Classification automation of thermoplastic particles in a cured epoxy matrix according to their size on microscopic images

Victoria A. Sablina; Alexander N. Varnavsky; Andrei N. Varnavsky

doi:10.1117/12.2267090

30 December 2016 Classification automation of thermoplastic particles in a cured epoxy matrix according to their size on microscopic images

Victoria A. Sablina, Alexander N. Varnavsky, Andrei N. Varnavsky

Author Affiliations +

Proceedings Volume 10224, International Conference on Micro- and Nano-Electronics 2016; 102242B (2016) https://doi.org/10.1117/12.2267090
Event: The International Conference on Micro- and Nano-Electronics 2016, 2016, Zvenigorod, Russian Federation

Abstract

Epoxy resins have wide applications in modern industries. To improve the properties of such resins the thermoplastic component is often used. This component dissolves in the epoxy resin at a high temperature. To determine the properties of the obtained cured epoxy matrix with thermoplastic particles it is important to estimate and classify this particle sizes. In this paper we investigate methods for solving these tasks automatically. The thermoplastic particle sizes are analyzed using the microscopy images of the cured epoxy matrix. The digital image processing methods for the thermoplastic particle detection are discussed. The Otsu’s method is implemented for microscopic images with homogeneous background. The Circular Hough Transform method is implemented for microscopic images with big visible particle radii. The results of both methods for the considered images are represented. The parameters of the Gaussian distribution for the thermoplastic particle sizes in a cured epoxy matrix are estimated from the analyzed microscopic images.

Citation Download Citation

Victoria A. Sablina, Alexander N. Varnavsky, and Andrei N. Varnavsky "Classification automation of thermoplastic particles in a cured epoxy matrix according to their size on microscopic images", Proc. SPIE 10224, International Conference on Micro- and Nano-Electronics 2016, 102242B (30 December 2016); https://doi.org/10.1117/12.2267090

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available