Filter designing for image processing based on multidimensional linear extrapolation

Valery Kh. Bagmanov; Airat R. Zainullin; Ivan K. Meshkov; Albert Kh. Sultanov

doi:10.1117/12.2054871

4 April 2014 Filter designing for image processing based on multidimensional linear extrapolation

Valery Kh. Bagmanov, Airat R. Zainullin, Ivan K. Meshkov, Albert Kh. Sultanov

Proceedings Volume 9156, Optical Technologies for Telecommunications 2013; 91560I (2014) https://doi.org/10.1117/12.2054871
Event: Optical Technologies for Telecommunications 2013, 2013, Samara, Russian Federation

Abstract

This article is proposed to develop a method of the synthesis of the prediction filter based on the multidimensional linear extrapolation to improve the accuracy of the pixel value prediction, as well as to assess the effectiveness of the proposed predictive filters depending on the prediction step and the dimension of training vectors to minimize the prediction error and the entropy of the differential signal. The article contain a solution of the special cases for a number of elements of the vector prediction, statistical dependence of the vector dimension and prediction filter order from the mean square error and the entropy of the differential signal are determined. Optimal prediction step is founded based on the experimental data and all the results are being analyzed.

Citation Download Citation

Valery Kh. Bagmanov, Airat R. Zainullin, Ivan K. Meshkov, and Albert Kh. Sultanov "Filter designing for image processing based on multidimensional linear extrapolation", Proc. SPIE 9156, Optical Technologies for Telecommunications 2013, 91560I (4 April 2014); https://doi.org/10.1117/12.2054871

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