基于C-V模型的木材缺陷重建图像特征提取

Feature Extraction of Wood Defect Reconstructed Images Based on the C-V Model

以含有裂纹的柳木木材、含有空洞的椴树木材为样本,实验研究了基于细胞反演法的木材重建图像的特征提取。首先,利用细胞的反向投影方法将木材断层图像进行重建后,对所得图像进行开启化平滑处理;然后,利用C-V模型获取木材断层图像中缺陷部分特征;最后,将测得的木材缺陷面积值与真实值进行比较。结果表明:利用C-V模型可以将重建的缺陷图像特征准确的分割出来,实现了对此细胞反演法重建质量的评价;为木材缺陷重建图像的质量评估提供了方法,为今后木材缺陷监测仪的设计提供参考。

We proposed a feature extraction algorithm of wood reconstructed images based on the cell-inversion method. Firstly,the cell-inversion method is used to reconstruct the wood tomographic image,and open smooth filtering is implemented to the results. Secondly,C-V model is used to obtain the wood defect features from the reconstructed image. Finally,a comparison is made between measured and real values of the defect area which provide a quality evaluation of the cell inversion algorithm. Willow samples with cracks and Linden samples with cavity were used for experiment. The C-V model can segment the defect image and extract features from the reconstructed image. This research will provide a quality evaluation method of wood defect image reconstruction and the future design of wood defect monitor.