Estimation of parameters of geometric transformation of images by fixed-point method

被引:0
作者
V. R. Krasheninnikov
M. A. Potapov
机构
[1] Ul’yanovsk State Technical University,
关键词
image; geometric transformation; estimation; parameters; fixed point; pseudo-gradient algorithms; parallel shift; auxiliary transformation; straight line; scaling; square of the gradient; Laplacian; numerical solution; binary; correlation coefficient; threshold; sample variances; covariance;
D O I
10.1134/S105466181202006X
中图分类号
学科分类号
摘要
In solving many practical problems, the problem of combining images and the closely related problem of binding a portion of the image often arises. If the model of mutual interframe geometric transformation (GT) of two images is given, then the problem of combination is reduced to estimating the parameters of this model. There is a large number of works dedicated to the development of algorithms for estimating the parameters of GT; in particular, pseudo-gradient algorithms have been well developed [3]. However, for the success of these (and many other) algorithms, a fairly accurate initial approximation of parameters of GT is required. Otherwise, one must take a set of initial approximations. Thus, it becomes necessary to make a rough estimate of the parameters of GT, which can be taken as an initial approximation for more accurate algorithms. In this paper, the method of rough estimation of the parameters of GT, which uses the notion of the fixed point, is proposed.
引用
收藏
页码:303 / 317
页数:14
相关论文
共 3 条
  • [1] Pyt’ev Yu. P.(1983)Morphological Analysis of Images Dokl. Akad. Nauk SSSR 269 1061-1064
  • [2] Krasheninnikov V. R.(2010)Estimating Parameters of Interframe Geometric Transformation of an Image Sequence by the Fixed Point Method Pattern Recogn. Image Anal. 20 316-323
  • [3] Potapov M. A.(undefined)undefined undefined undefined undefined-undefined