应用经典限幅滤波算法(CFA)对边缘去噪处理时容易造成有效的高频边缘被抑制、破坏边缘连续性、丢失目标结构特征的问题。提出了一种基于局部结构形态特征的改进型限幅滤波算法,用于图像边缘滤波处理。该算法利用限幅滤波的原理,引入由5个相邻边缘点构成的滑动模子并遍历边缘各点,对滑动模子中增量超限的点加以结构形态预测和阈值判断,即通过滑动模子建立局部轮廓的结构形态模型,并应用模型进行边缘预测;对超限点与预测值的差异进行了比较,为判定是否遇到台阶、凸缘或尖锐的结构特征提供了依据。为了测试新算法在边缘保持和滤波降噪方面的能力,与传统限幅滤波算法进行了对比实验。实验结果表明:基于局部结构形态特征的改进限幅滤波算法不但具有高效的去噪能力,而且对目标结构中的高频边缘具有显著保护作用。
Abstract
It is easy to cause the problem that the high frequency edges are suppressed, the continuity of the edges is destroyed and the structural features of the target are lost when the classical clipping and filtering algorithm(CFA) is applied to the edge denoising. Therefore, an improved CFA based on local structure shape features is proposed for image edge filtering. Based on the principle of CFA, a sliding template composed of 5 adjacent edge points and sliding along the edge is used in the algorithm. The point that overruns the threshold in the sliding template is predicted by the local structural shape model. To be specific, the model of the local structural contour is established by using the sliding template and applied to predict the overrun point. Then, it is judged that whether the difference between the overrun point and its predicted value is greater than the threshold, in the physical sense it means that whether the step, flange or sharp structural features are encountered. In order to test the ability of the new algorithm in edge preservation and noise reduction, comparative experiments with the traditional algorithmare carried out. The experimental results show that the improved CFA based on local structure features not only has efficient denoising ability, but also has significant protection effect on the high-frequency edge of the target structure.
关键词
计量学 /
图像边缘滤波 /
限幅滤波算法 /
局部结构形态 /
机器视觉
Key words
metrology /
image edge filtering /
clipping and filtering algorithm /
local structure shape /
machine vision
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
［1］ 邢雪亮, 甘文波, 蒋朝根. 基于机器视觉的航空铆钉尺寸检测技术［J］. 计量学报, 2020, 41(5): 518-523.
Xing X L, Gan W B, Jiang C G. Technology of Size Detection of Air Rivets Basedon Machine Vision［J］. Acta Metrologica Sinica, 2020, 41(5): 518-523.
［2］ 吴凤和. 基于计算机视觉测量技术的图像轮廓提取方法研究［J］. 计量学报, 2007, 28(1): 18-22.
Wu F H. A Studyon Contour Extraction Methodin Computer Vision Measurement Technology［J］. Acta Metrologica Sinica, 2007, 28(1): 18-22.
［3］ 冯芙蓉, 张兆功. 目标轮廓检测技术新进展［J］. 计算机科学, 2021, 48(z1): 1-9.
Feng F R, Zhang Z G. Recent Advances for Object Contour Detection Technology［J］. Computer Science, 2021, 48(z1): 1-9.
［4］ 张红霞, 王灿, 刘鑫, 等. 图像边缘检测算法研究新进展［J］. 计算机工程与应用, 2018, 54(14): 11-18.
Zhang H X, Wang C, Liu X, et al. Image edge detection algorithm and its new development［J］. Computer Engineering and Applications, 2018, 54(14): 11-18.
［5］ 曾建华, 黄时杰. 典型图像边缘检测算子的比较与分析［J］. 河北师范大学学报(自然科学版), 2020, 44(4): 295-301.
Zeng J H, Huang S J. Comparison and Analysis on Typical Image Edge Detection Operators［J］. Journal of Hebei Normal University(Natural Science), 2020, 44(4): 295-301.
［6］ 李静, 陈桂芬, 丁小奇. 基于改进Canny算法的图像边缘检测方法研究［J］. 计算机仿真, 2021, 38(4): 371-375.
LiJ, Chen G F, Ding X Q. Research on image edge detection method based on improved canny algorithm［J］. Computer Simulation, 2021, 38(4): 371-375.
［7］ 张梦, 张小美, 黄颖辉. 一种改进的形态学边缘检测算法［J］. 广西科技大学学报, 2021, 32(2): 72-77.
Zhang M, Zhang X M, Huang Y H. An improved morphological edge detection algorithm［J］. Journal of Guangxi University of Science and Technology, 2021, 32(2): 72-77.
［8］ 张世辉, 张红桥, 韩德伟. 结合表观、运动和边缘结构信息的遮挡边界检测方法［J］. 计量学报, 2016, 37(3): 241-245.
Zhang S H, Zhang H Q, Han D W. Occlusion Boundary Detection by Combining Appearance, Motion and Edge Structure Cues in Video［J］. Acta Metrologica Sinica, 2016, 37(3): 241-245.
［9］ 熊珍珍, 叶发茂. 基于特征值的阳性选择的图像边缘检测算法［J］. 科技通报, 2017, 33(11): 182-185.
Xiong Z Z, Ye F M. Image edge detection algorithm based on positive selection of eigenvalue set［J］. Bulletin of Science and Technology, 2017, 33(11): 182-185.
［10］ 童胜杰, 江明, 焦传佳. 一种改进工件边缘检测方法的研究［J］. 电子测量与仪器学报, 2021, 35(1): 128-134.
Tong S J, Jiang M, Jiao C J. Research on an improved edge detection method of work piece［J］. Journal of Electronic Measurement and Instrumentation, 2021, 35(1): 128-134.
［11］ 沈德海, 鄂旭, 张龙昌. 一种抑制脉冲噪声的边缘检测算法［J］. 电子设计工程, 2015, 23(9): 93-96.
Shen D H, E X, Zhang L C. An edge detection algorithm of suppression impulse noise［J］. Electronic Design Engineering, 2015, 23(9): 93-96.
［12］ 康宇, 赵冬青, 上官鹏, 等. 基于FPGA的图像边缘保护高斯滤波算法实现［J］. 电子设计工程, 2021, 29(6): 94-98,110.
KangY, Zhao D Q, Shangguan P. Realization of image edge protection Gauss filter algorithm based on FPGA［J］. Electronic Design Engineering, 2021, 29(6): 94-98,110.
［13］ 杨花雨, 詹华蕊. 基于中值滤波技术的视频图像边缘检测算法［J］. 科学技术与工程, 2019, 19(9): 143-147.
Yang H Y, Zhan H R. Edge detection algorithm of video image based on median filter technology［J］. Science Technology and Engineering, 2019, 19(9): 143-147.
［14］ 刘高生, 马小三, 王培珍. 基于改进的中值滤波和数学形态学的图像边缘检测［J］. 计算机与现代化, 2011(8): 57-59,63.
Liu G S, MA X S, Wang P Z. A new edge detection algorithm based on improved median filter and mathematical morphology［J］. Computer and Modernization, 2011(8): 57-59,63.
［15］ 石晓红, 黄钦开, 苗佳欣, 等. 基于卷积网络的边缘保持滤波方法［J］. 计算机科学, 2019, 46(9): 277-283.
Shi X H, Huang Q K, Miao J X, et al. Edge-preserving filtering method based on convolutional neural networks［J］. Computer Science, 2019, 46(9): 277-283.
［16］ 蔡永洪. 基于限幅滤波的图像边缘去噪方法及装置、设备: 202110644007. 7［P］. 2021-6-10.
［17］ 杨高科. 图像处理、分析与机器视觉基于LabVIEW［M］. 北京: 清华大学出版社, 2018.
［18］ 张世辉, 张笑维,李贺,等. 结合多尺度及密集特征图融合的阴影检测方法［J］. 计量学报, 2021, 42(5): 570-576.
Zhang S H, Zhang X W, Li H, et al. Shadow Detection Method Combining Multi-Scale and Dense Feature Map Fusion［J］. Acta Metrologica Sinica, 2021, 42(5): 570-576.
基金
广东省市场监督管理局科技计划项目2020CJ02; 广东省教育厅2020年省高职教育教学改革研究与实践项目高职扩招专项JGGZKZ2020114
PDF(1235 KB)
