基于改进SIFT的图像拼接算法

摘要

In order to solve the problems of heavy computing load and the inaccurate matching of feature points compared with the traditional image mosaic algorithm based on SIFT, an novel image mosaic algorithm based on improved SIFT is proposed in this paper. The feature points are extracted by improved SIFT, so it can reduce the computing load. Meanwhile, the feature points matching are realized by simulated annealing algorithm, and the geometric parameter is computed. Experimental results demonstrate that the proposed method is robust to translation, rotate, intensity and noise, and can produce high quality image mosaic.%针对目前基于SIFT的图像拼接算法复杂度较高和特征点匹配不准等问题,提出了一种基于改进SIFT的图像拼接算法.算法利用改进的SIFT进行特征提取,降低了算法的复杂度,同时采用模拟退火算法进行特征点匹配,从而估计出几何变换的参数.实验结果表明,该方法对图像间存在的平移、旋转、明暗强度和噪声干扰都具有良好的鲁棒性,可实现高质量的图像拼接.