半导体光电, 2019, 40 (1): 129, 网络出版: 2019-03-25  

基于Zernike矩的圆形插针特征点提取算法研究

Research on Feature Point Extraction of Circular Pin Image Based on Zernike Moment
作者单位
北京航空航天大学 仪器科学与光电工程学院, 北京 100191
摘要
在电连接器插针缺陷检测系统中, 插针图像特征点的获取是检测关键, 为了实现插针位置的高精度检测, 提出了一种基于Zernike矩的插针特征点定位算法。通过增大Zernike矩的算子模板尺寸, 以及优化边缘阶跃模型, 提高了亚像素边缘检测算法的精度。将最大熵阈值法应用于Zernike矩边缘检测算法, 实现了自动选择最佳阈值, 解决了传统算法中手动调节阈值的低效率问题。对提取的亚像素边缘点进行拟合获得椭圆目标中心, 实现了插针的位置特征点提取。仿真实验与实际测试结果表明, 该算法能够实现图像边缘的亚像素检测和插针特征点的准确定位, 算法定位误差小于0.1个像素。
Abstract
In the defect detection system for electronic connectors, it is a key point to acquire the feature points of pin images. Thus in order to realize the high accuracy measurment of pin locations, a feature point positioning algorithm based on Zernike moment was proposed. The precision of sub-pixel edge detection algorithm was improved by increasing the size of operator model of Zernike moment and optimizing the edge step model. The maximum entropy threshold method was applied to the Zernike moment edge detection algorithm, which realizes the automatic selection of the optimal threshold and overcomes the disadvantage of the low efficiency of the manual adjusting threshold in traditional algorithms. The simulation image and the actual test result show that the algorithm can realize sub-pixel detection of image edge, accurately identify the feature point of the pin, and the algorithm localization error is less than 0.1pixel.

李慧鹏, 刘缤艳, 魏晓马, 赵庆松. 基于Zernike矩的圆形插针特征点提取算法研究[J]. 半导体光电, 2019, 40(1): 129. LI Huipeng, LIU Binyan, WEI Xiaoma, ZHAO Qingsong. Research on Feature Point Extraction of Circular Pin Image Based on Zernike Moment[J]. Semiconductor Optoelectronics, 2019, 40(1): 129.

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!