Diffuse Prior Monotonic Likelihood Ration Test for Evaluation of Fused Image Quality Metrics

reportActive / Technical Report | Accession Number: ADA533363 | Open PDF

Abstract:

This paper introduces a novel method to score how well proposed fused image quality measures FIQMs indicate the effectiveness of humans to detect targets of interest in fused imagery. The human detection performance is measured via human perception experiments. A good FIQM should relate to perception results in a monotonic fashion. The new method, the diffuse prior monotonic likelihood ratio DPMLR test compares the H1 hypothesis that the intrinsic human detection performance is related to the FIQM via a monotonic function to the null hypothesis that the detection and image quality relationship is random. The paper discusses many interesting properties of the DPMLR and demonstrates the effectiveness of the DPMLR test via Monte Carlo Simulations. Finally, the DPMLR is used to score FIQMs over 35 scenes implementing various image fusion algorithms.

Author(s):
Wei, Chuanming ; Kaplan, Lance M. ; Burks, Stephen D. ; Blum, Rick S.
Author Organization(s):
ARMY RESEARCH LAB ADELPHI MD
Descriptive Note:
Conference paper
Supplementary Note:
See also ADM002299. Presented at the International Conference on Information Fusion (12th), Fusion 2009, in Seattle, WA on 6-9 July 2009; published in proceedings of the same, p1076-1083. U.S. Government or Federal Rights License. The original document contains color images.
Pagination:
0009

Security Markings

DOCUMENT & CONTEXTUAL SUMMARY

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

RECORD

Collection: TR
Identifying Numbers
Contract/Grant Number(s):
W911NF-06-2-0020, W911NF-08-1-0449
Monitor Series:
ARO
 Subject Terms
Joint Capability Areas:
JCA_2_Battlespace Awareness; JCA_2.2.2_Imagery Collection; JCA_2.2_Collection; JCA_5_Command and Control; JCA_5.5.2_Task; JCA_5.5_Direct; JCA_1_Force Support; JCA_1.2.7_Experimentation; JCA_1.2_Force Preparation; JCA_8_Building Partnerships
Modernization Areas:
AI and Machine Learning
Communities of Interest:
Biomedical
Descriptor(s):
*VISUAL PERCEPTION, *TARGET DETECTION, PERFORMANCE(HUMAN), FEATURE EXTRACTION, COMPOSITE IMAGES, SYMPOSIA, IMAGE PROCESSING
Field(s)/Group(s):
Cybernetics, Optical Detection and Detectors, Human Factors Engineering and Man Machine Systems
Keyword(s):
IMAGE FUSION ALGORITHMS, DPMLR(DIFFUSE PRIOR MONOTONIC LIKELIHOOD RATIO), FIQM(FUSED IMAGE QUALITY MEASURE)
Report Date:
2009 Jul 01
Creation Date:
2010 Dec 29