Skip to Main Content
 

Global Search Box

 
 
 
 

Files

File List


22367.pdf (1.35 MB)

ETD Abstract Container

Abstract Header

Thresholded K-means Algorithm for Image Segmentation

Girish, Deeptha S
http://orcid.org/0000-0003-2797-4633
http://rave.ohiolink.edu/etdc/view?acc_num=ucin1479815784173769

Abstract Details

2016, MS, University of Cincinnati, Engineering and Applied Science: Electrical Engineering.
Image processing aims to derive relevant information from an image or a group of images. Most traditional image processing algorithms that perform basic functions on images are very specific to image data. It is now common to use machine learning algorithms to perform certain tasks on images. These algorithms treat images like any other data matrix and work on them. Using these algorithms gives us the ability to perform a lot more functions on image data. The performance of these machine learning algorithms on images is very good. We work on enhancing the performance of these machine learning algorithms on images by developing methods that use the machine learning algorithms, but also use the fact that the data we are dealing with is an image and by using the properties of an image. We explore the idea of using K-means clustering algorithm for image segmentation. Firstly, we use the concept of extended pixel representation for image segmentation. We introduce new extended pixel representations, perform segmentation using k-means algorithm and compare the results for different kinds of images. Second, we deal with the problem of determining the number of clusters in the image which is a prior to the implementation of the K-means algorithm.
Anca Ralescu, Ph.D. (Committee Chair)
Kenneth Berman, Ph.D. (Committee Member)
Dan Ralescu, Ph.D. (Committee Member)
93 p.
Electrical Engineering
Extended pixel representation; optimal number of clusters; K-means algorithm; Thresholded K-means algorithm; image segmentation; clusters

Recommended Citations

Citations

  • Girish, D. S. (2016). Thresholded K-means Algorithm for Image Segmentation [Master's thesis, University of Cincinnati]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1479815784173769

    APA Style (7th edition)

  • Girish, Deeptha. Thresholded K-means Algorithm for Image Segmentation. 2016. University of Cincinnati, Master's thesis. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=ucin1479815784173769.

    MLA Style (8th edition)

  • Girish, Deeptha. "Thresholded K-means Algorithm for Image Segmentation." Master's thesis, University of Cincinnati, 2016. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1479815784173769

    Chicago Manual of Style (17th edition)

ucin1479815784173769
348
© 2016, some rights reserved.Creative Commons License Thresholded K-means Algorithm for Image Segmentation by Deeptha S Girish is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License. Based on a work at etd.ohiolink.edu.
This open access ETD is published by University of Cincinnati and OhioLINK.