摘要
根据干涉条纹区域的特征,对比了多种常规的边缘检测方法,提出了一种基于二阶梯度熵函数的散斑干涉条纹区域自动提取的判定函数,并通过分析不同的散斑干涉条纹图片,确定了最佳的检验子区熵的尺寸区间以及不同干涉条纹图中的自适应阈值区间,最终通过连通区域分割完成对条纹区域的自动提取。对所提方法进行实验验证,结果表明:子区熵尺寸取15 pixel以上时,图片熵值的计算更准确;自适应阈值在[0,Qmax-1.25]中取值时(Qmax为图中最大梯度熵值),可以将干涉条纹区域与散斑背景区域有效分割,实现对散斑干涉条纹区域的自动提取。
According to the characteristics of interference fringe region and compared with many conventional edge detection methods, a judgment function is proposed for the automatic extraction of speckle interference fringe regions based on second-order gradient entropy functions. By analyzing different speckle interference fringe images, an optimum entropy size interval of a test sub-region and adaptive threshold intervals of different interference fringe patterns are determined. The automatic extraction of the stripe region is finally completed through connected region segmentation. The method is validated experimentally. Experimental results show that more accurate image entropy is obtained when the size of sub-region entropy is above 15 pixel. The fringe region and speckle background region can be segmented accurately when the adaptive threshold is within a range of 0 to Qmax-1.25, where Qmax is the maximum gradient entropy in the image, thereby achieving automatic extraction of the speckle interference fringe region.
作者
吴双乐
胡慧然
钟诗民
孙方圆
赵琪涵
王永红
Wu Shuangle;Hu H uiran;Zhong Shimin;Sun Fang yuan;Zhao Qihan;Wang Yonghong(School of Instrument Science and Opto-Electronics Engineering,Hefei University of Technology,Hefei,Anhui 230009,China)
出处
《光学学报》
EI
CAS
CSCD
北大核心
2019年第12期169-177,共9页
Acta Optica Sinica
基金
国家重点研发计划(2016YFF0101803)
国家自然科学基金(51805137)
安徽自然科学基金(1808085QE129)
关键词
测量
散斑干涉
干涉条纹区域
二阶梯度熵
自适应阈值
measurement
speckle interferometry
interference fringe region
second-order gradient entropy
adaptive threshold
