Asee peer logo

A Color Image Merging Algorithm Using Matlab

Download Paper |

Collection

2008 Annual Conference & Exposition

Location

Pittsburgh, Pennsylvania

Publication Date

June 22, 2008

Start Date

June 22, 2008

End Date

June 25, 2008

ISSN

2153-5965

Conference Session

International Division Poster Session

Tagged Division

International

Page Count

10

Page Numbers

13.16.1 - 13.16.10

Permanent URL

https://peer.asee.org/3120

Download Count

562

Request a correction

Paper Authors

biography

Eric Boyer Pennsylvania State University-Harrisburg

visit author page

Mr. Boyer is now a graduate student in the Master of Engineering Program, Electrical Engineering at Penn State University at Harrisburg.

visit author page

biography

Aldo Morales Pennsylvania State University-Harrisburg

visit author page

Dr. Morales received his electronic engineering degree with distinction from the University of Tarapaca, Arica, Chile, and M.S. and Ph.D. degrees in electrical and computer engineering from the State University of New York at Buffalo. His research interests are digital signal and image processing, and computer vision. He is now an Associate Professor of Electrical Engineering at Penn State University at Harrisburg.

visit author page

Download Paper |

Abstract
NOTE: The first page of text has been automatically extracted and included below in lieu of an abstract

A Color Image Merging Algorithm Using MATLAB Eric Boyer and Aldo Morales Electrical Engineering Program Penn State Harrisburg Middletown, PA 17057

Abstract:

Students in the Electrical Engineering program at Penn State Harrisburg have many opportunities to apply their acquired knowledge through hands-on course projects and laboratory experiences in electronics, digital and image processing, VLSI, power and other courses, in addition to their capstone senior project. This paper presents an example of an image processing course project in which an efficient algorithm to merge color images is developed using MATLAB. The algorithm’s efficiency is based on the fact that only one color plane is used to detect similarities between images before the merging is accomplished. Results show that the proposed method performs well with sample images obtained from the Internet.

I. Introduction

The Electrical Engineering program at Penn State Harrisburg provides an opportunity for students to pursue interests in electrical and electronic circuits, including digital circuits and VLSI and its fabrication, microprocessors and their applications, electromagnetics, communications, control systems, digital signal/image processing and computer vision1. Typically, students demonstrate acquired knowledge through performance on exams, quizzes, homework and course projects. In this paper, we will present an efficient algorithm for color image merging based on an image processing course project.

Image merging of two images into a single image can be done using different methods. In A. German et al 2 entropy was used as the basis to merge images with different exposure and lighting conditions. Scheunders and De Backer3 introduced multispectral image wavelet representation to merge Lanstat Thematic Mapper images. N. Soussi and J. L. Biuat4 escribed simultaneous display, edges and structure superimposition, transparency, and hierarchical image merging for medical applications. However, note that some of these techniques are beyond an undergraduate level course in image processing. This paper will describe an efficient and simple procedure to produce a large merged image using MATLAB and will present the necessary code to implement it. The overall goal is to acquire several small and more detailed images of large objects and then compose a larger image file by combining these small image files. It is understood that large objects cannot be imaged with any great detail. The algorithm references two different images to be merged. The first image is a database image. The second image in the algorithm is the image to be added to the database image. The algorithm starts by extracting a single color plane from both color RGB images. The next step is to sample the pixel intensity values of a specified window in the second image and to store in a matrix the pixel intensities within this window. The contents of this matrix are then used to find a similar arrangement of pixel intensities in the database image. The algorithm starts at the left

ASEE holds the copyright on this document. It may be read by the public free of charge. Authors may archive their work on personal websites or in institutional repositories with the following citation: © 2008 American Society for Engineering Education. Other scholars may excerpt or quote from these materials with the same citation. When excerpting or quoting from Conference Proceedings, authors should, in addition to noting the ASEE copyright, list all the original authors and their institutions and name the host city of the conference. - Last updated April 1, 2015