摘要
医学图像现已成为临床诊断、病理分析及治疗的重要依据和手段,医学图像边缘检测的好坏,会直接影响到后续的治疗过程。分析了基于小波变换和数学形态学的边缘检测算法的不足,提出了一种联合提升小波和形态学的医学图像边缘检测算法。首先对原始图像做提升小波变换,然后采用多方位形态学算子检测边缘,最后进行提升小波反变换。实验结果表明该方法能在有效地去除噪声的同时准确地检测出肺部病灶图像的边缘,是一种有效的医学图像边缘检测方法。
Medical images have already become the important basis of the clinical diagnosis, pathological analysis and treatment. The edge detection results of the medical image whether good or bad will directly affect the subsequent course of treatment. An edge detection algorithm is proposed for the medical image combined lifting wavelet with morphology according to the disadvantage of the wavelet transform and mathematical morphology-based edge detection algorithms. First, lifting wavelet transform is implemented for the original image. And then the multi-directional morphology operators are used to detect edge. Finally, the inverse lifting wavelet transform is implemented. The experimental results show that this approach can denoise effectively and accurately detect the edge of lung lesion image. It is an effective edge detection method for medical image.
出处
《电视技术》
北大核心
2013年第1期28-30,47,共4页
Video Engineering
基金
山西省自然科学基金项目(2010011019-3)
关键词
医学图像
提升小波
数学形态学
边缘检测
medical image
lifting wavelet
mathematical morphology
edge detection
