期刊文献+

彩色图像最优拼接线的改进算法研究 被引量:5

Improved optimal stitching line applied to image stitching
下载PDF
导出
摘要 讨论了彩色图像的精确拼接问题,针对拼接时重叠区域和拼接线附近出现的模糊、错位、穿越等问题,提出了根据待拼接图像重叠区域像素点邻域内的颜色和纹理作为特征的能量计算公式,并提出树形搜索方向的动态寻找最优拼接线算法。实验部分将提出的算法与其他方法进行了对比,结果表明,该方法不仅可以很好地克服掉上述"鬼影"问题,解决寻找拼接线时出现的穿越现象,也可以最大限度地实现拼接线两侧图像间的过渡连续。 This paper discusses the image stitching. Due to the problems that overlapping area becomes fuzzy or dislocated when stitching the images, a new energy calculation formula whose characteristics is based on pixel’s color and texture which belongs to the neighborhood pixels in image overlap area is put forward. And an algorithm of dynamically searching the direction to find the optimal stitching line is put forward. The experiment section includes comparisons between this method and others. The result demonstrates that this method can not only overcome the problem of“ghosting”, but also achieve the transition between both sides of the stitching line naturally.
作者 孙培双 韩其睿 SUN Peishuang;HAN Qirui(School of Computer Science & Software Engineering, Tianjin Polytechnic University, Tianjin 300387, China)
出处 《计算机工程与应用》 CSCD 北大核心 2016年第21期218-221,234,共5页 Computer Engineering and Applications
基金 国家自然科学基金(No.51378350)
关键词 图像拼接 能量计算 最优拼接线 动态规划 image stitching energy calculation best stitching line dynamic programming
  • 相关文献

参考文献4

二级参考文献37

  • 1徐成华,王蕴红,谭铁牛.三维人脸建模与应用[J].中国图象图形学报(A辑),2004,9(8):893-903. 被引量:42
  • 2王建忠,肖绍良.图像镶嵌及其边界处理[J].模式识别与人工智能,1993,6(3):189-195. 被引量:20
  • 3李晓明,郑链,胡占义.基于SIFT特征的遥感影像自动配准[J].遥感学报,2006,10(6):885-892. 被引量:153
  • 4魏文忠.多光谱图像融合中配准技术的研究及小波应用.北京理工大学硕士论文[M].,1995..
  • 5SCHMID M.A performance evaluation of local descriptors[J].IEEE Trans.On pattern Analysis and Machine intelligence,2005,27 (10):1615-1630.
  • 6EI RUBE I A,SHARRS.M A,SALEM A R.,et al.Image registration based on multi-scale SIFT for remote sensing images[J].Signal Processing and Communication Systems,3rd International Conference on 2009(9):28-30.
  • 7DA CUNHA A L,ZHOU J P,DO M N.The nonsubsampled eontourlet transform:theory,design,and applications[J].IEEE Trans.on Image Processing,2006,15(10):3089-3101.
  • 8DO M N VETIERLI M.The eontourlet transform:an efficient directional multi-resolution image representation[J].IEEE Trans.on Image Processing,2005,14(12):2091-2106.
  • 9SHENSA M J.The discrete wavelet transform:Wedding the à trons and Mallat algorithms[J].IEEE Trans.On Signal Processing.1992,40(10):2464-2482.
  • 10LOWE D G.Distinctive image features from scale-invariant keyPoints[J].International Journal on Computer Vision,2004,60(2):91-110.

共引文献71

同被引文献30

引证文献5

二级引证文献27

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部