Image Processing-Based Non-Metallic Inclusion Detection Framework with Extreme Value Distribution

EDIZ, POLAT and HUSEYIN, AYDILEK (2015) Image Processing-Based Non-Metallic Inclusion Detection Framework with Extreme Value Distribution. In: Third International Conference on Advances in Information Processing and Communication Technology - IPCT 2015, 10-11 December, 2015, Rome, Italy.

[img]
Preview
Text
20151223_102909.pdf - Published Version

Download (512kB) | Preview
Official URL: https://www.seekdl.org/conferences/paper/details/7...

Abstract

Non-metallic inclusions are one of the main problems in steel industry. They are formed by chemical reactions during the steel production process. Non-metallic inclusions have negative effects on mechanical properties of steel. Thus, the detection and the classification of them are very important for the product quality. In this paper, we have developed a sulfide type non-metallic inclusion detection and classification system employing image processing algorithms according to internationally accepted standards. In addition, the system has been analyzed using Gumbel Extreme Value Distributions to predict the expected extreme valued length of inclusion. The system has been tested with AISI 1040 steel as an example, and successful results have been obtained.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Image Processing, Non-metallic inclusions, Gumbel, Extreme Value Distribution.
Depositing User: Mr. John Steve
Date Deposited: 04 Apr 2019 11:59
Last Modified: 04 Apr 2019 11:59
URI: http://publications.theired.org/id/eprint/1157

Actions (login required)

View Item View Item