一种改进的基于小波方向对比度的无缝拼接算法  

An improved seamless image stitching algorithm based on wavelet direction contrast

作　　者：李涛[1] 陈卫东[1] 李良福[1] 

机构地区：[1]西安应用光学研究所,陕西西安710065

出　　处：《应用光学》2009年第3期437-441,共5页Journal of Applied Optics

摘　　要：为了提高图像无缝拼接效果,对现有平滑算法进行分析,在此基础上提出一种基于小波方向对比度的中缝平滑算法。该算法首先对源图像进行基于统计参数的预处理,使得图像整体亮度趋于一致,然后利用小波变换对图像进行多分辨率分解,对于分解后的图像提出采用一种基于改进的小波方向对比度的规则进行平滑处理。文中还通过几种图像客观评价标准对仿真结果进行了评价,结果表明:该方法在两图像灰度相差较大时也能够取得较好的平滑效果,对光照具有鲁棒性,并且平滑后的图像可以保留原始图像的细节信息,使得图像在保证清晰度的前提下达到无缝拼接。The smoothing of images is a very important step in the stitching process of images. An improved seamless image stitching algorithm based on the wavelet direction contrast is presented by the analysis of some available smoothing, algorithms. The improved algorithm makes the luminance of the two images same first, then the multi-resolution decomposition of the two images is implemented by using wavelet transformation and the images are smoothed by an improved wavelet direction contrast algorithm. The simulation results were assessed with some objective evaluation standards. The results show that this algorithm can make two images smoothly in despite of a great gray difference between the two images. Therefore, it is independent of the ambient light and can make the details of images clear.

关 键 词：无缝拼接 图像平滑 统计参数 小波方向对比度 

分 类 号：TN911.78[电子电信—通信与信息系统]