Pattern recognition of 1D- and 2D-images for arbitrary scale of spatial coordinates
DOI:
https://doi.org/10.20535/RADAP.2015.60.25-33Keywords:
normalization, normal orthogonal transformation, pattern recognition, transform coefficient, Mellin transformAbstract
Introduction. Possible methods of pattern recognition are described. Transform coefficient, allowing numerically to evaluate the difference between the test and reference signal is proposed. In this case, the reference signal is selected by researcher independently, which gives more freedom. Theoretical positions. The possibility ofMellin transform using for pattern classification of images based on their normalization or normalized transformation when scale of studied images is differ from a reference image, is considered. A similar ofFourier and Mellin transforms is proved. Classification algorithm. Proposed algorithm can be used when change of scale arguments of the signals is presented. This algorithm has a clear structure that allows implement it in hardware with minimal effort. Examples. Examples of the Mellin transform using for different distortion types of the test signal are considered. The test signals have time scale and distorted form changing. The obtained sensitivity value of classifier to parameters changes of the investigated image with respect to the reference image was sufficient to get a stable work of this unit. Conclusions. The main advantages of the Mellin transform using for recognizing signals at different scales are presented in conclusions.Downloads
Published
2015-03-30
Issue
Section
Computing methods in radio electronics
License
Copyright (c) 2020 S. M. Litvintsev, I. O. Sushko, Ye. V. Vistyzenko, A. I. Rybin
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).