Local anisotropic features method and its application

Igor S. Gibin; Pavel G. Popov

doi:10.1117/12.262630

27 December 1996 Local anisotropic features method and its application

Igor S. Gibin, Pavel G. Popov

Proceedings Volume 2969, Second International Conference on Optical Information Processing; (1996) https://doi.org/10.1117/12.262630
Event: Second International Conference on Optical Information Processing, 1996, St. Petersburg, Russian Federation

Abstract

The local anisotropic features method is based on the analysis of anisotropy direction of energy Fourier spectrum of image points local neighborhood. Numbers of discrete anisotropic directions are chosen as features. In the features space the measure of images nearness is set. Thanks to its properties local anisotropic features (LAF) are invariant to a wide class of input images bright transformations. This allows to identify images got by different observing channels, in different spectral ranges, within different external observation conditions. LAF method allows to perform multifunctional images processing: recognition, tracking, compression of data. LAF method may be adapted practically to any image receiver and used for multichannel information processing: channels complexing and scene integral image synthesis. The advantage of LAF method is that all kinds of processing may be realized in one computing device. Another advantage of this method is its high obstacles stability. Using the dynamic nearness measure as a constituent and integral part of the method allows to select dynamic objects and to mark them out against the underlying background. It is convenient to use LAF method in hierarchical and neuro-like structures, this makes it winning to use this method in automatic recognition system. The report considers apparatus realization and gives experimental results of images processing in multichannel optoelectronic systems in real time.

Citation Download Citation

Igor S. Gibin and Pavel G. Popov "Local anisotropic features method and its application", Proc. SPIE 2969, Second International Conference on Optical Information Processing, (27 December 1996); https://doi.org/10.1117/12.262630

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