基于冗余小波变换的相对模糊连通图像交互式分割算法  

Relative Fuzzy Connected Interactive Image Segmentation Algorithm Based on Redundant Wavelet Transform

作　　者：田春娜[1] 高新波[1] 

机构地区：[1]西安电子科技大学电子工程学院,西安710071

出　　处：《电子与信息学报》2006年第12期2287-2291,共5页Journal of Electronics & Information Technology

基　　金：国家自然科学基金(60202004);教育部重点项目(104173);新世纪优秀人才支持计划资助课题

摘　　要：为了提高图像分割算法的抗噪声性能,该文提出一种基于冗余小波变换的相对模糊连通图像交互式分割算法。与文献中基于尺度的相对模糊连通交互式分割算法相比,新算法在几乎不改变分割效果的前提下,速度提高了十几倍,且对不同的噪声模型均具有较好的鲁棒性。此外,文中还对小波变换的不同尺度对图像分割效果的影响进行了较为系统地研究。用人造图像和实际的医学图像所做的测试实验结果表明,该文提出的新算法可实现对非噪声和噪声图像中感兴趣目标的快速而准确的分割。To improve the performance of the image segmentation algorithm, a relative fuzzy connected interactive segmentation algorithm is presented based on Redundant Wavelet Transform （RWT）. In comparison with the original scale-based algorithm, the proposed one, with almost the same accuracy, accelerates the segmentation speed by tens times. And it is insensitive to different noise models. In addition, a study of the influence of different redundant wavelet decomposition scales is also included. The experimental results illustrate that the proposed algorithm can obtain the object regions of interest from medical as well as man-made noisy images quickly and reliably with only a little interaction.

关 键 词：冗余小波变换 交互式图像分割 模糊连通度 快速算法 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]