基于Gabor滤波器的低对比度纸病检测算法  

An Algorithm for Low Contrast Paper Defects Inspection Based on Gabor Filter

作　　者：曲蕴慧[1,2] 汤伟[1] 文豪[1] 雷涛[1] QU Yunhui;TANG Wei;WEN Hao;LEI Tao(College of Electric and Information Engineering,Shaanxi University of Science & Technology,Xi' an,Shaanxi Province,710021;Computer Teaching and Research Section,Xi' an Medical University,Xi'an,Shaanxi Province,710021)

机构地区：[1]陕西科技大学电气与信息工程学院,陕西西安710021 [2]西安医学院计算机教研室,陕西西安710021

出　　处：《中国造纸学报》2019年第2期42-46,共5页Transactions of China Pulp and Paper

基　　金：陕西省教育厅自然专项(17JK0645);陕西省科技统筹创新工程计划项目(2012KTCQ01-19);陕西省重点科技创新团队计划项目(2014KCT-15)

摘　　要：针对现有的纸病检测算法对裂痕、褶皱等低对比度纸病检出率低、抗干扰能力差的问题,提出一种基于Gabor滤波器的纸病检测算法。首先使用Gabor滤波器以及Gaussian滤波器去除纸张纹理干扰,增强纸病区域对比度;然后使用Laplasian算法进行边缘检测,最后使用形态学闭运算得到完整的纸病边缘图像。实验结果表明,该算法对低对比度纸病检测正确率高,并具有良好的抗干扰性能。Traditional paper defect detection algorithms have the problems of low detection rate and poor anti-interference ability for low contrast paper defects such as cracks and wrinkles.Considering these problems,an algorithm of low contrast paper defects based on Gabor let filter was presented.Firstly,the Gabor filter and Gaussian filter were used to eliminate the texture elements and enhance the contrast.Then,Laplacian algorithm was used for edge detection.Finally,morphological closed operation was used to obtain a whole edge image.The simulation results indicated that this algorithm had the advantages of high detection rate,accurate positioning and good anti-disturbance performance for low contrast paper defects.

关 键 词：GABOR滤波器 低对比度 边缘检测 形态学 纸病检测 

分 类 号：TS753.9[轻工技术与工程—制浆造纸工程]