三维光学模型的激光图像边缘检测研究  

Research on laser image edge detection of 3D optical model

作　　者：肖建英 邓强 XIAO Jianying;DENG Qiang(Network and information service center of Mianyang City College,Mianyang Sichuan 621000,China)

机构地区：[1]绵阳城市学院网络与信息服务中心,四川绵阳621000

出　　处：《激光杂志》2023年第8期110-114,共5页Laser Journal

基　　金：教育部产学研协同育人项目(No.202102146011)。

摘　　要：常规方法对激光图像进行边缘检测时,边缘检测会发生模糊,影响激光图像中心点的定位精度,为此设计基于三维光学模型的激光图像边缘检测方法。通过三维光学模型获取激光图像内部参数,分析激光粒子跃迁的能量变化过程,将图像分解过程用维矩阵模型进行表示,使用Gabor滤波器对激光图像进行滤波预处理,利用卷积神经网络完成采样运算,对比结果判定像素点是否为边缘点,完成检测。测试结果表明:本方法图像检测边缘检测得到的图像中心点定位横纵距离偏差都在0.1 mm以下,检测精度高于90%,检测时间低于1.25 s,验证了方法的有效性。When the conventional method is used to detect the edge of the laser image,the edge detection will be blurred,which will affect the positioning accuracy of the center point of the laser image.Therefore,a laser image edge detection method based on a three-dimensional optical model is designed.The internal parameters of the laser image are obtained through the three-dimensional optical model,the energy change process of the laser particle transition is analyzed,the image decomposition process is represented by a dimensional matrix model,the Gabor filter is used to fil-ter the laser image,and the convolutional neural network is used to complete the sampling operation.,compare the re-sults to determine whether the pixel is an edge point,and complete the detection.The test results show that the hori-zontal and vertical distance deviation of the image center point positioning obtained by the image detection edge detec-tion method in this paper is less than 0.1 mm,the detection accuracy is higher than 90%,and the detection time is less than 1.25 s,which verifies the effectiveness of the method.

关 键 词：三维光学模型 激光图像 图像中心 光源距离 边缘检测 

分 类 号：TN958[电子电信—信号与信息处理]