出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：A novel method for color image retrieval, based on statistical non-parametric tests such as twosampleWald 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 queryand target images; if the images pass the test, then it is proceeded to test the spectrum ofenergy, 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 thesame class, i.e. both the images are same; otherwise, it is assumed that the images belong todifferent classes, i.e. both images are different. The proposed method is robust for scaling androtation, since it adjusts itself and treats either the query image or the target image is thesample of other.
