Change detection methods for distinction task of stochastic textures based on nonparametric method

Albert Kh. Sultanov

doi:10.1117/12.2234419

26 March 2016 Change detection methods for distinction task of stochastic textures based on nonparametric method

Albert Kh. Sultanov

Proceedings Volume 9807, Optical Technologies for Telecommunications 2015; 98070W (2016) https://doi.org/10.1117/12.2234419
Event: XIII International Scientific and Technical Conference on Optical Technologies in Telecommunications, 2015, Ufa, Russian Federation

Abstract

The following article describes use of nonparametric method. This method is to be used to find multivariate change of random processes for image processing. It is aimed to find the borders of irregular phenomena in front of terrain. The current task of finding change and evaluation of a change point in consequent setting proposes test statistics based on value of sampling characteristic functions. The relevant criterion in a wide range of alternatives has a predetermined assessment of the asymptotic significance level. Current work also proposes an algorithm of texture segmentation for two-dimensional case. This algorithm is given as a consequence of processing operations in columns and rows of test statistics values, obtained during scanning of images. The test results are quoted.

Citation Download Citation

Albert Kh. Sultanov "Change detection methods for distinction task of stochastic textures based on nonparametric method", Proc. SPIE 9807, Optical Technologies for Telecommunications 2015, 98070W (26 March 2016); https://doi.org/10.1117/12.2234419

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available