Title: Comparison of different active contour models-based image segmentation techniques for metal alloy particle analysis in material science applications
Authors: Arti Bang; Guzayya Sarkhawas; Yogesh Dandawate
Addresses: Department of Electronics and Telecommunication, Vishwakarma Institute of Information Technology, Pune 411048, India ' Department of Electronics and Telecommunication, Vishwakarma Institute of Information Technology, Pune 411048, India ' Department of Electronics and Telecommunication, Vishwakarma Institute of Information Technology, Pune 411048, India
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.
Keywords: active contours; image processing; level set segmentation; metal alloy particles; particle counting; particle size; image segmentation; materials science; directional speed; stopping force; metal alloys.
International Journal of Image Mining, 2016 Vol.2 No.1, pp.12 - 30
Received: 09 Sep 2015
Accepted: 26 Jan 2016
Published online: 13 Sep 2016 *