Evaluasi Kemampuan Kecerdasan Buatan Text-to-image dalam Mencitrakan Karakter Genetik pada Sifat Fenotipik Biji Kopi Robusta dan Arabika
DOI:
https://doi.org/10.31941/biofarm.v20i2.5326Abstract
Indonesia merupakan produsen kopi terbesar keempat di dunia. Produksi kopi robusta mendominasi jenis kopi yang dihasilkan, disusul oleh jenis kopi arabika. Dalam penyortiran biji kopi pada penentuan benih unggul dan kopi layak jual, diperlukan pengetahuan dan keterampilan untuk mengidentifikasi sifat fenotipe biji kopi yang berkualitas tinggi. Perkembangan kecerdasan buatan yang sangat pesat dapat menjadi peluang untuk digunakan dalam membantu memvisualisasikan biji kopi robusta dan arabika yang unggul. Penelitian ini bertujuan untuk menguji kecerdasan buatan text-to-image dalam mengubah narasi menjadi gambar yang menunjukkan biji kopi unggulan. Penelitian telah dilakukan dengan menggunakan dua prompt yang diujikan ke dalam tiga laman kecerdasan buatan text-to-image. Hasil visualisasi kemudian dievaluasi manual dengan menggunakan referensi rujukan. Evaluasi dilakukan terhadap karakteristik ukuran biji, bentuk, warna, morfologi alur tengah (sulkus), dan pola tekstur permukaan. Hasil penelitian menunjukkan bahwa ketiga laman kecerdasan buatan text-to-image tidak mampu melakukan visualisasi secara sempurna untuk menggambarkan sifat fenotipe biji kopi robusta dan arabika. Hal ini menunjukkan bahwa saat ini, ketiga macam laman kecerdasan buatan text-to-image tidak mampu mengolah prompt sesuai dengan referensi yang ada. Oleh karena itu, direkomendasikan untuk melakukan pengecekan ulang dalam penggunaan hasil kecerdasan buatan text-to-image dalam pengambilan keputusan, khususnya terkait penentuan kualitas biji kopi robusta dan arabika berdasarkan sifat renotip sebagai manifestasi genetik jenis tersebut.
References
Abduh, M. Y. (2018). dari ITB Untuk Indonesia: Biorefinery Kopi. Bandung: Pusat Penelitian Biosains dan Bioteknologi, Institut Teknologi Bandung.
Adiwijaya, N. O., Romadhon, H. I., Putra, J. A., & Kuswanto, D. P. (2022). The quality of coffee bean classification system based on color by using k-nearest neighbor method. In Journal of Physics: Conference Series (Vol. 2157, No. 1, p. 012034). IOP Publishing.
Akbar, M., Rachmawati, E., & Sthevanie, F. (2020). Visual feature and machine learning approach for arabica green coffee beans grade determination. In Proceedings of the 6th International Conference on Communication and Information Processing (pp. 97-104).
Boychev, D., & Cholakov, R. (2024). ImagiNet: A Multi-Content Dataset for Generalizable Synthetic Image Detection via Contrastive Learning. arXiv preprint arXiv:2407.20020.
Chin, Z. Y., Jiang, C. M., Huang, C. C., Chen, P. Y., & Chiu, W. C. (2023). Prompting4debugging: Red-teaming text-to-image diffusion models by finding problematic prompts. arXiv preprint arXiv:2309.06135.
Davis, A. P., Govaerts, R., Bridson, D. M., & Stoffelen, P. (2006). An annotated taxonomic conspectus of the genus Coffea (Rubiaceae). Botanical Journal of the Linnean Society, 152(4), 465-512.
Farah, A. (2012). Coffee constituents. Coffee: Emerging health effects and disease prevention, 1, 22-58.
Firmansyah, M. (2016). Analisis Daya Saing Ekspor Kopi Indonesia di Pasar Internasional.
Foong, T. Y., Kotyan, S., Mao, P. Y., & Vargas, D. V. (2023). The Challenges of Image Generation Models in Generating Multi-Component Images. arXiv preprint arXiv:2311.13620.
Gu, J., Wang, X., Li, C., Zhao, J., Fu, W., Liang, G., & Qiu, J. (2022). AI-enabled image fraud in scientific publications. Patterns, 3(7).
Jayakumari, B. N. B., Mambilamthoda, A. N. K., Stephen, S. A., Venkitesan, P., & Raghavendra, V. (2024). Coffee bean graded based on deep net models. International Journal of Electrical & Computer Engineering (2088-8708), 14(3).
Kammer, M. N. (2023). A Case Study in Artificial Intelligence-Generated Manuscripts. Chest, 164(2), 478-480.
Kristensen, T. (2004). Vulnerability Roundup: Lethal pictures. Network Security, 2004(10), 19-20.
Li, Z., Cao, M., Wang, X., Qi, Z., Cheng, M. M., & Shan, Y. (2024). Photomaker: Customizing realistic human photos via stacked id embedding. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 8640-8650).
Limongi, R. (2024). The use of artificial intelligence in scientific research with integrity and ethics. Future Studies Research Journal: Trends and Strategies, 16(1), e845-e845.
Martauli, E. D. (2018). Analysis of coffee production in Indonesia. JASc (Journal of Agribusiness Sciences), 1(2), 112-120.
Nugroho, S. A., Bagiatus, S., Setyoko, U., Fatimah, T., Novenda, I. L., & Pujiastuti, P. (2022). Pengaruh ZPT Nabati dan Media Tumbuh terhadap Pekembangan Kopi Robusta. Jurnal Biosense, 5(2), 62-76.
Nwakanma, O. (2010). The Image Maker. Wasafiri, 25(1), 75-81.
Özkan, M., & Sasani, H. (2023). Discussion on the Artificial Intelligence (AI) Tools Usage in the Scientific World. European Journal of Therapeutics, 29(4), 996-997.
Petrellis, N. (2021, July). Fish morphological feature recognition based on deep learning techniques. In 2021 10th International Conference on Modern Circuits and Systems Technologies (MOCAST) (pp. 1-4). IEEE.
Pise, D., Yadgiri, N., Gaikwad, P., Dusawar, Y., & Nandanwar, P. (2024). AI Image Generator. International Journal of Advanced Research in Science, Communication and Technology, 768-773.
Putra, A. I., Budisusanto, Y., & Deviantari, U. W. (2022). ANAlisis Produktivitas Kebun Kopi 2016–2019 dengan Metode Spasial Temporal (Studi Kasus: Seluruh Indonesia). Kokoh, 20(2), 71-84.
Sikandar, A. & Bahar, A. M. (2024). A comparative analysis to assess anatomical illustrations via three AI-Driven Text-to-Image generators. Eur. J. Anat., 28(5): 631-634.
Sun, Y., Chu, Z., Qin, Z., & Ren, K. (2024). Prompt-Consistency Image Generation (PCIG): A Unified Framework Integrating LLMs, Knowledge Graphs, and Controllable Diffusion Models. arXiv preprint arXiv:2406.16333.
Valles-Coral, M. A., Ivan Bernales-del-Aguila, C., Benavides-Cuvas, E., & Cabanillas-Pardo, L. (2023). Effectiveness of a cherry coffee sorter prototype with image recognition using machine learning. Brazilian Journal of Agricultural Sciences/Revista Brasileira de Ciências Agrárias, 18(1).
Wang, P., Li, Y., Singh, K. K., Lu, J., & Vasconcelos, N. (2021). Imagine: Image synthesis by image-guided model inversion. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 3681-3690).
Widyawati, R. F., Suliswanto, M. S. W., Febriana, H., & Abbas, M. H. I. (2024). The Effect of Land Area and Labor on Production of Coffee in Indonesia. KnE Social Sciences, 450-461.
Wintgens, J. N. (Ed.). (2012). Coffee-growing, processing, sustainable production: A Guidebook for Growers, Processors, Traders and researchers. John Wiley & Sons.
Wu, Y., Yu, N., Backes, M., Shen, Y., & Zhang, Y. (2023). On the proactive generation of unsafe images from text-to-image models using benign prompts. arXiv preprint arXiv:2310.16613.
Zhu, Y., Durand, T., Chenin, E., Pignal, M., Gallinari, P., & Vignes-Lebbe, R. (2017). Using a deep convolutional neural network for extracting morphological traits from herbarium images. Biodiversity Information Science and Standards, 1, e20400.
Downloads
Additional Files
Published
Issue
Section
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 a Creative Commons Attribution License that allows others to share the work with an acknowledgement 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 acknowledgement 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 (See The Effect of Open Access).
