基于图像邻域滤波和分频处理的边缘检测  

作　　者：王娟 

机构地区：[1]湖北文理学院理工学院,湖北襄阳441025

出　　处：《科技创新与应用》2020年第31期22-23,共2页Technology Innovation and Application

摘　　要：提出了一种新的基于平滑算法和分频优化算法相结合的滤波方法,该算法首先根据图像特征选择七个掩模,计算邻域内七个掩模的均值和方差,选择最小方差所对应的区域的灰度均值代替原来的灰度值,实现图像的平滑;然后将图像分频,分别对高低频信号优化再融合,得到一副新的灰度图像,最后对图像进行边缘检测。实验结果表明,该算法能很好地避免噪声放大,且能保留良好的边缘细节。A new filtering method based on the combination of smoothing algorithm and frequency division optimization algorithm is proposed.Firstly,seven masks are selected according to image features,and the mean and variance of seven masks in the neighborhood are calculated.The gray mean value of the region corresponding to the minimum variance is selected to replace the original gray value,and the image smoothing is realized.Then the image is divided into different frequencies,and the high and low frequency signals are optimized and fused to get a new grayscale image.Finally,the edge of the image is detected.The experimental results show that the algorithm can avoid noise amplification and retain good edge details.

关 键 词：边缘检测 局部平滑 分频优化 抗噪性能 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]