Please use this identifier to cite or link to this item:
|Title:||Methodology of Correlation Analysis in Solution of a Problem of Normalization of Projective Image Transformations|
|Citation:||Lyashenko V., Lyubchenko V., Mohammad A., Kobylin O. Methodology of Correlation Analysis in Solution of a Problem of Normalization of Projective Image Transformations // International Journal of Scientific & Engineering Research. – 2015. – Vol. 6(9). – P. 249-255.|
|Abstract:||Processing and interpretation of images is one of composing systems of the intellectual analysis of data. It is caused by that the significant part of information about outward things can be received on the basis of the video data analysis about images of the real world. At that, such analysis uses various methods, approaches and theories where the special place is occupied by the procedures connected with recognition of scenes or separate objects, presented on incoming images. Thus, it is necessary to consider the fact, that incoming images owing to objective factors could be subject to various geometrical distortions. Such distortions impose the restrictions and features on possibility of application of separate approaches and methods to processing and interpretation of images. Hence, a procedure of correlation normalization of images which allows to compare and recognize images is considered in this work. The work proves the possibility of representation of projective group of transformations, as one of versions of geometrical distortions of the incoming image, in the form of composition of the basic, simple transformations which are also versions of geometrical distortions of the incoming image. At the same time, the expediency of application of a partial correlation method for realization of procedure of correlation normalization of images is considered. The formalized description of the offered procedure of correlation normalization of images is given. Examples of separate steps of realization of the offered procedure are resulted.|
|Appears in Collections:||Кафедра інформатики (ІНФ)|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.