Effect of Image Compression using Fast Fourier Transformation and Discrete Wavelet Transformation on Transfer Learning Wafer Defect Image Classification

Authors

  • Jessnor Arif Mat Jizat
  • Dr. Ahmad Fakhri Ab. Nasir Faculty of Computing, Universiti Malaysia Pahang, 26600 Pahang, Malaysia.
  • Dr. Anwar P.P Abdul Majeed Faculty of Manufacturing & Mechatronic Engineering Technology (FTKPM), Universiti Malaysia Pahang, 26600 Pahang, Malaysia.
  • Edmund Yuen Ideal Vision Integration Sdn Bhd, 02-25, Level 2, Setia Spice Canopy, Jln Tun Dr Awang, 11900 Bayan Lepas, Penang, Malaysia

DOI:

https://doi.org/10.15282/mekatronika.v2i1.6704

Keywords:

Wafer Defect, Logistic Regression, InceptionV3, Fast Fourier Transformation, Discrete Wavelet Transformation

Abstract

Automated inspection machines for wafer defects usually captured thousands of images on a large scale to preserve the detail of defect features. However, most transfer learning architecture requires smaller images as input images. Thus, proper compression is required to preserve the defect features whilst maintaining an acceptable classification accuracy. This paper reports on the effect of image compression using Fast Fourier Transformation and Discrete Wavelet Transformation on transfer learning wafer defect image classification. A total of 500 images with 5 classes with 4 defect classes and 1 non-defect class were split to 60:20:20 ratio for training, validating and testing using InceptionV3 and Logistic Regression classifier. However, the input images were compressed using Fast Fourier Transformation and Discrete Wavelet Transformation using 4 level decomposition and Debauchies 4 wavelet family. The images were compressed by 50%, 75%, 90%, 95%, and 99%. As a result, the Fast Fourier Transformation compression show an increase from 89% to 94% in classification accuracy up to 95% compression, while Discrete Wavelet Transformation shows consistent classification accuracy throughout albeit diminishing image quality. From the experiment, it can be concluded that FFT and DWT image compression can be a reliable method for image compression for grayscale image classification as the image memory space drop 56.1% while classification accuracy increased by 5.6% with 95% FFT compression and memory space drop 55.6% while classification accuracy increased 2.2% with 50% DWT compression.

Downloads

Published

2020-06-05 — Updated on 2020-06-05

How to Cite

[1]
J. A. Mat Jizat, A. F. . Ab. Nasir, A. P.P Abdul Majeed, and E. . Yuen, “Effect of Image Compression using Fast Fourier Transformation and Discrete Wavelet Transformation on Transfer Learning Wafer Defect Image Classification ”, MEKATRONIKA, vol. 2, no. 1, pp. 16–22, Jun. 2020.

Issue

Section

Original Article

Most read articles by the same author(s)