Comparison of different active contour models-based image segmentation techniques for metal alloy particle analysis in material science applications
by Arti Bang; Guzayya Sarkhawas; Yogesh Dandawate
International Journal of Image Mining (IJIM), Vol. 2, No. 1, 2016

Abstract: Material particle analysis is one of the difficult tasks in material science engineering. To understand the particle characteristics, size and shape of the particle are important features for measurement. Image processing techniques predominantly segmentation technique provides effective analysis of particle. This paper presents an improved adaptive level set method: modified from traditional level set method (LSM) with respect to the parameters; adaptive directional speed and stopping force based on weighted probability, which further improves the algorithm accuracy for particle image segmentation and parameters measurement. Also, the proposed methodology is compared with the traditional LSM and Chanvese method both subjectively and objectively. In this paper, different microscopic images of metal alloy particles from material science research laboratory are tested on each segmentation method to effectively achieve parameters such as area, number, roundness, and so on. Experimental results show that the proposed method provides average accuracy of 87% with respect to dice coefficient.

Online publication date: Tue, 13-Sep-2016

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Image Mining (IJIM):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com