Implementasi Multi-View Convolutional Neural Network untuk Klasifikasi Kualitas Buah Jambu Kristal
Kata Kunci:
visi komputer, klasifikasi gambar, MVCNN, jambu kristalAbstrak
Jambu kristal atau Psidium Guajava merupakan buah yang umum dibudidayakan di negara-negara tropis, seperti India, Indonesia, Bangladesh, dan Amerika Selatan, dan banyak digunakan untuk kebutuhan industri. Dalam industri, menjaga standar kualitas buah di tahap produksi merupakan suatu tantangan yang membutuhkan perhatian khusus. Kelelahan dan keterampilan pekerja yang bervariasi membuat proses penilaian menjadi tidak konsisten. Untuk meningkatkan pengendalian kualitas pada buah, diperlukan sebuah sistem yang dapat melakukan pengecekan kualitas secara konsisten dan efisien. Pembuatan sistem ini memiliki tantangan tersendiri, informasi yang diberikan oleh satu sisi yang ditangkap oleh kamera tidak cukup untuk mengetahui kualitas buah. Untuk mengatasi tantangan di atas, penelitian ini akan membuat sistem klasifikasi kualitas jambu kristal menggunakan Multi-View Convolutional Neural Network yang menerima input gambar dari dua view, atas dan bawah. Hasil dari penelitian adalah model dengan loss, akurasi, dan f1-score yang mencapai 0.194, 0.91, 0.93. Dengan melakukan pengurangan lapisan max-pooling sebanyak 1 di akhir, model mengalami peningkatan performa dengan loss, akurasi, dan f1-score yang mencapai 0.193, 0.93, 0.94.
Referensi
Akanda, Md. K.M. et al., 2018. A short review on a Nutritional Fruit : Guava. ResearchGate [Preprint]. https://www.researchgate.net/publication/330702066_A_short_review_on_a_Nutritional_Fruit_Guava.
ASEAN, 2008. ASEAN STANDARD FOR GUAVA. https://asean.org/wp-content/uploads/2012/05/7-ASEAN-STANDARD-FOR-GUAVA-2008.pdf (Accessed: October 25, 2023).
Bader, F. & Rahmifard, S., 2020. A methodology for the selection of industrial robots in food handling. Innovative Food Science and Emerging Technologies, 64, p. 102379. https://doi.org/10.1016/j.ifset.2020.102379.
Bobde, S. et al., 2021. Fruit Quality Recognition using Deep Learning Algorithm. 2021 International Conference on Smart Generation Computing, Communication and Networking (SMART GENCON) [Preprint]. https://doi.org/10.1109/smartgencon51891.2021.9645793.
Chen, Y. et al., (2021) 'A Deep Learning-Based vision system combining detection and tracking for fast On-Line citrus sorting,' Frontiers in Plant Science, 12. https://doi.org/10.3389/fpls.2021.622062.
Dadgar, A., Baleghi, Y. & Ezoji, M. 2022. Multi-view data fusion in multi-object tracking with probability density-based ordered weighted aggregation. Optik, 262, p. 169279. https://doi.org/10.1016/j.ijleo.2022.169279.
Dube, A., Satankar, N. & Pratibha, P. 2021. Rich medicinal qualities of poor man’s apple- Psidium guajava L. Journal of Pharmacognosy and Phytochemistry, 10(2), pp. 807–810.
He, K. et al. 2015. Deep Residual Learning for Image Recognition. Microsoft Research. https://doi.org/10.48550/arXiv.1512.03385.
Kanwal, N., Randhawa, M. & Iqbal, Z. 2016. A Review of Production, Losses and Processing Technologies of Guava. Asian Journal of Agriculture and Food Sciences, 4(2). https://www.researchgate.net/publication/338823595_A_Review_of_Production_Losses_and_Processing_Technologies_of_Guava.
Luo, L., 2021. Research on image classification algorithm based on convolutional neural network. Journal of Physics, 2083(3), p. 032054. https://doi.org/10.1088/1742-6596/2083/3/032054.
Purwono, P. et al., 2023. Understanding of Convolutional Neural Network (CNN): a review. International Journal of Robotics and Control Systems, 2(4), pp. 739–748. https://doi.org/10.31763/ijrcs.v2i4.888.
Seeland, M. & Mäder, P., 2021. Multi-view classification with convolutional neural networks. PLOS ONE, 16(1), p. e0245230. https://doi.org/10.1371/journal.pone.0245230.
Shi, X. et al., 2022. Vision-based apple quality grading with multi-view spatial network. Computers and Electronics in Agriculture, 195, p. 106793. https://doi.org/10.1016/j.compag.2022.106793.
Sun, L. et al., 2019. Multi-View convolutional neural networks for mammographic image classification. IEEE Access, 7, 126273–126282. https://doi.org/10.1109/access.2019.2939167.
Uzair, M., & Jamil, N., 2020. Effects of Hidden Layers on the Efficiency of Neural networks. 2020 IEEE 23rd International Multitopic Conference (INMIC), 1–6. https://doi.org/10.1109/inmic50486.2020.9318195.
Yamashita, R. et al., 2018. Convolutional neural networks: an overview and application in radiology. Insights Into Imaging, 9(4), pp. 611–629. https://doi.org/10.1007/s13244-018-0639-9.
Yan, X. et al., 2021. Deep multi-view learning methods: A review. Neurocomputing, 448, pp. 106–129. https://doi.org/10.1016/j.neucom.2021.03.090.
Akanda, Md. K.M. et al., 2018. A short review on a Nutritional Fruit : Guava. ResearchGate [Preprint]. https://www.researchgate.net/publication/330702066_A_short_review_on_a_Nutritional_Fruit_Guava.
ASEAN, 2008. ASEAN STANDARD FOR GUAVA. https://asean.org/wp-content/uploads/2012/05/7-ASEAN-STANDARD-FOR-GUAVA-2008.pdf (Accessed: October 25, 2023).
Bader, F. & Rahmifard, S., 2020. A methodology for the selection of industrial robots in food handling. Innovative Food Science and Emerging Technologies, 64, p. 102379. https://doi.org/10.1016/j.ifset.2020.102379.
Bobde, S. et al., 2021. Fruit Quality Recognition using Deep Learning Algorithm. 2021 International Conference on Smart Generation Computing, Communication and Networking (SMART GENCON) [Preprint]. https://doi.org/10.1109/smartgencon51891.2021.9645793.
Chen, Y. et al., (2021) 'A Deep Learning-Based vision system combining detection and tracking for fast On-Line citrus sorting,' Frontiers in Plant Science, 12. https://doi.org/10.3389/fpls.2021.622062.
Dadgar, A., Baleghi, Y. & Ezoji, M. 2022. Multi-view data fusion in multi-object tracking with probability density-based ordered weighted aggregation. Optik, 262, p. 169279. https://doi.org/10.1016/j.ijleo.2022.169279.
Dube, A., Satankar, N. & Pratibha, P. 2021. Rich medicinal qualities of poor man’s apple- Psidium guajava L. Journal of Pharmacognosy and Phytochemistry, 10(2), pp. 807–810.
He, K. et al. 2015. Deep Residual Learning for Image Recognition. Microsoft Research. https://doi.org/10.48550/arXiv.1512.03385.
Kanwal, N., Randhawa, M. & Iqbal, Z. 2016. A Review of Production, Losses and Processing Technologies of Guava. Asian Journal of Agriculture and Food Sciences, 4(2). https://www.researchgate.net/publication/338823595_A_Review_of_Production_Losses_and_Processing_Technologies_of_Guava.
Luo, L., 2021. Research on image classification algorithm based on convolutional neural network. Journal of Physics, 2083(3), p. 032054. https://doi.org/10.1088/1742-6596/2083/3/032054.
Purwono, P. et al., 2023. Understanding of Convolutional Neural Network (CNN): a review. International Journal of Robotics and Control Systems, 2(4), pp. 739–748. https://doi.org/10.31763/ijrcs.v2i4.888.
Seeland, M. & Mäder, P., 2021. Multi-view classification with convolutional neural networks. PLOS ONE, 16(1), p. e0245230. https://doi.org/10.1371/journal.pone.0245230.
Shi, X. et al., 2022. Vision-based apple quality grading with multi-view spatial network. Computers and Electronics in Agriculture, 195, p. 106793. https://doi.org/10.1016/j.compag.2022.106793.
Sun, L. et al., 2019. Multi-View convolutional neural networks for mammographic image classification. IEEE Access, 7, 126273–126282. https://doi.org/10.1109/access.2019.2939167.
Uzair, M., & Jamil, N., 2020. Effects of Hidden Layers on the Efficiency of Neural networks. 2020 IEEE 23rd International Multitopic Conference (INMIC), 1–6. https://doi.org/10.1109/inmic50486.2020.9318195.
Yamashita, R. et al., 2018. Convolutional neural networks: an overview and application in radiology. Insights Into Imaging, 9(4), pp. 611–629. https://doi.org/10.1007/s13244-018-0639-9.
Yan, X. et al., 2021. Deep multi-view learning methods: A review. Neurocomputing, 448, pp. 106–129. https://doi.org/10.1016/j.neucom.2021.03.090.
Unduhan
Diterbitkan
Cara Mengutip
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2024 Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Artikel ini berlisensiCreative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
