摘要
分析了原有图像过渡区确定方法中的缺陷及其产生的根源 ,根据过渡区内像素点具有的邻域方向性 ,引入了基于一元线性回归处理的局部区域随机波动消除方法 .对大量的实际图像的处理结果表明 ,这种方法将会大大提高过渡区判定过程的鲁棒性和定位精度 .
The deficiency of original image transition region theory and its origin were analyzed. Based on the directional property of neighborhood pixels in the transition region, one-dimensional linear regression process was introduced to eliminate the influence of random fluctuations in local image regions. The practical results show that the robustness and the accuracy of new algorithm could be improved greatly.
出处
《红外与毫米波学报》
SCIE
EI
CAS
CSCD
北大核心
2001年第3期211-214,共4页
Journal of Infrared and Millimeter Waves
关键词
过渡区
图像分割
一元线性回归
计算机视觉
transition region
image segmentation
one-dimensional linear regression
