Redundancy in lattice algebra based associative neural networks for image retrieval from noisy inputs

Gonzalo Urcid; José-Angel Nieves-Vázquez; Rocío Morales-Salgado

doi:10.1117/12.2633686

3 October 2022 Redundancy in lattice algebra based associative neural networks for image retrieval from noisy inputs

Gonzalo Urcid, José-Angel Nieves-Vázquez, Rocío Morales-Salgado

Proceedings Volume 12226, Applications of Digital Image Processing XLV; 1222614 (2022) https://doi.org/10.1117/12.2633686
Event: SPIE Optical Engineering + Applications, 2022, San Diego, California, United States

Abstract

Since lattice algebra based associative memories can store any number k of associated vector pairs (x, y), where x is a real n-dimensional vector and y is a real m-dimensional vector, we propose a basic redundancy mechanism to endow with retrieval capability the dual canonical min-W and max-M lattice associative memories for inputs corrupted by random noise. To achieve our goal, given a finite set of exemplar vectors, redundant patterns are added in order to enlarge the original fixed point set of the original exemplars. The redundant patterns are masked versions designed to be spatially correlated with each exemplar x in a given learning data set. An illustrative example with noisy color images are given to measure the retrieval capability performance of the proposed redundancy technique as considered for lattice associative memories.

Conference Presentation

Citation Download Citation

Gonzalo Urcid, José-Angel Nieves-Vázquez, and Rocío Morales-Salgado "Redundancy in lattice algebra based associative neural networks for image retrieval from noisy inputs", Proc. SPIE 12226, Applications of Digital Image Processing XLV, 1222614 (3 October 2022); https://doi.org/10.1117/12.2633686

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