| 基于灰度共生矩阵和聚类方法的木材缺陷识别 |
| |
| 引用本文： | 吴东洋,业宁,苏小青.基于灰度共生矩阵和聚类方法的木材缺陷识别[J].计算机与数字工程,2010,38(11):38-41. |
| |
| 作者姓名： | 吴东洋 业宁 苏小青 |
| |
| 作者单位： | [1]南京林业大学信息技术学院,南京210037 [2]海南省万宁市农业银行红专支行,万宁571500 |
| |
| 基金项目： | 国家自然科学基金，江苏省自然科学基金 |
| |
| 摘 要： | 文章提出了一种新的基于灰度共生矩阵的木材纹理特征提取和聚类分析的木材缺陷识别方法。该方法基于灰度共生矩阵,提取5个具有代表性的纹理特征：能量（E）,惯性矩（I）,均值和（SOA）,聚类阴影（SOC）,方差和（SOV）,实现数据降维,对产生的特征数据集分别利用k-means算法及AP算法进行聚类,自动找出并正确标识木材表面缺陷位置,并对比分析不同木材表面缺陷类型识别效率。实验结果表明,该方法能快速有效地进行木材表面缺陷自动识别。
|
| 关 键 词： | 灰度共生矩阵 k-means Affinity Propagation聚类 |
Wood Defect Recognition Based on GLCM and Clustering Algorithm |
| |
| Wu Dongyang,Ye Ning,Su Xiaoqing.Wood Defect Recognition Based on GLCM and Clustering Algorithm[J].Computer and Digital Engineering,2010,38(11):38-41. |
| |
| Authors: | Wu Dongyang Ye Ning Su Xiaoqing |
| |
| Affiliation: | Wu Dongyang) Ye Ning) Su Xiaoqing)(School of Information Technology,Nanjing Forestry University1),Nanjing 210037)(The Red Special Branch of Agricultural Bank,Hainan Province2),Wanning 571500) |
| |
| Abstract: | A new method based on GLCM and Clustering Algorithm for wood defect identification was analyzed.The method is based on GLCM,extracting the five wood image texture characteristics E,I,SOA,SOC and SOV,decreasing the data dimensions,classifying the feature data set by K-means and AP,finding out automatically and identifying correctly the wood surface defect location,and comparing and analyzing the identification efficiency of different wood surface defects.According to the experiment,the method can automatically identify the wood surface defect rapidly and effectively. |
| |
| Keywords: | GLCM K-means Affinity Propagation clustering |
| 本文献已被 维普 万方数据 等数据库收录！ |
|
