| 一种基于混合纹理特征的木板材表面缺陷检测方法 |
| |
| 引用本文： | 尹建新,祁亨年,冯海林,杜晓晨.一种基于混合纹理特征的木板材表面缺陷检测方法[J].浙江林学院学报,2011,28(6):937-942. |
| |
| 作者姓名： | 尹建新 祁亨年 冯海林 杜晓晨 |
| |
| 作者单位： | 浙江农林大学信息工程学院,浙江临安,311300 |
| |
| 基金项目： | 国家自然科学基金资助项目，浙江省自然科学基金资助项目，浙江农林大学预研项目 |
| |
| 摘 要： | 利用计算机视觉技术检测木板材表面缺陷。提出了一种基于混合纹理特征的表面缺陷检测算法,能准确、鲁棒地检测出木板材表面图像中是否有缺陷。首先,分别使用灰度共生矩阵方法、Gabor滤波方法和几何不变矩方法提取了10个优化后的图像纹理及尺度、平移、旋转不变特征;然后,对特征向量进行有效组合;最后,基于融合后的混合纹理特征向量,应用BP人工神经网络对样本集进行训练和检测。实验表明,该方法能准确地对木板材表面缺陷进行检测,平均检测成功率达96.2%。
|
| 关 键 词： | 林业工程 灰度共生矩阵 Gabor滤波 不变矩 木板材 缺陷检测 |
A method for wood surface defect detection based on mixed texture features |
| |
| YIN Jian-xin,QI Heng-nian,FENG Hai-lin,DU Xiao-chen.A method for wood surface defect detection based on mixed texture features[J].Journal of Zhejiang Forestry College,2011,28(6):937-942. |
| |
| Authors: | YIN Jian-xin QI Heng-nian FENG Hai-lin DU Xiao-chen |
| |
| Institution: | YIN Jian-xin,QI Heng-nian,FENG Hai-lin,DU Xiao-chen(School of Information and Engineering,Zhejiang A & F University,Lin'an 311300,Zhejiang,China) |
| |
| Abstract: | It is important to detect the wood surface defects using computer vision technology.In this paper,a defect detection method which can accurately and robustly determine whether there is defect on wood surface image or not is proposed based on mixed texture features.At first,gray level co-occurrence matrix(GLCM),Gabor filtering and invariant moment method are used to extract 10 image scale,translation,rotation invariant and texture features optimally.Then,feature vectors are mixed effectively.Finally,BP artif... |
| |
| Keywords: | forest engineering gray level co-occurrence matrix(GLCM) gabor filter invariant moment wood image defect detection |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
