Computer vision and artificial intelligence (AI)-based ripeness classification of oil palm fruits in oil palm plantations
Palm oil is one of the most important export products, and Malaysia is the world’ssecond-largest exporter of palm oil. Before the invention of technology, the ripenessof the oil palm fruit bunches was assessed through a traditional method involvingpersonnel with considerable expertise in such identi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Karya Ilham Publishing
2025
|
| Subjects: | |
| Online Access: | https://umpir.ump.edu.my/id/eprint/45504/ |
| _version_ | 1848827436089737216 |
|---|---|
| author | Chong, Wei Han Nor Azuana, Ramli Wan Mohd Rozaimi, Wan Mustafa Lilik Jamilatul, Awalin |
| author_facet | Chong, Wei Han Nor Azuana, Ramli Wan Mohd Rozaimi, Wan Mustafa Lilik Jamilatul, Awalin |
| author_sort | Chong, Wei Han |
| building | UMP Institutional Repository |
| collection | Online Access |
| description | Palm oil is one of the most important export products, and Malaysia is the world’ssecond-largest exporter of palm oil. Before the invention of technology, the ripenessof the oil palm fruit bunches was assessed through a traditional method involvingpersonnel with considerable expertise in such identification processes. However, it wasvery time-consuming and was accompanied by human error that resulted in poordecision-making in the harvesting, thereby cutting down the yields. These challengesare solved in this research through the incorporation of a Convolutional NeuralNetwork (CNN) model, which is in the deep learning (DL) domain of artificialintelligence (AI). The main goal of this research is to establish an AI-based system withthe help of Google Teachable Machine (GTM) to classify the ripeness of the oil palmfruit bunches. Data for this research was obtained from Google Images and samplesduring a site visit in Negeri Sembilan, Malaysia. Posterior performance measures wereobtained, and an evaluation was made on the pre-trained model after model trainingby measuring the confusion matrix and accuracy, as well as accuracy per epoch and theloss per epoch. Before the images are fed to the modelling process, they undergopreprocessing for image enhancement, resizing, and annotation. This researchconfirmed that GTM could classify the ripeness stage with an overall accuracy of 98%.This research could help shorten the harvesting period and increase the volume of theoil palm fruit bunches produced. It is also intricately linked to the SustainableDevelopment Goals (SDGs), specifically SDG 12: Responsible Consumption andProduction, allowing for mainly proper identification of ripeness, thus enabling lesswastage, optimisation of resource use, and support of sustainable agriculture. |
| first_indexed | 2025-11-15T04:00:41Z |
| format | Article |
| id | ump-45504 |
| institution | Universiti Malaysia Pahang |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T04:00:41Z |
| publishDate | 2025 |
| publisher | Karya Ilham Publishing |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | ump-455042025-08-28T06:31:56Z https://umpir.ump.edu.my/id/eprint/45504/ Computer vision and artificial intelligence (AI)-based ripeness classification of oil palm fruits in oil palm plantations Chong, Wei Han Nor Azuana, Ramli Wan Mohd Rozaimi, Wan Mustafa Lilik Jamilatul, Awalin QA75 Electronic computers. Computer science Palm oil is one of the most important export products, and Malaysia is the world’ssecond-largest exporter of palm oil. Before the invention of technology, the ripenessof the oil palm fruit bunches was assessed through a traditional method involvingpersonnel with considerable expertise in such identification processes. However, it wasvery time-consuming and was accompanied by human error that resulted in poordecision-making in the harvesting, thereby cutting down the yields. These challengesare solved in this research through the incorporation of a Convolutional NeuralNetwork (CNN) model, which is in the deep learning (DL) domain of artificialintelligence (AI). The main goal of this research is to establish an AI-based system withthe help of Google Teachable Machine (GTM) to classify the ripeness of the oil palmfruit bunches. Data for this research was obtained from Google Images and samplesduring a site visit in Negeri Sembilan, Malaysia. Posterior performance measures wereobtained, and an evaluation was made on the pre-trained model after model trainingby measuring the confusion matrix and accuracy, as well as accuracy per epoch and theloss per epoch. Before the images are fed to the modelling process, they undergopreprocessing for image enhancement, resizing, and annotation. This researchconfirmed that GTM could classify the ripeness stage with an overall accuracy of 98%.This research could help shorten the harvesting period and increase the volume of theoil palm fruit bunches produced. It is also intricately linked to the SustainableDevelopment Goals (SDGs), specifically SDG 12: Responsible Consumption andProduction, allowing for mainly proper identification of ripeness, thus enabling lesswastage, optimisation of resource use, and support of sustainable agriculture. Karya Ilham Publishing 2025-06-03 Article PeerReviewed pdf en cc_by_nc_4 https://umpir.ump.edu.my/id/eprint/45504/1/AAIJV1_N2_P44_58.pdf Chong, Wei Han and Nor Azuana, Ramli and Wan Mohd Rozaimi, Wan Mustafa and Lilik Jamilatul, Awalin (2025) Computer vision and artificial intelligence (AI)-based ripeness classification of oil palm fruits in oil palm plantations. ASEAN Artificial Intelligence Journal, 2 (1). pp. 44-58. ISSN 3083-9971. (Published) https://doi.org/10.37934/aaij.2.1.4458 https://doi.org/10.37934/aaij.2.1.4458 https://doi.org/10.37934/aaij.2.1.4458 |
| spellingShingle | QA75 Electronic computers. Computer science Chong, Wei Han Nor Azuana, Ramli Wan Mohd Rozaimi, Wan Mustafa Lilik Jamilatul, Awalin Computer vision and artificial intelligence (AI)-based ripeness classification of oil palm fruits in oil palm plantations |
| title | Computer vision and artificial intelligence (AI)-based ripeness classification of oil palm fruits in oil palm plantations |
| title_full | Computer vision and artificial intelligence (AI)-based ripeness classification of oil palm fruits in oil palm plantations |
| title_fullStr | Computer vision and artificial intelligence (AI)-based ripeness classification of oil palm fruits in oil palm plantations |
| title_full_unstemmed | Computer vision and artificial intelligence (AI)-based ripeness classification of oil palm fruits in oil palm plantations |
| title_short | Computer vision and artificial intelligence (AI)-based ripeness classification of oil palm fruits in oil palm plantations |
| title_sort | computer vision and artificial intelligence (ai)-based ripeness classification of oil palm fruits in oil palm plantations |
| topic | QA75 Electronic computers. Computer science |
| url | https://umpir.ump.edu.my/id/eprint/45504/ https://umpir.ump.edu.my/id/eprint/45504/ https://umpir.ump.edu.my/id/eprint/45504/ |