基于Mean Shift的织物图像分割算法

首先介绍了Mean Shift算法的处理过程,然后以处理织物图像分割为研究对象,将扩展形式的Mean shift算法用于解决织物图像分割问题。新提出的织物图像分割算法包括2个步骤:Mean Shift图像滤波和Mean Shift图像分割,并介绍了各自的原理。分割效果有3个关键参数控制:空域带宽、色度域带宽和最小区域限制。实验结果给出了3个参数的影响和选取分析,最后给出该织物图像分割算法与原CAD处理效果比较图,表明该算法具有可行性、有效性和鲁棒性。

Fabric image segmentation algorithm based on Mean Shift

Firstly,Mean Shift procedure was introduced.And then targeting at the research on fabric image segmentation,the extended Mean shift algorithm was used to try to solve the issue.A newly proposed fabric image segmentation algorithm involved two steps: Mean Shift image filtering and image segmentation,and their principles were explained respectively.The segmentation results were controlled by three important parameters,i.e.spatial bandwidth,color bandwidth and minimum region,whose influence,selection and analysis were demonstrated.Finally,the fabric image segmentation algorithm and the graph for comparison showing the previous CAD processed effect were given,which showed the feasibility,efficiency and robustness of that algorithm in fabric image processing.