Open AccessMETHODS OF TARGET RECOGNITION BASED ON CENTRAL IMAGE CHORD TRANSFORMATION
Author(s) -
Veaceslav Perju,
AUTHOR_ID
Publication year - 2021
Publication title -
journal of engineering science
Language(s) - English
Resource type - Journals
eISSN - 2587-3482
pISSN - 2587-3474
DOI - 10.52326/jes.utm.2021.28(4).05
Subject(s) - normalization (sociology) , artificial intelligence , computer science , pattern recognition (psychology) , chord (peer to peer) , transformation (genetics) , computer vision , invariant (physics) , logarithm , automatic target recognition , mathematics , mathematical analysis , distributed computing , biochemistry , chemistry , sociology , anthropology , mathematical physics , gene , synthetic aperture radar
In the article the analysis of different approaches to invariant target recognition was made, such as based on the support vector machines, deep learning techniques, neural networks, generation of moment features, etc. It was determined that one of the perspectives approaches in target recognition suppose the use of the central and logarithmic central image chords transformations. There have been described the new methods of the target recognition, based on the central image chords transformation. Tasks of target recognition were formulated. New 4 methods of target recognition were described. It is presented the comparison of the different target’s recognition methods regarding the processing stages number, realized operations, target’s image normalization’s operation, the operations realized in parallel, kind of the target’s scale and rotation determination sequence, target’s rotation determination approach.