Abstract
In the paper, we present new methods and features for identification of visual objects. The features proposed allow to apply the method of potential functions and to train the system on examples. We outline two methods for determination of the position, the angle of rotation, and the size of an object for the subsequent object identification and feature calculation. The methods applied use the input data in the form of the vector description of an image obtained by the vectorization procedure of segment borders.
Similar content being viewed by others
References
A. P. Shcherbakov, “Fast Algorithm for Calculation of Position, Angle of Rotation, and Size of an Object-Pattern on a Two-Dimensional Visual Scene,” Tsifrovaya obrabotka signalov, No. 4, 15–20 (2004).
R. C. Gonzales and R. E. Woods, Digital Images Processing (Prentice-Hall, New Jersey, 2002) 2nd ed.
L. L. Levin, Introduction to the Pattern Recognition Theory (Tomsk, 1982) [in Russian].
M. A. Aizerman, E. I. Braverman, and L. I, Rozonoer, Method of Potential Functions in the Theory of Machine Learning (Nauka, Moscow, 1973) [in Russian].
Author information
Authors and Affiliations
Corresponding author
Additional information
Anatolii P. Shcherbakov. Born 1968. Graduated from the Faculty of Applied Mathematics and Cybernetics of the Tomsk State University in 1992. Received candidate’s degree in 1997. Senior researcher at the Laboratory of Molecular Spectroscopy, Institute of Atmospheric Optics, Siberian Division of the Russian Academy of Sciences. Scientific interests: automatization of analysis of spectrum of molecules, systems of data acquisition from spectral instruments, self-identification of spectra.
Rights and permissions
About this article
Cite this article
Shcherbakov, A.P. Fast identification of two-dimensional visual patterns in arbitrary position. Space of features. Pattern Recognit. Image Anal. 17, 450–456 (2007). https://doi.org/10.1134/S1054661807040025
Received:
Issue Date:
DOI: https://doi.org/10.1134/S1054661807040025