Klasifikasi Kematangan Buah Pinang (Areca catechu L.) Menggunakan Hybrid Deep Feature Fusion dan XGBoost

Anggi; Nelly Khairani Daulay; Ahmad Sobri

doi:10.47065/bit.v7i2.2864

Anggi * Universitas Bina Insan Lubuklinggau, Indonesia
Nelly Khairani Daulay Universitas Bina Insan, Lubuk Linggau, Indonesia
Ahmad Sobri Universitas Bina Insan, Lubuk Linggau, Indonesia

DOI: https://doi.org/10.47065/bit.v7i2.2864

Keywords: Buah Pinang; Klasifikasi Citra; Deep Learning; Feature Fusion; ResNet50; EfficientNetB0; XGBoost

Abstract

Areca nut (Areca catechu L.) maturity is one of the factors affecting harvest quality. Visual maturity identification still has limitations because it can be influenced by observer subjectivity and environmental conditions. This study aims to classify areca nut maturity levels using a Hybrid Deep Feature Fusion approach by combining ResNet50 and EfficientNetB0 as feature extractors with XGBoost as the classification algorithm. The dataset used in this study was a primary dataset consisting of 1,200 areca nut images categorized into three maturity classes: unripe, semi-ripe, and ripe. The research stages included image preprocessing, feature extraction using CNN models, feature combination through feature concatenation, classification using XGBoost, and performance evaluation using accuracy, precision, recall, F1-score, confusion matrix, and 5-Fold Cross Validation. The experimental results showed that ResNet50 + XGBoost and Hybrid Deep Feature Fusion + XGBoost achieved accuracy, precision, recall, and F1-score values of 100%, while EfficientNetB0 + XGBoost achieved an accuracy of 99.16%. These results indicate that CNN-based features are able to represent the visual characteristics of areca nut images in the dataset used. The Hybrid Deep Feature Fusion approach provides an analysis of feature combination from two different CNN architectures, although increasing the feature dimensions does not always improve evaluation performance when a single feature extractor is already capable of representing dataset characteristics effectively. Future research can be conducted by increasing dataset variations to evaluate the generalization capability of the method under more diverse environmental conditions.

References

M. Rizzo, M. Marcuzzo, A. Zangari, A. Gasparetto, and A. Albarelli, “Fruit ripeness classification: A survey,” Artif. Intell. Agric., vol. 7, pp. 44–57, Mar. 2023, doi: 10.1016/j.aiia.2023.02.004.

E. Tapia-Mendez, I. A. Cruz-Albarran, S. Tovar-Arriaga, and L. A. Morales-Hernandez, “Deep Learning-Based Method for Classification and Ripeness Assessment of Fruits and Vegetables,” Appl. Sci., vol. 13, no. 22, p. 12504, Nov. 2023, doi: 10.3390/app132212504.

Z. Huang, D. M. Eugene, X. Li, X. Wang, and X. X. Romeiko, “A comprehensive review of quality measurements of fruits using electronic nose and computer vision,” Clean. Waste Syst., vol. 14, p. 100498, Jun. 2026, doi: 10.1016/j.clwas.2026.100498.

R. Szeliski, “Computer Vision: Algorithms and Applications, 2nd Edition”.

Z. Zhao, “Deep Learning for Fruit Ripeness Determination”.

Y. Shu, J. Zhang, Y. Wang, and Y. Wei, “Fruit Freshness Classification and Detection Based on the ResNet-101 Network and Non-Local Attention Mechanism,” Foods, vol. 14, no. 11, p. 1987, Jun. 2025, doi: 10.3390/foods14111987.

S. Ashari, G. J. Yanris, and I. Purnama, “Oil Palm Fruit Ripeness Detection using Deep Learning,” Sinkron, vol. 7, no. 2, pp. 649–656, May 2022, doi: 10.33395/sinkron.v7i2.11420.

K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” Dec. 10, 2015, arXiv: arXiv:1512.03385. doi: 10.48550/arXiv.1512.03385.

M. Tan and Q. V. Le, “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks,” Sep. 11, 2020, arXiv: arXiv:1905.11946. doi: 10.48550/arXiv.1905.11946.

L. P. Nur’aini and M. Rahardi, “Detection of Ripeness in Oil Palm Fresh Fruit Bunches Using the YOLO12S Algorithm on Digital Images,” vol. 9, no. 4.

P. M. Naik and B. Rudra, “X-ArecaNet: Dataset of arecanut X-ray images for deep learning applications,” Data Brief, vol. 61, p. 111721, Aug. 2025, doi: 10.1016/j.dib.2025.111721.

S. Patil, A. Naik, and J. Parab, “Efficient Deep Learning model for de-husked Areca nut classification,” J. Appl. Nat. Sci., vol. 15, no. 4, pp. 1529–1540, Dec. 2023, doi: 10.31018/jans.v15i4.5067.

M. D. Jamil et al., “Improved early-stage crop classification using a novel fusion-based machine learning approach with Sentinel-2A and Landsat 8–9 data,” Environ. Monit. Assess., vol. 197, no. 9, p. 982, Aug. 2025, doi: 10.1007/s10661-025-14420-9.

L. Wittstruck, T. Jarmer, and B. Waske, “Multi-Stage Feature Fusion of Multispectral and SAR Satellite Images for Seasonal Crop-Type Mapping at Regional Scale Using an Adapted 3D U-Net Model,” Remote Sens., vol. 16, no. 17, p. 3115, Aug. 2024, doi: 10.3390/rs16173115.

B. Xiao, “Fruit Ripeness Identification From Digital Images Using Deep Learning”.

“MSFF: Multi-Scale feature fusion for fine-grained image classification,” Acad. J. Comput. Inf. Sci., vol. 6, no. 2, 2023, doi: 10.25236/AJCIS.2023.060215.

H. O. Ilhan, G. Serbes, and N. Aydin, “Decision and feature level fusion of deep features extracted from public COVID-19 data-sets,” Appl. Intell., vol. 52, no. 8, pp. 8551–8571, Jun. 2022, doi: 10.1007/s10489-021-02945-8.

T. Chen and C. Guestrin, “XGBoost: A Scalable Tree Boosting System,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco California USA: ACM, Aug. 2016, pp. 785–794. doi: 10.1145/2939672.2939785.