Palm oil classification using deep learning

Saleh, Abdulrazak Yahya; Liansitim, Ermawatih

doi:10.31763/sitech.v1i1.1

Cited by 18 publications

(22 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Non-destructive techniques for ripeness classification of FFBs are field and lab spectroscopy (Che Man et al, 1999;Kasemsumran et al, 2012;, computer vision (Hussain et al, 2019;Lecun et al, 2015;Onoja et al, 2019;Saleh and Liansitim, 2020), digital image processing (Choong et al, 2006;Gibon et al, 2009;Sunilkumar and Babu, 2013), hyperspectral analysis (Bensaeed et al, 2014;Junkwon et al, 2009), optical sensing (Utom et al, 2018), inductive frequency technique (Harun et al, 2013), laser-light backscattering imaging (Mohd Ali et al, 2020) and fruit battery (Misron et al, 2020a).…”

Section: P R E S Smentioning

confidence: 99%

“…CNN relies on the huge number of layers with a complex structure which allows it to process complex data. CNN is commonly used as a classifier to grade FFBs (Onoja et al, 2019;Saleh and Liansitim, 2020).…”

Section: Computer Visionmentioning

confidence: 99%

“…CNN is used as a classifier of the ripeness of FFBs which identifies the colour feature of each class. The model reached 96% of training accuracy and 97% of validation accuracy (Saleh and Liansitim, 2020). Ibrahim et al (2018) used a similar method of classifying oil palm fruits using CNN.…”

Section: Computer Visionmentioning

confidence: 99%

See 2 more Smart Citations

A Review of Non-Destructive Ripeness Classification Techniques for Oil Palm Fresh Fruit Bunches

MANSOUR¹

2022

JOPR

View full text Add to dashboard Cite

Grading of oil palm fresh fruit bunches (FFB) is commonly conducted using visual inspection by trainedworkers who inspect the oil palm FFB according to the colour and the number of the loose fruits on the ground. However, this method is labour intensive and time consuming. In addition, the workers may misclassify the fruit's ripeness due to the height of the tree, miscounting the loose fruits, unclear vision of the bunches on the tree and lighting conditions. Unripe or overripe bunches result in a less efficient palm oil refining process, low palm oil quality and profit losses. Non-destructive techniques can offer better solutions for ripeness classifications with higher accuracy. The techniques are field and lab spectroscopy, computer vision, hyperspectral imaging, laser-light backscattering imaging and fruit battery sensor. Spectroscopy, hyperspectral imaging and laser-light backscattering imaging techniques need to be deployed with a special set up which may not be suitable for real-time ripeness classification. Computer vision, using image processing techniques and machine learning algorithms allow real-time in-situ ripeness classification via mobile devices. This article aims to review the feasibility of each method to allow real-time in-situ ripeness classification of the oil palm fruit bunches with high accuracy.

show abstract

Section: P R E S Smentioning

confidence: 99%

Section: Computer Visionmentioning

confidence: 99%

See 1 more Smart Citation

A Review of Non-Destructive Ripeness Classification Techniques for Oil Palm Fresh Fruit Bunches

MANSOUR¹

2022

JOPR

View full text Add to dashboard Cite

show abstract

“…Raw data (without labels) can be processed and accepted for the clustering process. This method is different from supervised learning [26] [27], which receives input in the form of vectors (x-1, y1), (x2, y2), …, (xi , yi), where xi is data of the training data and yi is the class label for xi. This method is very popular, fast, and simple [28].…”

Section: K-means Clusteringmentioning

confidence: 99%

K-Means Clustering for Egg Embryo's Detection Based-on Statistical Feature Extraction Approach of Candling Eggs Image

Saifullah

2020

Sinergi

View full text Add to dashboard Cite

This research discusses the detection of embryonic eggs using the k-means clustering method based on statistical feature extraction. The processes that occur in detection are image acquisition, image enhancement, feature extraction, and identification/detection. The data used consisted of 200 egg image data, consisting of 100 test data and 100 new test data. The acquisition process uses a smartphone camera by capturing candled egg objects. The results of image acquisition become a reference in the process of image enhancement and feature extraction using Statistical Feature Extraction. The statistical feature extraction applied is the Gray Level Co-occurrence Matrix (GLCM) method, which consists of 6 features, namely Energy, Contrast, Entropy, Variance, Correlation, and Homogeneity. The results of feature extraction (6 features) are grouped by the K-means Clustering method. The clustering process uses Euclidean distance calculations to determine the proximity of features. The results of grouping and testing give the best average results with an accuracy of ≈ 74% from several test samples.

show abstract

“…Table 1 shows different ripeness classification methods for oil palm FFBs. Convolution neural network (CNN) (Ibrahim et al, 2018;Saleh & Liansitim, 2020;Arulnathan et al, 2022), achieved accuracies of 92-97%. However, the models consisted of a few CNN layers (one or two layers) and would not be able to capture the high-level features.…”

Section: Introductionmentioning

confidence: 99%

Object Detection Algorithms for Ripeness Classification of Oil Palm Fresh Fruit Bunch

Mansour¹,

Dambul²,

Choo³

2022

IJTech

View full text Add to dashboard Cite

Ripe oil palm fresh fruit bunch allows extraction of high-quality crude palm oil and kernel palm oil. As the fruit ripens, its surface color changes from black (unripe) or dark purple (unripe) to dark red (ripe). Thus, the surface color of the oil palm fresh fruit bunches may generally be used to indicate the maturity stage. Harvesting is commonly done by relying on human graders to harvest the bunches according to color and number of loose fruits on the ground. Non-destructive methods such as image processing and computer vision, including object detection algorithms have been proposed for the ripeness classification process. In this paper, several object detection algorithms were investigated to classify the ripeness of oil palm fresh fruit bunch. MobileNetV2 SSD, EfficientDet (Lite0, Lite1 and Lite2) and YOLOv5 (YOLOv5n, YOLOv5s and YOLOv5m) were simulated and compared in terms of their mean average precision, recall, precision and training time. The models were trained on a dataset with four main ripeness classes: ripe, unripe, half-ripe, and over-ripe. In conclusion, object detection algorithms can be used to classify different ripeness levels of oil palm fresh fruit bunch, and among the different models, YOLOv5m showed promising results with a mean average precision of 0.842 (0.5:0.95).

show abstract

Palm oil classification using deep learning

Cited by 18 publications

References 13 publications

A Review of Non-Destructive Ripeness Classification Techniques for Oil Palm Fresh Fruit Bunches

A Review of Non-Destructive Ripeness Classification Techniques for Oil Palm Fresh Fruit Bunches

K-Means Clustering for Egg Embryo's Detection Based-on Statistical Feature Extraction Approach of Candling Eggs Image

Object Detection Algorithms for Ripeness Classification of Oil Palm Fresh Fruit Bunch

Contact Info

Product

Resources

About