木地板表面死节缺陷图像检测方法

Detection Method of Wood Floor Surface Dead Knot Defect Images

针对室内装饰实木地板表面死节缺陷,提出一种基于多通道大津法(Otsu)与加权Chan-Vese(CV)模型的实木地板死节缺陷图像检测算法。首先,输入RGB彩色图像并提取R、G、B三颜色通道,分别对三通道进行Otsu阈值分割,将三通道二值图进行或运算,得到初始水平集;然后,将三通道的数据项进行加权,与正则化项一起构成能量泛函,进行曲线演化;最后,采用加权CV模型进行水平集迭代计算,得到木地板死节缺陷。试验结果表明,提出的算法能充分利用各通道的优点,提高分割效果。

Aiming at the surface dead knot defects of solid wood flooring for interior decoration,an wood floor dead knot defect image detection algorithm based on Otsu and CV model was proposed.First,the RGB color image was input and R,G,B three-color channels were extracted respectively,and segmented by Otsu threshold method,then the three channel binary images were OR operated,the initial level set was gained.Then,the data items of the three channels were weighted to form the energy functional together with the regularization items,followed by curve evolution.Finally,the weighted CV model was used to calculate the level set iteratively,and the dead knot defects of wood floor were obtained.The test results show that the proposed algorithm can make full use of the advantages of each channel and improve the segmentation effect.