Author(s)

K. Seetharaman^1*, S. Selvaraj²

¹Department of Computer Science & Engineering, Annamalai University, Annamalai Nagar, India.
²Department of Computer Applications, Research Scholar, Manonmaniam Sundaranar University, Tirunelveli, India.

This paper proposes a novel method based on statistical tests of hypotheses, such as F-ratio and Welch’s t-tests. The input query image is examined whether it is a textured or structured. If it is structured, the shapes are segregated into various regions according to its nature; otherwise, it is treated as textured image and considered the entire image as it is for the experiment. The aforesaid tests are applied regions-wise. First, the F-ratio test is applied, if the images pass the test, then it is proceeded to test the spectrum of energy, i.e. means of the two images. If the images pass both tests, then it is concluded that the two images are the same or similar. Otherwise, they differ. Since the proposed system is distribution-based, it is invariant for rotation and scaling. Also, the system facilitates the user to fix the number of images to be retrieved, because the user can fix the level of significance according to their requirements. These are the main advantages of the proposed system.

F-Ratio Test, Welch’s Test, Tests of Hypotheses, Mean Average Precision, Target Image, Query Image

Seetharaman, K. and Selvaraj, S. (2016) Statistical Tests of Hypothesis Based Color Image Retrieval. Journal of Data Analysis and Information Processing, 4, 90-99. doi: 10.4236/jdaip.2016.42008.