Abstract
This paper considers the question of the use of the complete sliding control function when solving the problem of automatic construction of the local processing procedure of image signals adjusted using empirical data (hierarchical regression). A technique to halt the process of forming various combinations of training and control samples and, hence, the process of constructing the image processing procedure is proposed and based on an interval estimate of the functional of sliding quality control.
Similar content being viewed by others
References
V. N. Vapnikand A. V. Chervonenkis, Pattern Recognition Theory (Nauka, Moscow, 1974) [in Russian].
K. V. Vorontsov, “Combination approach for estimating training algorithms quality,” in Mathematical Problems of Cybernetics, Ed. by O. B. Lupanov (Fizmatlit, Moscow, 2004), Vol. 13, pp. 5–36 [in Russian].
R. C. Gonzalez and R. E. Woods, Digital Image Processing (New Jersey, Prentice Hall, 2002).
V. N. Kopenkov and V. V. Myasnikov, “Algorithm for generating automatically a procedure for processing local nonlinear image based on hierarchical regression,” Komp’yut. Opt. 36(2), 257–266 (2012).
V. A. Soifer, Methods for Images Computer Procession, 2nd ed. (Fizmatlit, Moscow, 2003) [in Russian].
L. Breiman, J. H. Friedman, R. A. Olshen, and C. J. Stone, Classification and Regression Trees (Wadsworth, Monterey, Calif, 1984).
S. Haykin, Neural Networks: A Comprehensive Foundation (Prentice Hall, 1999).
V. Kopenkov, “Effecient algorithms of local discret wavelet transform with HAAR-like bases,” Pattern Recogn. Image Anal. 18(4), 654–661 (2008).
Author information
Authors and Affiliations
Corresponding author
Additional information
This paper uses the materials of the report submitted at the 11th International Conference “Pattern Recognition and Image Analysis: New Information Technologies,” Samara, The Russian Federation, September, 23–28, 2013.
Vasilii Nikolaevich Kopenkov was born in 1978. He graduated from Samara State Aerospace University in 2001. He received his Candidate of Technical Sciences degree in 2011. At present, he is an associate professor and Geoinformatics and Information Security chair at Samara State Aerospace University and a researcher at the Image Processing Systems Institute, Russian Academy of Sciences. His scientific interests include digital image and signal processing, geoinformatics, pattern recognition, and earth remote sensing data processing. He is the author of 42 publications, including 14 articles. He is a member of the Russian Pattern Recognition and Image Analysis Association.
Rights and permissions
About this article
Cite this article
Kopenkov, V.N. On halting the process of hierarchical regression construction when implementing computational procedures for local image processing. Pattern Recognit. Image Anal. 24, 506–510 (2014). https://doi.org/10.1134/S1054661814040087
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1054661814040087