基于SIFT特征匹配的图像拼接算法  

Image Mosaic Algorithm Based on SIFT Feature Matching

作　　者：廖飞[1] 叶玮琼[1] 王鹏程[1] 吴金津[1] 许可可[1] 

机构地区：[1]湖南工业大学计算机与通信学院,湖南株洲412007

出　　处：《湖南工业大学学报》2014年第1期71-75,共5页Journal of Hunan University of Technology

摘　　要：针对传统图像拼接算法效率低和鲁棒性差的问题,提出一种改进的基于SIFT特征匹配的图像拼接算法。在图像预处理阶段,首次运用离散余弦变换、量化、反离散余弦变换、反量化,来对图像增强。其次,在计算变换模型时,由于没有预检验策略,致使RANSAC算法迭代次数增加。为此,提出了预检验策略。实验结果表明,在不改变匹配精度的前提下,该改进算法得到了比较理想的效果。In order to solve the problem of low efficiency and poor robustness of traditional image mosaic algorithm, an improved SIFT-based feature matching algorithm for image stitching were put forward. Firstly enhanced the images by using the discrete cosine transform,quantization, inverse discrete cosine transform and inverse quantization in the image preprocessing stage, and then proposed the pre-inspection strategy in view of the RANSAC algorithm iteration increasing when computing the transformation models. The experimental results showed that the improved algorithm obtained the quite ideal effect without changing the matching precision.

关 键 词：图像拼接 离散余弦变换 RANSAC算法 SIFT算法 

分 类 号：TP317.4[自动化与计算机技术—计算机软件与理论]