Neural networks for local recognition of images with mixed noise

Alexander N. Dolia; Vladimir V. Lukin; Alexander A. Zelensky; Jaakko T. Astola; Chris Anagnostopoulos

doi:10.1117/12.420932

4 April 2001 Neural networks for local recognition of images with mixed noise

Alexander N. Dolia, Vladimir V. Lukin, Alexander A. Zelensky, Jaakko T. Astola, Chris Anagnostopoulos

Proceedings Volume 4305, Applications of Artificial Neural Networks in Image Processing VI; (2001) https://doi.org/10.1117/12.420932
Event: Photonics West 2001 - Electronic Imaging, 2001, San Jose, CA, United States

Abstract

A new approach to neural network (NN) application for local recognition of images with mixed noise is put forward. Although some pixels in images can be corrupted by spikes the proposed technique permits to eliminate uncertainty observed in this case and to correctly recognize the pixels that, in fact, correspond to an edge, a homogeneous region or an small-sized object. For this purpose a procedure of recognition of one among four basic hypotheses and additional determination of spike properties within the scanning window is proposed. This recognition task is performed for two groups of outputs (classes) of one common NN. The problems of NN learning and structure selection for this case are discussed. The performance of neural network classifier is analyzed for different input data types and for various characteristics of noise. An improvement in correct recognition is shown for the proposed approach in comparison to previous work.

Citation Download Citation

Alexander N. Dolia, Vladimir V. Lukin, Alexander A. Zelensky, Jaakko T. Astola, and Chris Anagnostopoulos "Neural networks for local recognition of images with mixed noise", Proc. SPIE 4305, Applications of Artificial Neural Networks in Image Processing VI, (4 April 2001); https://doi.org/10.1117/12.420932

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