面向摄像整纬器的织物纬斜检测方法  

Detection Method of Fabric Weft Skew With Camera Straightener

作　　者：刘建宝 李平[1] LIU Jianbao;LI Ping(College of Information Science and Engineering,Huaqiao University,Xiamen 361021,China)

机构地区：[1]华侨大学信息科学与工程学院,福建厦门361021

出　　处：《华侨大学学报（自然科学版）》2020年第1期96-102,共7页Journal of Huaqiao University(Natural Science)

基　　金：国家自然科学基金资助项目(61603144);福建省自然科学基金资助项目(2018J01095);福建省高校产学合作科技重大项目(2013H6016);华侨大学中青年教师科技创新资助计划项目(ZQN-PY509)。

摘　　要：为了解决局部阴影、疵点和噪点对图像法的检测带来不利影响的问题,设计一种基于分步大津法和窗口像素统计的图像检测方法.首先,利用图像分割技术解决在有局部阴影情况下图像二值化的问题;然后,通过窗口像素统计的方法得到纬斜信息;最后,根据统计结果得到准确的纬斜角度值.实验结果表明:该检测方法可以克服局部阴影、疵点、噪点的影响,保证检测误差低于0.3°.In order to solve the problems of local shadows,defects and noises which will have a negative impact on image detection,an image detection method based on step-by-step Otsu method and window pixel statistics is designed.Firstly,image segmentation technology is used to solve the problem of image binarization in the case of local shadows.Then,weft skew information is obtained by window pixel statistics method.Finally,accurate weft skew angle values are obtained according to the statistical results.The experimental results show that the detection method can overcome the influence of local shadows,defects and noises,and ensure that the detection error is less than 0.3°.

关 键 词：纬斜检测 纹理识别 分步大津法 图像二值化 像素统计 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术] TS195.3[自动化与计算机技术—计算机科学与技术]