Screw Absence Classification on Aluminum Plate via Features Based Transfer Learning Models

Authors

  • Weng Zhen Lim Faculty of Manufacturing and Mechatronic Engineering Technology, Universiti Malaysia Pahang, 26600 Pahang, Malaysia.
  • Norasmiza Mohd Faculty of Manufacturing and Mechatronic Engineering Technology, Universiti Malaysia Pahang, 26600 Pahang, Malaysia.
  • Anwar P. P. Abdul Majeed School of Robotics, XJTLU Entrepreneur College (Taicang), Xi’an Jiatong-Liverpool University, Suzhou, 215123, P. R. China
  • Mohd Azraai Mohd Razman Faculty of Manufacturing and Mechatronic Engineering Technology, Universiti Malaysia Pahang, 26600 Pahang, Malaysia.
  • Yin Goon Koon TT Vision Technologies Sdn. Bhd., Plot 106, Hilir Sungai Keluang 5, Bayan Lepas Phase 4, 11900, Penang, Malaysia

DOI:

https://doi.org/10.15282/mekatronika.v5i1.9408

Keywords:

Machine Vision, Transfer Learning, Machine Learning, Hyperparameter Tuning

Abstract

Screw is one of the important elements in every industry. Present of screw play an important role in which it holds the product in its own position and prevent loosen or collision with the case which will cause the small components or compartment fall off from its original position and lead to product failure. With the rise of revolution 4.0 in the industry, it helps to reduce the labor cost and human error. The main purpose of this study is to create a robust classification model used for machine vision detection – absence and present of screw, which could be adapted into respective robotics application system. 6 degree of freedom UR robot, Universal Robot is used to collect the custom dataset in TT Vision Technologies Sdn Bhd. The collected dataset is then classified into two categories, named as absent and present. Pretrained dataset, ImageNet is used to ease the training process in this research. Transfer learning model is used to extract the features which used to feed into different machine learning models. Each machine learning models undergoes hyperparameters tunning to achieve best classification accuracy. Samling ratio of 60:20:20 is used to separate the data in training, validation and testing respectively before fed into different ml models

Downloads

Published

2023-04-21

How to Cite

[1]
W. Z. Lim, N. Mohd, A. P. P. Abdul Majeed, M. A. Mohd Razman, and Y. G. Koon, “Screw Absence Classification on Aluminum Plate via Features Based Transfer Learning Models”, Mekatronika: J. Intell. Manuf. Mechatron., vol. 5, no. 1, pp. 62–66, Apr. 2023.

Issue

Section

Original Article

Most read articles by the same author(s)

<< < 1 2 3 4