1 October 1998 Discriminating a specified digital image from noise process
Author Affiliations +
In this paper, the problem of discriminating a specified signal from noise process is considered, where the signal is associated with a digital image. In the univariate case it is well known that the one-sided t-test is uniformly most powerful for the null hypothesis against all one-sided alternatives. Such a property does not easily extend to the multivariate case. In the present paper, a test is derived for the hypothesis that the main of a vector random variable is zero against specified alternatives, when the covariance matrix is unknown. This test depends on the given alternatives and is more powerful than Hotelling's T. The test is invariant to intensity changes in a background of Gaussian noise and achieves a fixed probability of a false alarm. Thus, operating in accordance to the local noise situation, the test is adaptive. The properties of the proposed test are investigated when a single alternative is specified.
© (1998) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Nicholas A. Nechval, Nicholas A. Nechval, Konstantin N. Nechval, Konstantin N. Nechval, } "Discriminating a specified digital image from noise process", Proc. SPIE 3460, Applications of Digital Image Processing XXI, (1 October 1998); doi: 10.1117/12.323237; https://doi.org/10.1117/12.323237


Back to Top