基于3次B样条小波变换和改进自适应阈值的边缘检测算法  

A New Edge Detection Algorithm Based on 3-B-Spline Wavelet Transform and an Improved Adaptive Threshold

作　　者：徐靖 王煜 豆帅 王元勋[3] 

机构地区：[1]航宇救生装备有限公司,湖北襄阳 [2]武汉航空仪表有限责任公司,湖北武汉 [3]华中科技大学,湖北武汉

出　　处：《计算机科学与应用》2017年第3期225-231,共7页Computer Science and Application

基　　金：国家自然科学基金资助项目(11072083)。

摘　　要：针对含噪声图像边缘提取问题,本文将边缘提取与图像去噪结合起来,提出了一种改进NormalShrink自适应阈值去噪算法。该算法首先通过3次B样条小波变换和局部模极大值法提取出可能包含图像边缘特征的小波系数,考虑边缘像素之间特殊的空间关系以及噪声在各级小波分解尺度下的不同效应,构建适合各个尺度级的改进Normalshrink自适应阈值,并依此对提取出的小波系数进行筛选。试验结果表明,与Candy算子和传统的Normalshrink自适应阈值相比,本文方法提取出的图像边缘较为完整清晰,峰值信噪比提升约3 db。In order to solve the problem of noisy image edge detection, an improved NormalShrink adaptive wavelet threshold is put forward on the foundation of combining edge detection and denoising. According to the different characteristics of noise at different wavelet scales and the special spatial relationship between the edge pixels, the algorithm first extracts wavelet coefficients which may contain image edge feature by using 3-B-spline wavelet transform and local maximum mode, and then constructs an improved Normalshrink adaptive threshold of each scale level which is used to select the extracted wavelet coefficients. Experimental results show that this method can keep image’s edges clear and increase PSNR about 3 db.

关 键 词：边缘提取 小波变换 自适应阈值 峰值信噪比 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]