A Comparison of Noise Cleaning Techniques

reportActive / Technical Report | Accession Number: ADA074854 | Open PDF

Abstract:

A variety of noise cleaning techniques are compared on two test pictures. All of the techniques tested are based on local analysis of a small neighborhood of each pixel. They include median and mode filtering selective local averaging or weighted averaging schemes of various sorts and Kalman filtering. Iterated weighted averaging and iterated median filtering were judged to give the best overall performance.

Author(s):
Davenport, Judith P.
Author Organization(s):
MARYLAND UNIV COLLEGE PARK COMPUTER SCIENCE CENTER
Descriptive Note:
Technical rept.
Supplementary Note:
Sponsored in part by DARPA. DOI: 10.21236/ADA074854
Pagination:
0041

Security Markings

DOCUMENT & CONTEXTUAL SUMMARY

Distribution:
Approved For Public Release
Distribution Statement:
Approved For Public Release; Distribution Is Unlimited.

RECORD

Collection: TR
Identifying Numbers
Report Number(s):
CSC-TR-689
Contract/Grant Number(s):
DAAG53-76-C-0138, DARPA ORDER-3206
Monitor Series:
NVL
 Subject Terms
Joint Capability Areas:
JCA_3.2_Engagement; JCA_3_Force Application
Communities of Interest:
Cyber
Descriptor(s):
*IMAGE PROCESSING, *KALMAN FILTERING, GAUSSIAN NOISE, GRADIENTS, ITERATIONS, NOISE REDUCTION, PROBABILITY DENSITY FUNCTIONS, SIGNAL TO NOISE RATIO, WEIGHTING FUNCTIONS
Field(s)/Group(s):
Cybernetics, Human Factors Engineering and Man Machine Systems
Keyword(s):
PIXELS, SMOOTHING
Report Date:
1978 Sep 01