected. In Matlab 6.5 GUI programming framework
we implement wood defect detection system by choosing the Isodata clustering iteration method
Otsu method of maximum variance
maximum entropy method and Sobel edge segmentation method for image segmentation and comparisons. We can achieve the fast and accurate image segmentation and wood material defect detection by using the Isodata clustering iteration method.
Szymani R, Mcdonald K A.Defect detection in lumber: state of the art[J].Forest Products Journal,1981, 31(11):34-43.[2] Longuetaud F, Mothe F, Kerautret B,et al.Automatic knot detection and measurements from X-ray CT images of wood: a review and validation of an improved algorithm on softwood samples[J].Computers and Electronics in Agriculture,2012, 85(2):77-89.[3] Portala J F, Ciccotelli J.Nondestructive testing techniques applied to wood scanning[J].Measurement,1992, 2(3/4):299-307.[4] Radovan S, George P, Panagiotis M,et al.An approach for automated inspection of wood boards[C].Proc. IEEE ICIP,2001,2:798-801.[5] Conners R W, Kline D E, Araman P A,et al.Machine vision technology in the forest products industry: a multiple sensor approach[J].IEEE Computer,1997, 30(7):38-45.[6] Kline D E, Surak C, Araman P A.Automated hardwood lumber grading utilizing a multiple sensor machine vision technology[J].Computers and Electronics in Agriculture,2003, 41(2):139-155.[7] 陈恺,陈芳,戴敏,等. 基于萤火虫算法的二维熵多阈值快速图像分割[J]. 光学精密工程, 2014,22 (2): 517-523. Chen K,Chen F,Dai M, et al.Fast image segmentation with multilevel threshold of two-dimensional entropy based on firefly algorithm[J].Optics and Precision Engineering,2014, 22(2):517-523.(in Chinese)[8] Philipp I, Rath T.Improving plant discrimination in image processing by use of different color space transformations[J].Computers and Electronics in Agriculture,2002, 35(1):1-15.[9] 宋建中. 图像处理智能化的发展趋势[J]. 中国光学, 2011,5(4):431-440. Song J Z. Development trend of image processing intelligence[J].Chinese Optics,2011,5(4),431-440.(in Chinese)[10] 洪军. 模糊 ISODATA聚类分析方法的设计[J]. 计算机与数字工程, 2009,37(2):19-20. Hong J.Design of a Fuzzy ISODATA clustering analyzing algorithm[J].Computer Digital Engineering,2009, 37(2):19-20.(in Chinese)[11] Tilton J C. Analysis of hierarchically related image segmentations[C].Proc. 2003 IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data,2003:60-69.[12] Wu W R,Wei S C.Rotation and gray-scale transform-invariant texture classificationusing spiral re-sampling, sub-band decomposition and Hidden Markov Model[J].IEEE Trans on Image Processing,1996, 5(12):1423-1434.[13] 高成. Matlab图像处理与应用[M]. 北京:国防工业出版社, 2007. Gao C.Matlab Image Processing and Application [M]. Beijing: National Defence Industry Press, 2007.(in Chinese)
0
浏览量
20
下载量
2
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621