A Comprehensive Methodology for Image Recognition Utilizing Machine Learning and Computer Vision: Automation of the Harvesting Process
Nadia Adibah Rajab1, Nor Asmaa Alyaa Nor Azlan2, Wong Kuan Yew3, Adi Saptari4, Effendi Mohamad5
1Nadia Adibah Rajab, Department of Materials Manufacturing and Industrial Engineering, Faculty of Mechanical Engineering, Universiti Teknologi Malaysia, Johor Bahru, Malaysia.
2Dr. Nor Asmaa Alyaa Nor Azlan, Department of Materials Manufacturing and Industrial Engineering, Faculty of Mechanical Engineering, Universiti Teknologi Malaysia, Johor Bahru, Malaysia.
3Prof. Dr. Wong Kuan Yew, Department of Materials Manufacturing and Industrial Engineering, Faculty of Mechanical Engineering, Universiti Teknologi Malaysia, Johor Bahru, Malaysia.
4Prof. Dr. Adi Saptari, Department of Industrial Engineering, President University, J1 KiHajar Dewantara, Kota Jababeka, Cikarang Baru, Bekasi.
5Dr. Effendi Mohamad, Faculty of Industrial and Manufacturing Technology and Engineering, Universiti Teknikal Malaysia Melaka, Jalan Hang Tuah Jaya, Melaka, Malaysia.
Manuscript received on 27 September 2024 | Revised Manuscript received on 06 October 2024 | Manuscript Accepted on 15 November 2024 | Manuscript published on 30 November 2024 | PP: 7-12 | Volume-13 Issue-12, November 2024 | Retrieval Number: 100.1/ijitee.K999413111024 | DOI: 10.35940/ijitee.K9994.13121124
Open Access | Editorial and Publishing Policies | Cite | Zenodo | OJS | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This study aims to investigate the machine learning techniques implemented in image recognition technology for the identification and classification of oil palm fruit ripeness. The accurate determination of fruit ripeness is crucial for optimizing harvest time and improving oil yield. The palm oil industry is one of the major plantations in Malaysia. The harvesting process of oil palm fruit was conducted with traditional methods by relying on manual inspection, which can be subjective and inconsistent. Plus, it required several workers. A model of image recognition was developed using machine learning algorithms and computer vision to automate the harvesting process and overcome the shortage of labor issues. Implementing this technology in the field could lead to more consistent harvests and higher-quality oil production. Several machine learning models were developed, trained, and tested for their ability to classify the ripeness stages. The findings suggest the trending techniques in implementing image recognition which can provide a reliable and efficient tool for assessing oil palm fruit ripeness.
Keywords: Palm Oil Fruit Ripeness Classification, Image Recognition, Machine Learning, Deep Learning.
Scope of the Article: