Vertical Edge Detection-Based Automatic Optical Inspection of HGA Solder Jet Ball Joint Defects

Article Sidebar

PDF
DOI: https://doi.org/10.37936/ecti-cit.201592.54420
Keywords:
Optical Inspection Solder Jet Ball Joint Defect Vertical Edge Detection

Main Article Content

Jirarat Ieamsaard
Department of Electrical and Computer Engineering, Naresuan University, Thailand
Suchart Yammen
Department of Electrical and Computer Engineering, Naresuan University, Thailand
Paisarn Muneesawang
Department of Electrical and Computer Engineering, Naresuan University, Thailand
Frode Eika Sandnes
Institute of information Technology, Faculty of Technology, Art and Design, Oslo and Akershus University College of Applied Sciences, Norway

Abstract

The Head Gimbal Assembly (HGA) is an essential hard disk drive (HDD) component allowing data to be read from and written to the media. Defects on the HGA may affect the data read/write process and reduce the quality of the HDD. Therefore, HGA inspection needs to be improved during HDD manufacturing. This paper describes an image processing method that automate the optical inspection of HGA solder jet ball joint defects. Vertical edge detection methods are proposed for identifying defects. The performance of the vertical edge detection method is compared to a Sobel-based method, Roberts’ method and a Prewitt’s method. The methods were tested with 18,123 HGA images. The experimental results show that the vertical edge detection method outperforms the other methods, which had an accuracy of 99.3%, as compared to the Sobel based method, with an accuracy of 80% and 78.2 for Roberts’ method and 65.9 for Prewitt’s method.

Article Details

How to Cite
[1]
J. Ieamsaard, S. Yammen, P. Muneesawang, and F. E. Sandnes, “Vertical Edge Detection-Based Automatic Optical Inspection of HGA Solder Jet Ball Joint Defects”, ECTI-CIT Transactions, vol. 9, no. 2, pp. 173–181, Apr. 2016.
Issue
Vol. 9 No. 2 (2015): ECTI Transaction on CIT (Nov 2015)
Section
Artificial Intelligence and Machine Learning (AI)