New approach to image processing based on the methodology of pattern recognition

Vladislav V. Sergeyev

doi:10.1117/12.302491

10 March 1998 New approach to image processing based on the methodology of pattern recognition

Vladislav V. Sergeyev

Proceedings Volume 3348, Optical Information Science and Technology (OIST97): Computer and Holographic Optics and Image Processing; (1998) https://doi.org/10.1117/12.302491
Event: Optical Information Science and Technology, 1997, Moscow, Russian Federation

Abstract

A new approach to local spatially-invariant digital image processing is based on the non-traditionally use of a pattern recognition methodology. Corresponding methods of `processing through recognition' (P/R-methods) include (1) the input image features formation in a sliding 2D window, and (2) the classification of every pixel of output image. In this paper the general schemes of P/R-method training and running are given. Some fast parallel-recursive algorithms of the image features formation in a sliding window are shown. The problems of synthesis of output image pixel classifier are discussed. Results of research of P/R-method with reference to some problems of image processing are described. Advantages of the proposed approach are marked.

Citation Download Citation

Vladislav V. Sergeyev "New approach to image processing based on the methodology of pattern recognition", Proc. SPIE 3348, Optical Information Science and Technology (OIST97): Computer and Holographic Optics and Image Processing, (10 March 1998); https://doi.org/10.1117/12.302491

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