Shape Classification of Harumanis Mango using Discriminant Analysis (DA) and Support Vector Machine (SVM)

Authors

  • F. S. A. Sa'ad Centre of Excellence for Advanced Sensor Technology, Universiti Malaysia Perlis
  • M. F. Ibrahim Centre of Excellence for Advanced Sensor Technology, Universiti Malaysia Perlis
  • A. Y. Md. Shakaff Centre of Excellence for Advanced Sensor Technology, Universiti Malaysia Perlis
  • A. Zakaria Centre of Excellence for Advanced Sensor Technology, Universiti Malaysia Perlis
  • M. Z. Abdullah School of Electrical and Electronic Engineering, Universiti Sains Malaysia,
  • A. H. Adom Centre of Excellence for Advanced Sensor Technology, Universiti Malaysia Perlis

Abstract


The perceived quality of fruits, such as mangoes, is greatly dependent on many parameters such as ripeness, shape, size, and is influenced by other factors such as harvesting time. Unfortunately, a manual fruit grading has several drawbacks such as subjectivity, tediousness and inconsistency. By automating the procedure, as well as developing new classification technique, it may solve these problems. This paper presents the novel work on the using visible Imaging as a Tool in Quality Monitoring of Harumanis Mangoes. A Fourier-Descriptor method was developed from CCD camera images to grade mango by its shape. Discriminant analysis (DA) and Support vector machine (SVM) were applied for classification process and able to correctly classify 98.3% for DA and 100% for SVM.

Downloads

Published

2014-12-31

How to Cite

Sa’ad, F. S. A., Ibrahim, M. F., Md. Shakaff, A. Y., Zakaria, A., Abdullah, M. Z., & Adom, A. H. (2014). Shape Classification of Harumanis Mango using Discriminant Analysis (DA) and Support Vector Machine (SVM). Journal of Engineering and Technology (JET), 5(2), 93–104. Retrieved from https://jet.utem.edu.my/jet/article/view/170

Issue

Vol. 5 No. 2 (2014): JOURNAL OF ENGINEERING AND TECHNOLOGY

Section

Articles

License

Thank you for your interest in submitting your manuscript to the Journal of Engineering and Technology (JET).

JET publishes only original works. Manuscripts must not be previously published or under consideration by any other publications. Papers published in JET may not be published again in whole or in part without permission. Please review these guidelines for researching, writing, formatting and submitting your manuscript. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0).

Those submitting manuscripts should be carefully checked to ensure that all works contributed to the manuscript are acknowledged. The list of authors should include all those who can legitimately claim authorship. Manuscript should only be submitted for consideration once consent is given by all contributing authors using Transfer of Copyright form.