Off-campus South Dakota State University users: To download campus access theses, please use the following link to log into our proxy server with your South Dakota State University ID and password.

Non-South Dakota State University users: Please talk to your librarian about requesting this thesis through interlibrary loan.

Document Type

Thesis - University Access Only

Award Date


Degree Name

Master of Science (MS)

Department / School

Electrical Engineering and Computer Science

First Advisor

Sung Y. Shin


Abstract: Content-Based Image Retrieval (CBIR) has been improving in the past decade and many methods has been presented to reduce the gap between low-level descriptions of an image and the high-level semantics of the image (Kashani 2011). Searching for effective method for CBIR led to the use of Genetic Algorithms (GA) (aka. evolutionary programming). Methods used GA (Gali 2012), (Xie Oct. 2013) have faced difficulties when defining the fitness function. That led other methods (Chih-Chin Lai 2011) to eliminate the fitness function and replace it with user selection or feedback, where the speed of the process reduced significantly since the user interaction is needed at every iteration of the GA. In my method, we get the benefit of the Genetic Algorithms and we keep the fitness function with limited access to the population selection with the help of user feedback. We define a new function which we xi called the ALTERNATING FUNCTION that controls who is going to select the new population, either the fitness function or the user feedback of the most fitness results. This function will let the fitness function to select five generation then switch to the user to select one generation, and so on.

Library of Congress Subject Headings

Image processing--Digital techniques
Pattern recognition systems
Genetic algorithms.


Includes bibliographical references (pages 50-54)



Number of Pages



South Dakota State University



Rights Statement

In Copyright