Image searching is an essential feature of many software applications. Histograms can be used to represent the pixel color intensities of images. Measuring the similarities between images by comparing the histograms can be performed through the use of information-theoretic measures, such as the Kullback-Leibler divergence and cross-entropy. In this project, a query image is selected from a collection of images and it is compared to the other images to determine which image is most similar to the query image. This process is carried out by creating histograms of each image, and then using measures such as the Kullback-Leibler divergence and cross-entropy to compare the histograms. The .NET functional language, F#, is used in the implementation of this project. The C# language, another .NET language, was also used for coding the graphical user interface.
A project presented to the Department of Computer and Information Sciences State University of New York Polytechnic Institute Utica, New York In partial fulfillment of the requirements of the Master of Science Degree.