Skip to Main Content
Frequently Asked Questions
Submit an ETD
Global Search Box
Need Help?
Keyword Search
Participating Institutions
Advanced Search
School Logo
Files
File List
14074.pdf (5.98 MB)
ETD Abstract Container
Abstract Header
A Structure based Methodology for Retrieving Similar Rasters and Images
Author Info
Jayaraman, Sambhavi
Permalink:
http://rave.ohiolink.edu/etdc/view?acc_num=ucin1428048689
Abstract Details
Year and Degree
2015, MS, University of Cincinnati, Engineering and Applied Science: Computer Science.
Abstract
Until a decade ago, information was retrieved from text based documents, however, in recent times there has been a great advancement in the area of Image Retrieval. With the advent of technology, it is possible to visualize almost any kind of information. The amount of data stored in images in the form of maps, rasters etc. is continuously increasing, thereby increasing size of the image database. Image databases are widely used in medical sciences, space programs and geographical domain to name a few and therefore, there is a need for retrieval of relevant images to help in research and development. There are two ways to fetch relevant images with respect to a query image. The first method is the text base image retrieval that extracts images based on textual content such as, keywords, tags, titles etc. associated with an image. The second method, content based image retrieval is developed to overcome the drawbacks faced by the text based image retrieval technique. This method pulls out the required images based on the contents of the image, namely, color, texture and shape. The method employed in our thesis is the content based image retrieval. The dataset used in this work consists of a collection of terrain images. In this research, we strive to retrieve images that contain similar terrain characteristics to a query image. In order to do this, statistical measures such as entropy and mean are used to represent the features of an image. This helps in retrieving images irrespective of the orientation and location of the landform types. The results captured by the proposed method are visually validated and are further supported by determining the accuracy of the approach. Experiments conducted show that our method gives good results and we have provided all the necessary evidence to support our claim.
Committee
Raj Bhatnagar, Ph.D. (Committee Chair)
Nan Niu, Ph.D. (Committee Member)
Tomasz Stepinski, Ph.D. (Committee Member)
Paul Talaga, Ph.D. (Committee Member)
Pages
80 p.
Subject Headings
Artificial Intelligence
Keywords
Retrieve similar rasters and images
;
Retrieve similar images using statistical measures
;
Feature Extraction from an image
;
Content-based Image Retrieval
;
Extract similar images irrespective of orientation
;
Entropy, mean and minimum cost spanning tree
Recommended Citations
Refworks
EndNote
RIS
Mendeley
Citations
Jayaraman, S. (2015).
A Structure based Methodology for Retrieving Similar Rasters and Images
[Master's thesis, University of Cincinnati]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1428048689
APA Style (7th edition)
Jayaraman, Sambhavi.
A Structure based Methodology for Retrieving Similar Rasters and Images.
2015. University of Cincinnati, Master's thesis.
OhioLINK Electronic Theses and Dissertations Center
, http://rave.ohiolink.edu/etdc/view?acc_num=ucin1428048689.
MLA Style (8th edition)
Jayaraman, Sambhavi. "A Structure based Methodology for Retrieving Similar Rasters and Images." Master's thesis, University of Cincinnati, 2015. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1428048689
Chicago Manual of Style (17th edition)
Abstract Footer
Document number:
ucin1428048689
Download Count:
507
Copyright Info
© 2015, all rights reserved.
This open access ETD is published by University of Cincinnati and OhioLINK.