Klasifikasi Kematangan Buah Pisang Kepok dengan Perbandingan Metode CNN VGG16 dan LSTM
DOI:
https://doi.org/10.29407/rcath930Keywords:
Pisang Kepok, CNN, VGG16, LSTM, Klasifikasi KematanganAbstract
Pisang kepok merupakan salah satu komoditas hortikultura penting di Indonesia yang banyak dimanfaatkan sebagai bahan baku industri pangan. Tingkat kematangan pisang kepok sangat memengaruhi kualitas, umur simpan, serta nilai ekonominya. Penentuan kematangan secara manual masih bersifat subjektif dan tidak konsisten sehingga berpotensi menimbulkan kerugian pascapanen. Penelitian ini bertujuan untuk membandingkan performa metode Convolutional Neural Network (CNN) dengan arsitektur VGG16 dan Long Short-Term Memory (LSTM) dalam klasifikasi tingkat kematangan buah pisang kepok berbasis citra digital. CNN VGG16 digunakan untuk mengekstraksi fitur spasial citra, sedangkan LSTM digunakan untuk mempelajari pola sekuensial fitur. Hasil kajian berdasarkan penelitian terdahulu menunjukkan bahwa CNN VGG16 memberikan akurasi yang lebih tinggi dan stabil dibandingkan LSTM pada data citra statis. Dengan demikian, CNN VGG16 dinilai lebih sesuai untuk sistem klasifikasi kematangan pisang kepok berbasis pengolahan citra.
Downloads
References
[1] Upadhyay, A., Kumar, R., & Singh, P. (2022). Deep learning approaches for fruit quality assessment: A review. Journal of Food Engineering, 315, 110768. https://doi.org/10.1016/j.jfoodeng.2021.110768.
[2] Ferdaus, M. H., Rahman, M. S., & Islam, M. N. (2025). Local banana varieties and maturity detection using image processing techniques. International Journal of Agricultural Technology, 21(2), 455–468.
[3] Rahmad, C., Astiningrum, M., & Purnomo, N. B. (2019). Identifikasi dan prediksi tingkat kematangan pisang Candi dengan fitur warna dan tekstur menggunakan metode K-Nearest Neighbor. Jurnal Teknik Informatika, Politeknik Negeri Malang.
[4] Gill, S. S., Tuli, S., Xu, M., Singh, I., & Singh, P. (2022). A comparative study of CNN and LSTM for image-based classification. IEEE Access, 10, 112345–112360. https://doi.org/10.1109/ACCESS.2022.3187456.
[5] Chuquimarca, L., Villacís, J., & Andrade, M. (2025). Banana ripeness classification using convolutional neural network architectures. Computers and Electronics in Agriculture, 213, 108045. https://doi.org/10.1016/j.compag.2024.108045.
[6] Sintiya, C., Gunawan, E., Marpaung, D. R., Fa, F. R., & Sinaga, F. M. (2025). Pengembangan aplikasi deteksi kematangan buah pisang berbasis web menggunakan model CNN–LSTM. Jurnal Sifo Mikroskil, 26(1), 1–20. https://doi.org/10.55601/jsm.v26i1.1500.
[7] Suhendri, S., & Rahmad, C. (2021). Pengaruh cahaya dan kualitas citra dalam deteksi kematangan buah pisang menggunakan pengolahan citra digital. Jurnal MATRIK (Manajemen, Teknik Informatika, dan Rekayasa Komputer), 21(1), 1–10. https://doi.org/10.30812/matrik.v21i1.1396.
[8] Alfarisi, R. M., Thoriq, A., Ciptaningtyas, D., & Pratopo, L. H. (2024). Rancangan perangkat lunak berbasis image processing sebagai grading tingkat kematangan buah pisang Cavendish (Musa cavendishii). Prosiding Agropross – National Conference of Agriculture, Politeknik Negeri Jember.
[9] Zhou, J., Sun, D. W., Cheng, J. H., & Pu, H. (2004). Non-destructive detection of fruit quality and maturity using machine vision techniques. Journal of Food Engineering, 62(4), 389–398.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Muhammad Qoyyum
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution 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.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
