CAJ | 학술논문

提出一种对板材表面缺陷和纹理进行协同快速准确检测的算法. 根据双树复小波所特有的方向性和时移不变性,研究了板材表面图像的双树复小波特征提取及融合算法,对板材表面图像进行3级双树复小波分解得到40个特征向量,并通过遗传算法优选出23个关键特征,优选后的特征能够较为完整地表达板材图像的复杂信息并减小数据冗余. 最后采用压缩感知理论,将优选后的特征向量作为样本矩阵列,构造出训练样本数据字典,通过最小残差完成对板材表面信息的分类识别. 实验对木材表面存在的弦切纹、径切纹、活结和死结等4类柞木样本进行了检测,正确率分别为91. 8%、100%、96. 4%和91. 8%,该算法能够以95%的平均识别率完成板材表面缺陷、纹理的协同检测.
제출일충대판재표면결함화문리진행협동쾌속준학검측적산법. 근거쌍수복소파소특유적방향성화시이불변성,연구료판재표면도상적쌍수복소파특정제취급융합산법,대판재표면도상진행3급쌍수복소파분해득도40개특정향량,병통과유전산법우선출23개관건특정,우선후적특정능구교위완정지표체판재도상적복잡신식병감소수거용여. 최후채용압축감지이론,장우선후적특정향량작위양본구진렬,구조출훈련양본수거자전,통과최소잔차완성대판재표면신식적분류식별. 실험대목재표면존재적현절문、경절문、활결화사결등4류작목양본진행료검측,정학솔분별위91. 8%、100%、96. 4%화91. 8%,해산법능구이95%적평균식별솔완성판재표면결함、문리적협동검측.
A quick and accurate collaborative classification method for wood defects and texture was pro-posed. As dual-tree complex wavelet has the advantages of approximate shift invariance and good direc-tional selectivity, dual-tree complex wavelet feature was extracted from wood board image and the fusion method was discussed. Three-level dual-tree complex wavelet decomposition was carried out to the surface image and 40 features were got, then genetic algorithm ( GA) was used for feature selection and 23 fea-tures were chosen. Feature fusion can better express the surface information and meanwhile heavily re-duce the data redundancy. Finally, wood surface classification was completed by using compressed sens-ing ( CS) , optimized dimensional feature vector was used as sample matrix and data dictionary of training samples was constructed, then, wood surface classification was completed by using least residual at last. Four types of Xylosma samples:radial texture, tangential texture, live knot and dead knot were used for experiment , the classification accuracy of the above four types were 91. 8%, 100%, 96. 4% and 91. 8%respectively. and this system could complete the defects and textures collaborative classification with an average recognition rate of 95%.