基于机器视觉的药品包装滤波算法实现  

Filtering Algorithm for Pharmaceutical Packaging based on Machine Vision

作　　者：刘志强[1] 孙怀远 宋晓康 LILT Zhi-qiang1, SUN Huai-yuan2., SONG Xiao-kang1(1. School of Medical instrument, University of Shanghai for Science and Technology, Shanghai 200093, China; 2. School of Medical Instrumentation, Shanghai University of Medicine and Health Sciences 201318, China)

机构地区：[1]上海理工大学医疗器械与食品学院,上海200093 [2]上海健康医学院医疗器械学院,上海201318

出　　处：《软件》2018年第9期93-96,共4页Software

摘　　要：为了有效地滤除泡罩药品包装视觉检测系统中的图像噪声,本文采用了一种结合高斯滤波器的导向滤波去噪方法。首先是分析了导向滤波的数学模型,利用高斯滤波器对含噪声的原始图像进行预去噪,然后再由得到的图像作为输入图像,原始图像进行灰度化处理后作为导向图像,最后进行导向滤波的去噪处理。同时与经典的滤波算法(均值滤波、中值滤波、双边滤波)进行实验对比分析,实验结果表明,改进的导向滤波能够滤除图像中的噪声,同时能很好地保留原始图像细节信息和边缘部分,对后续的图像处理具有一定的价值。In order to effectively filter the image noise in the visual inspection system of blister medicine packaging, this paper uses a Gaussian filter-based guided filtering denoising method. Firstly, the mathematical model of guided filtering is analyzed. The Gaussian filter is used to pre-noise the noise-containing original image, and then the resulting image is used as the input image. After the original image is grayed, it is used as a guide image, and finally guided. Filtered noise reduction. At the same time, the experiments were compared with the classical filtering algorithms （mean filter, median filter, and bilateral filter）. Experimental results show that the improved steerable filter can filter out the noise in the image while retaining the original image details and edges. In part, it has a certain value for the subsequent image processing.

关 键 词：图像处理 导向滤波 泡罩药品包装 视觉检测系统 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]