NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Collections About News Help Login
Back to Results
The effect of lossy image compression on image classificationWe have classified four different images, under various levels of JPEG compression, using the following classification algorithms: minimum-distance, maximum-likelihood, and neural network. The training site accuracy and percent difference from the original classification were tabulated for each image compression level, with maximum-likelihood showing the poorest results. In general, as compression ratio increased, the classification retained its overall appearance, but much of the pixel-to-pixel detail was eliminated. We also examined the effect of compression on spatial pattern detection using a neural network.
Document ID
19960003362
Acquisition Source
Legacy CDMS
Document Type
Preprint (Draft being sent to journal)
Authors
Paola, Justin D. (Research Inst. for Advanced Computer Science Moffett Field, CA, United States)
Schowengerdt, Robert A. (Research Inst. for Advanced Computer Science Moffett Field, CA, United States)
Date Acquired
September 6, 2013
Publication Date
August 16, 1995
Subject Category
Earth Resources And Remote Sensing
Report/Patent Number
NASA-CR-199550
NAS 1.26:199550
RIACS-TR-95-18
NIPS-95-05574
Meeting Information
Meeting: Annual IEEE International Geoscience and Remote Sensing Symposium
Location: Florence
Country: Italy
Start Date: July 20, 1995
End Date: July 24, 1995
Accession Number
96N13371
Funding Number(s)
CONTRACT_GRANT: NAG5-2198
CONTRACT_GRANT: NAS2-1372
Distribution Limits
Public
Copyright
Work of the US Gov. Public Use Permitted.

Related Records

There are no records associated with this record.
No Preview Available