Journal of Electrical and Computer Engineering / 2012 / Article / Tab 7

Research Article

Evaluating Subpixel Target Detection Algorithms in Hyperspectral Imagery

Table 7

The ๐ด t h ((A โˆ’ t h 2 )/(th โˆ’ t h 2 )) where A is the area under the Pd-log ( ๐‘ƒ fa) curve and t h is the threshold (i.e., the maximum false alarm rate) results of the IRBTA algorithm for V1 in the RIT test image are shown in the first two lines. The maximum false alarm rate is 10โˆ’3; other parameters are as given in Table 6. The third and fourth lines represent the same results normalized by dividing the value of the 3 ร— 3 filter by the values of the other filters.

โ€‰Ath by IRBTA-Threshold = 10-3

WindowOnly7 ร— 7Only5 ร— 53 ร— 3Global
7 ร— 75 ร— 5
V1_GLRT0.00070.00110.00100.00140.00320.0003
V1_ACE0.04360.09080.09460.16570.49810.0420

โ€‰Normalize relative to 3 ร— 3

V1_GLRT4.812.973.352.36111.83
V1_ACE11.445.495.263.01111.86

We are committed to sharing findings related to COVID-19 as quickly as possible. We will be providing unlimited waivers of publication charges for accepted research articles as well as case reports and case series related to COVID-19. Review articles are excluded from this waiver policy. Sign up here as a reviewer to help fast-track new submissions.