摘要
为了解决运动鞋生产过程光条在粗糙的鞋底表面产生的光斑以及光条宽度变化而带来光条图像的中心提取缺失的问题,提出一种适用于运动鞋底表面光条图像中心的提取算法。在最大类间差法(Otsu)的基础上引入了模板内像素灰度均值和其他像素灰度的差值阈值,从而有效分割出光条图像的光斑区域。采用Canny算子提取光条图像的边缘和宽度,并根据光条图像的宽度来改变Steger算法中高斯滤波核的大小。试验结果表明,所提算法可以准确分割运动鞋底表面的光条图像光斑,并快速提取鞋底表面光条的中心,解决因光条宽度变化而导致光条图像的中心提取失败的问题。
In order to solve the problem of light spot caused by light strip on rough sole surface and the problem of central extraction failure of light strip image due to changing the width of light strip image during the production of sports shoes,an algorithm of extracting center of light strip image was proposed,which was suitable for the surface of sole.On the basis of Otsu,the threshold of the difference between the mean grayscale of pixels in the template and other grayscale of pixels was introduced to effectively segment the spot of the light strip image.Canny operator was used to extract the edge and the width of light strip image,and the size of Gaussian filter kernel in Steger algorithm was changed according to the width of light strip image.The test results show that the proposed algorithm can accurately segment spot of light strip image on the surface of sole and quickly extract the center of the light strip image on the surface of sole,which solves the problem of central extraction failure of light strip image due to changing the width of light strip image.
作者
邢礼源
陈玉洁
张豪
罗一龙
XING Liyuan;CHEN Yujie;ZHANG Hao;LUO Yilong(College of Mechanical Engineering,DonghuaUniversity,Shanghai 201620,China)
出处
《东华大学学报（自然科学版）》
CAS
北大核心
2021年第4期43-48,共6页
Journal of Donghua University(Natural Science)
基金
国家重点研发计划资助项目(2018YFB1308800)。
