Analisis Komparatif Arsitektur Convolutional Neural Network untuk Klasifikasi Kualitas Cabai dengan Implementasi Perangkat Mobile
-
Nur Ikhsanudin
*
Universitas Dian Nuswantoro, Semarang,
Indonesia
- Muhamad Akrom Universitas Dian Nuswantoro, Semarang, Indonesia (*) Corresponding Author
Abstract
Manual chili quality sorting is susceptible to subjectivity and inter-assessor inconsistency, which can reduce product market value. This study conducts a comparative analysis of three Convolutional Neural Network (CNN) architectures—Custom CNN, MobileNetV3-Small, and EfficientNetV2-B0 for binary chili quality classification (Good/Bad) using a primary dataset of 1,383 chili images (684 Good-class, 699 Bad-class) captured with a smartphone camera. The Good class includes chili with a smooth surface, fresh color, and no decay spots, while the Bad class includes chili showing signs of decay, physical defects, or deformation. Evaluation was conducted based on accuracy, precision, recall, F1-Score, AUC, inference time, and post-quantization model size. The results show that EfficientNetV2-B0 achieved the highest accuracy of 92.0% (precision 92.4%, recall 92.0%, F1-Score 92.0%, AUC 0.961), MobileNetV3-Small obtained an accuracy of 87.7% with the lowest server-side inference latency (2.39 ms), and Custom CNN achieved 87.3% accuracy with the most compact model size (118 KB post-quantization). All three models were integrated into a Flutter-based Android application prototype as a proof-of-concept, displaying the classification result (Good/Bad), confidence score, and inference latency, with end-to-end response times ranging from 80 to 120 ms on a Xiaomi 13T device. This study contributes empirical comparative data on three CNN architectures in the chili quality classification domain, accompanied by the construction of a local dataset and technical validation of model deployment on a mobile device. The results of this study are expected to serve as a reference in selecting CNN architecture for the development of a mobile-based chili quality classification system, particularly as a first step toward the implementation of simple small-scale sorting at the farmer level.
Downloads
References
Y. A. Azis, N. Khuriyati, and A. Suyantohadi, “Classification of Dried Chilli Quality Using Image Processing,” IOP Conf. Ser. Earth Environ. Sci., vol. 686, no. 1, p. 012058, Mar. 2021, doi: 10.1088/1755-1315/686/1/012058.
M. A. Aziz, W. M. Arif Mohamad Nazir, A. M. Ali, and J. Abawajy, “Chili Ripeness Grading Simulation Using Machine Learning Approach,” in Proc. IEEE Int. Conf. Comput. (ICOCO), pp. 253–258, 2021, doi: 10.1109/ICOCO53166.2021.9673572.
D. S. Anggraeni, A. Widayana, P. D. Rahayu, and C. Rozikin, “Metode Algoritma Convolutional Neural Network pada Klasifikasi Penyakit Tanaman Cabai,” STRING (Satuan Tulisan Riset dan Inovasi Teknologi), vol. 7, no. 1, pp. 73–78, Aug. 2022, doi: 10.30998/string.v7i1.13304.
Y. Adiyantari, M. Rifki, B. Ulum, B. Rahmat, and M. H. P. Swari, “Implementasi Metode CNN Dan K-Nearest Neighbor Untuk Klasifikasi Tingkat Kematangan Tanaman Cabai Rawit,” Modem : Jurnal Informatika dan Sains Teknologi, vol. 2, no. 3, pp. 112–123, Jul. 2024, doi: 10.62951/modem.v2i3.131.
U. Mahdiyah, L. S. Wahyuniar, and S. Rochana, “Klasifikasi Kualitas Citra Cabai Dengan Menggunakan Algoritma Gradien Boosting,” JAMI: Jurnal Ahli Muda Indonesia, vol. 4, no. 1, pp. 58–66, Jun. 2023, doi: 10.46510/jami.v4i1.137.
N. Arifin, C. N. Insani, M. Milasari, and M. F. Rasyid, “Horticulture Smart Farming for Enhanced Efficiency in Industry 4.0 Performance,” Jurnal Teknik Informatika (Jutif), vol. 5, no. 5, pp. 1405–1412, Oct. 2024, doi: 10.52436/1.jutif.2024.5.5.2728.
D. Li, C. Zhang, J. Li, M. Li, M. Huang, and Y. Tang, “MCCM: Multi-Scale Feature Extraction Network for Disease Classification and Recognition of Chili Leaves,” Front. Plant Sci., vol. 15, p. 1367738, May 2024, doi: 10.3389/fpls.2024.1367738.
S. Rahman, R. A. Setyadi, A. Indrawati, A. Sembiring, and M. Zen, “Improving the Accuracy of Chili Leaf Disease Classification with ResNet and Fine-Tuning Strategy,” Int. J. Adv. Comput. Sci. Appl., vol. 15, no. 10, pp. 247–255, Oct. 2024, doi: 10.14569/IJACSA.2024.0151027.
D. Bhatt et al., “CNN Variants for Computer Vision: History, Architecture, Application, Challenges and Future Scope,” Electronics, vol. 10, no. 20, p. 2470, Oct. 2021, doi: 10.3390/electronics10202470.
S. Tai, Z. Tang, B. Li, S. Wang, and X. Guo, “Intelligent Recognition and Automated Production of Chili Peppers: A Review Addressing Varietal Diversity and Technological Requirements,” Agriculture, vol. 15, no. 11, p. 1200, May 2025, doi: 10.3390/agriculture15111200.
D. Liandaputra and A. Zahra, “Classification of Pineapple (Ananas comosus l.) Maturity Level Using Deep Learning Method,” G-Tech: Jurnal Teknologi Terapan, vol. 8, no. 2, pp. 1091–1103, Apr. 2024, doi: 10.33379/gtech.v8i2.4122.
R. Saktriawindarta and K. Kusrini, “Methods for Classifying Fruit and Vegetable Ripe Levels: A Systematic Review,” G-Tech: Jurnal Teknologi Terapan, vol. 8, no. 4, pp. 2344–2354, Oct. 2024, doi: 10.70609/gtech.v8i4.5067.
Sudianto, Y. Herdiyeni, A. Haristu, and M. Hardhienata, “Chilli Quality Classification Using Deep Learning,” in Proc. 2020 Int. Conf. Comput. Sci. Appl. Agric. (ICOSICA), Sep. 2020, doi: 10.1109/ICOSICA49951.2020.9243176.
M. Khoiruddin and S. Tena, “Fruit and Vegetable Classification Using Convolutional Neural Network with MobileNetV2,” J. Appl. Res. Comput. Sci. Inf. Syst., vol. 2, no. 2, pp. 203–210, Dec. 2024, doi: 10.61098/jarcis.v2i2.197.
Z. Ibrahim, M. Hanafi, S. M. Shafie, and S. M. Syed Ahmad, “Classification of C. annuum and C. frutescens Ripening Stages: How Well Does Deep Learning Perform?,” IIUM Engineering Journal, vol. 25, no. 2, pp. 167–178, Jul. 2024, doi: 10.31436/iiumej.v25i2.2769.
S. Winiarti and I. I. Khoirunnisa, “Mobile Application Development for Chili Disease Detection with Convolutional Neural Network,” International Journal of Informatics and Computation, vol. 6, no. 2, pp. 97–112, Dec. 2024, doi: 10.35842/ijicom.v6i2.93.
M. Setiono, “Klasifikasi Penyakit Antraknosa Citra Cabai Rawit Dengan Metode Convolutional Neural Network (CNN),” JATISI, vol. 11, no. 2, pp. 308–320, Jun. 2024, doi: 10.35957/jatisi.v11i2.8039.
T. R. Yudantoro, M. Djaeni, R. R. Isnanto, and Prayitno, “Deep Learning Models Performance for Classifying Dried Chili Based on Digital Image Analysis,” JOIV : International Journal on Informatics Visualization, vol. 9, no. 5, pp. 1951–1963, Sep. 2025, doi: 10.62527/joiv.9.5.2919.
S. Mahdiyyah et al., “Implementasi Object Detection untuk Deteksi Kualitas pada Buah Lemon dengan CNN,” Jurnal Riset dan Aplikasi Mahasiswa Informatika (JRAMI), vol. 6, no. 1, pp. 215–223, Jan. 2025, doi: 10.30998/jrami.v6i01.13417.
A. Howard et al., “Searching for MobileNetV3,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), pp. 1314–1324, Oct. 2019, doi: 10.1109/ICCV.2019.00140.
M. Tan and Q. V. Le, “EfficientNetV2: Smaller Models and Faster Training,” in Proc. Int. Conf. Mach. Learn. (ICML), vol. 139, pp. 10096–10106, Jul. 2021, doi: 10.48550/arXiv.2104.00298.
H. Talebi and P. Milanfar, “Learning to Resize Images for Computer Vision Tasks,” Proceedings of the IEEE International Conference on Computer Vision, pp. 487–496, Oct. 2021, doi: 10.1109/ICCV48922.2021.00055.
F. Zhuang et al., “A Comprehensive Survey on Transfer Learning,” Proceedings of the IEEE, vol. 109, no. 1, pp. 43–76, Jan. 2021, doi: 10.1109/JPROC.2020.3004555.
B. Jacob et al., “Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 2704–2713, Dec. 2018, doi: 10.1109/CVPR.2018.00286.
A. Gholami, S. Kim, Z. Dong, Z. Yao, M. W. Mahoney, and K. Keutzer, “A Survey of Quantization Methods for Efficient Neural Network Inference,” Low-Power Computer Vision, pp. 291–326, Jan. 2022, doi: 10.1201/9781003162810-13.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Analisis Komparatif Arsitektur Convolutional Neural Network untuk Klasifikasi Kualitas Cabai dengan Implementasi Perangkat Mobile
Pages: 2439−2450
Copyright (c) 2026 Nur Ikhsanudin, Muhamad Akrom
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
