改进的阈值选取方法在纸病图像分割中的应用  

Improved Threshold Selection Method of Paper Image Segmentation

作　　者：成亚维[1] 李茜[1] 汤伟[1] 

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

出　　处：《造纸科学与技术》2014年第1期65-68,共4页Paper Science & Technology

基　　金：国家国际科技合作项目(2010DFB43660);陕西省科技统筹创新工程计划项目(基金号:2012KTCQ01-19)

摘　　要：全局阈值分割法对含有对比度不同的纸病图像分割效果差,把图像先分块再求阈值,可以分割出每块区域的目标。针对上述分割结果的不足,提出了一种改进的阈值选取方法,该方法是用改进的迭代法对分割的子块求阈值,最后与每块区域的平均灰度值作比较,找出整幅图像的最优阈值。以含有灰度不一污点的纸病图像为处理对象,实验结果表明改进的方法可以分割出低对比度纸病。Segmentation effect of paper image with contrasting defects is poor using global threshold segmentation method. The goal in different area is segmented after image block. Considering problems of the above results, an improved method is proposed . It seek threshold in sub - blocks by improved iterative method , and then compare each sub -block＇s threshold value with average gray value to find the best threshold in the whole image. Taking pa- per images with different grayscale stains as binary object, the experimental results show that the improved method can segment the low contrast paper defect.

关 键 词：阈值分割 迭代阈值分割法 大津法 

分 类 号：TS736[轻工技术与工程—制浆造纸工程]