Reducing False Detection during Inspection of HDD using Super Resolution Image Processing and Deep Learning

Authors

  • Jirarat Ieamsaard Dept. of Electrical and Computer Eng., Faculty of Eng., Naresuan University, Phitsanulok, Thailand.
  • Frode Eika Sandnes Institute of Information Technology, Faculty of Technology, Art and Design, Oslo and Akershus University College of Applied Sciences, Oslo, Norway. Westerdals Oslo School of Art, Communication and Technology, Oslo, Norway.
  • Paisarn Muneesawang Dept. of Electrical and Computer Eng., Faculty of Eng., Naresuan University, Phitsanulok, Thailand.

Keywords:

Image Super Resolution, HGA Inspection, Solder Ball Defect, Contamination Detection,

Abstract

High false detection rates are a key reliability challenge in the Hard Disk Drive (HDD) industry. Therefore, automatic visual inspection is increasingly employed for HDD inspection. In order to improve the quality and reliability of HDD products, the false detection rate must be reduced. This paper presents a super-resolution image-based method for improving the performance of Head Gimbals Assembly (HGA) inspection. The experimental results confirm the efficiency of the super-resolution image processing for improving automatic inspection of defects such as pad burning and micro contaminations. Moreover, combining super resolution image processing with deep learning reduces the false detection rate and improves the accuracy of HGA inspection.

Downloads

Download data is not yet available.

Downloads

Published

2017-06-01

How to Cite

Ieamsaard, J., Eika Sandnes, F., & Muneesawang, P. (2017). Reducing False Detection during Inspection of HDD using Super Resolution Image Processing and Deep Learning. Journal of Telecommunication, Electronic and Computer Engineering (JTEC), 9(2-5), 91–95. Retrieved from https://jtec.utem.edu.my/jtec/article/view/2405

Issue

Vol. 9 No. 2-5: Circuit and System Advancement in Modern World IV

Section

Articles

License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)