当前位置:
X-MOL 学术
›
Optoelectron. Instrument. Proc.
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
Modified Method for Detecting Small Structures in Noisy Images
Optoelectronics, Instrumentation and Data Processing ( IF 0.5 ) Pub Date : 2019-11-01 , DOI: 10.3103/s8756699019060074 A. V. Likhachev
Optoelectronics, Instrumentation and Data Processing ( IF 0.5 ) Pub Date : 2019-11-01 , DOI: 10.3103/s8756699019060074 A. V. Likhachev
A classifier for operation with 1-pixel image fragments is proposed. Element segmentation into object and background is performed based on posterior probabilities, which are calculated using a histogram. A simulation experiment has shown that the developed algorithm provides a more accurate classification than segmentation based on the brightness threshold determined from the minimum condition for the weighted sum of errors of the first and second kind.
中文翻译:
检测噪声图像中小结构的改进方法
提出了一种用于对 1 像素图像片段进行操作的分类器。基于使用直方图计算的后验概率执行元素分割成对象和背景。仿真实验表明,所开发的算法提供了比基于第一类和第二类误差加权和的最小条件确定的亮度阈值的分割更准确的分类。
更新日期:2019-11-01
中文翻译:
检测噪声图像中小结构的改进方法
提出了一种用于对 1 像素图像片段进行操作的分类器。基于使用直方图计算的后验概率执行元素分割成对象和背景。仿真实验表明,所开发的算法提供了比基于第一类和第二类误差加权和的最小条件确定的亮度阈值的分割更准确的分类。