基于灰度相关图像拼接的改进算法  

An improved mosaic algorithm of panoramic images using gray correlation

作　　者：胡社教[1] 涂桂林[1] 江萍[2] 

机构地区：[1]合肥工业大学计算机与信息学院,安徽合肥230009 [2]合肥工业大学电气与自动化工程学院,安徽合肥230009

出　　处：《合肥工业大学学报（自然科学版）》2008年第6期863-865,共3页Journal of Hefei University of Technology：Natural Science

摘　　要：结合灰度相关与区域特征,文章提出了一种基于灰度相关图像拼接的改进算法。为减少匹配块的计算量,首先在选取的特征块上计算灰度平均值和每个像素与平均值的差值,然后选取一定的阈值来减小图像的搜索范围,最后利用灰度相关法匹配待拼接两幅图像。实验表明,该方法具有原理简单、速度增快和鲁棒性好的特点。On the basis of gray correlation and area characters, an improved algorithm for image mosaic based on gray correlation is presented in this paper. In order to reduce the calculation, the average gray values and the disparity between each pixel and the average values in the selected feature blocks are first computed, and then a threshold is chosen to reduce the search scope. And last the two images are matched through the gray correlation algorithm. The experiments show that the method is simple and fast-speed and has better robustness.

关 键 词：图像拼接 特征块 灰度相关 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]