Color Image Retrieval Based on Non-Parametric Statistical Tests of Hypothesis

Abstract

A novel method for color image retrieval based on statistical non-parametric tests such as two-sample Wald Test for equality of variance and Man-Whitney U test is proposed in this paper. The proposed method tests the deviation, i.e. distance in terms of variance between the query and target images; if the images pass the test, then it is proceeded to test the spectrum of energy, i.e. distance between the mean values of the two images; otherwise, the test is dropped. If the query and target images pass the tests then it is inferred that the two images belong to the same class, i.e. both the images are same; otherwise, it is assumed that the images belong to different classes, i.e. both images are different. The obtained test statistic values are indexed in ascending order and the image corresponds to the least value is identified as same or similar images. Here, either the query image or the target image is treated as sample; the other is treated as population. Also, some other features such as Coefficient of Variation, Skewness, Kurtosis, Variance, and Spectrum of Energy are compared between the query and target images color-wise. The proposed method is robust for scaling and rotation, since it adjusts itself and treats either the query image or the target image is the sample of other. The results obtained are comparable with the existing methods. Keywords—Variance, mean, query image, target image, non-parametric tests.