Metallic Surface Coating Defect Detection Using Firefly Based Adaptive Thresholding and Level Set Method
Yasir Aslam1, Santhi N2, Ramasamy N3, K. Ramar4

1Yasir Aslam*, Research Scholar, Department of Electronics and Communication Engineering, Noorul Islam Centre for Higher Education, Kumaracoil, India.
2Santhi N, Associate Professor, Department of Electronics and Communication Engineering, Noorul Islam Centre for Higher Education, Kumaracoil, India.
3Ramasamy N, Associate Professor, Department of Mechanical Engineering, Noorul Islam Centre for Higher Education, Kumaracoil, India.
4K. Ramar, Professor and Dean in Computer Science, Muthayammal Engineering College (autonomous), Rasipuram, India.

Manuscript received on 12 August 2019 | Revised Manuscript received on 18 August 2019 | Manuscript published on 30 August 2019 | PP: 3698 | Volume-8 Issue-10, August 2019 | Retrieval Number: J96660881019/2019©BEIESP | DOI: 10.35940/ijitee.J9666.0881019
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: An innovative approach is introduced to detect surface defects on titanium coated steel surfaces with varied size through the use of image processing techniques. This paper provides techniques which are useful to discover numerous kinds of surface defects present on coating surface. For defect detection, Firefly Algorithm (FA) based adaptive thresholding is proposed and is applied for the gray scale images. The FA ensuing nature inspired algorithm utilized expansively in support of determining various optimization problems and from the reconstructed image contours are extracted using level set method, the predictable images not including textures besides defects contours be compassed. The morphological post processing removes the noise in image and makes defects more distinguishable from the background. The speculative result persists in utilizing synchronous images of metal surface and shows that the proposed method can efficiently segment surface defects and obtain better performance than existing methods.
Keywords: Adaptive Thresholding, Defect Detection, Firefly Optimization, Level Set Method, Surface Coating.

Scope of the Article: Discrete Optimization