Skip to Main Content
 

Global Search Box

 
 
 
 

Files

File List


14074.pdf (5.98 MB)

ETD Abstract Container

Abstract Header

A Structure based Methodology for Retrieving Similar Rasters and Images

Jayaraman, Sambhavi
http://rave.ohiolink.edu/etdc/view?acc_num=ucin1428048689

Abstract Details

2015, MS, University of Cincinnati, Engineering and Applied Science: Computer Science.
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.
Raj Bhatnagar, Ph.D. (Committee Chair)
Nan Niu, Ph.D. (Committee Member)
Tomasz Stepinski, Ph.D. (Committee Member)
Paul Talaga, Ph.D. (Committee Member)
80 p.
Artificial Intelligence
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

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)

ucin1428048689
507
© 2015, all rights reserved.
This open access ETD is published by University of Cincinnati and OhioLINK.