ADAPTIVE IMAGE ENCODING AND CLASSIFICATION USING NEURAL NETWORKS

Award Information
Agency:
National Aeronautics and Space Administration
Amount:
$49,629.00
Program:
SBIR
Contract:
N/A
Solitcitation Year:
N/A
Solicitation Number:
N/A
Branch:
N/A
Award Year:
1989
Phase:
Phase I
Agency Tracking Number:
10502
Solicitation Topic Code:
N/A
Small Business Information
Netrologic Inc
4241 Jutland Dr, San Diego, CA, 92117
Hubzone Owned:
N
Woman Owned:
N
Socially and Economically Disadvantaged:
N
Duns:
N/A
Principal Investigator
 Richard S Cigledy
 () -
Business Contact
Phone: () -
Research Institution
N/A
Abstract
WE INTEND TO EXPLORE THE VIABILITY OF NEURAL NETWORKS FOR IMAGE COMPRESSION AND PATTERN CLASSIFICATION IN AN INTEGRATED SYSTEM. THIS IS A NEW APPROACH TO IMAGE COMPRESSION THAT HAS SEVERAL ADVANTAGES OVER STANDARD APPROACHES. SO FAR, NEURAL NETWORKS HAVE BEEN SHOWN TO BE COMPARABLE TO STANDARD TECHNIQUES (COTTRELL, MUNRO & ZIPSER,1987) FOR THE TASK OF IMAGE COMPRESSION. THEY SHOWED THAT A 3 LAYER BACK PROPAGATION NETWORK (RUMELHART, HINTON & WILLIAMS, 1986) WITH ESSENTIALLY NO TUNING COULD ACHIEVE LEVELS OF COMPRESSION ON THE ORDER OF 1 BIT PER PIXEL (BPP). WE INTEND TO EXTEND THAT WORK IN AN ATTEMPT TO ACHIEVE COMPRESSION RATES BELOW 1 BPP AND INVESTIGATE ITS USEFULNESS IN NASA APPLICATIONS. IF THE ALGORITHM CAN BE EMBEDDED IN HARDWARE, THE POTENTIAL ADVANTAGES FOR SPACE-BASED APPLICATIONS ARE: A COMPRESSION DEVICE THAT ADAPTS TO THE CURRENT ENVIRONMENTAL AND HARDWARE CONDITIONS AND OPERATES IN REAL TIME, LESS SENSITIVITY TO CHANNEL ERRORS, A RECONFIGURABLE PATTERN CLASSIFIER THAT CAN BE TRAINED IN SITU.

* information listed above is at the time of submission.

Agency Micro-sites

US Flag An Official Website of the United States Government