光图像亚像素边缘高精度自适应检测研究  

High precision adaptive detection of sub-pixel edge of laser image

作　　者：陈黎艳[1] 熊强强[1] CHEN Liyan;XIONG Qiangqiang(Nanchang Institute of Technology,Nanchang 330013,China)

机构地区：[1]南昌理工学院,南昌330013

出　　处：《激光杂志》2020年第11期86-90,共5页Laser Journal

基　　金：江西省高等学校教学改革研究项目(No.JXJG-17-25-10);江西省文化艺术科学规划项目(No.GY245)。

摘　　要：由于激光图像亚像素边缘易出现薄弱现象且边缘位置模糊,导致边缘检测速度以及精度下降,提出激光图像亚像素边缘高精度自适应检测研究。通过小波模极大原理对图像进行粗定位,获取亚像素边缘点位置,结合Zermike矩算法对边缘进行亚像素定位,结合最大类熵阈值方法计算对应的阈值,通过人工对阈值进行反复调整,设定低阈值和自适应阈值来保护图像弱边缘和提取真正边缘,完成激光图像亚像素边缘自适应检测。相关实验结果表明,检测图像图像包含的边缘信息较多,且对于噪声的抑制效果较好,检测信噪比较高,检测时间在1s左右,检测效率在90%以上。Due to the weakness of sub-pixel edge of laser image and the fuzzy edge position,the speed and accuracy of edge detection are reduced.Based on the principle of wavelet modulus maxima,the image is roughly located to obtain the position of edge points,and the Zermike moment algorithm is used to locate the edge sub-pixel,and the maximum entropy threshold method is used to calculate the corresponding threshold value.Through manual adjustment of the threshold value repeatedly,the low threshold value and the adaptive threshold value are set to protect the weak edge of the image and extract the real edge,and the laser image sub-pixel edge self-adaptive test is completed.Correlation experiment results show that the detection image contains more edge information,and the suppression effect of noise is better,the detection signal-to-noise ratio is higher,the detection time is about 1 s,and the detection efficiency is more than 90%.

关 键 词：多阈值 激光图像 亚像素 边缘位置 自适应检测 

分 类 号：TN386[电子电信—物理电子学]