摘要
设计了木材加工业中木材纹理表面的检测系统,提出了一种有效的选取小波频带重建图像的纹理瑕疵检测方法。设计的检测系统由新型LED光源,明暗域结合成像光学系统,高速高分辨率线阵CCD器件等组成。应用小波基函数在较优的分解级数上对纹理图像进行分解,然后在最佳的分辨率级数上正确选取平滑图像或者细节图像来重建图像。在重建图像中均匀纹理图案被有效地移除,仅仅保留了局部瑕疵区域,小波频带选取是基于小波系数的能量分布自动确定最佳重构参数。重构后的图像经阈值处理得到二值图像,最后运用数学形态学的方法对二值图像后处理。实验表明,该方法可用于实时在线检测木材表面的瑕疵。
The wood surface texture inspection method in wood machining industries is introduced. This inspection method consists of a new LED line light source, bright and dark tield combined imaging optical system, high speed anu high resolution linear array CCD sensor. First, the texture image is decomposed by using wavelet base function in terms of the optimum decomposition levels, and then the restoration image can be reconstructed by properly selecting the smooth subimage or the detail subimages at best resolution levels. The homogeneous texture pattern can be effectively removed and only local defects are preserved in the restored image. A subband selection procedure is developed to automatically determine the best reconstruction parameters based on the energy distribution of wavelet coefficients. Then binarized image is received after image segmentation. At last the methods of image post-processing mathematical morphology are used in segmentation image. Experiments demonstrate the validity of the method, and show the potential possibility of real-time processing in an on-line wood surface inspection.
出处
《光学与光电技术》
2008年第6期16-19,共4页
Optics & Optoelectronic Technology
关键词
线阵CCD
木材表面检测
瑕疵检测
小波重构
linear array CCD
wood surface inspection
defect detection
wavelet reconstruction
