Image Optimization Technique Using Local Binary Pattern And Multilayer Perceptron Classification To Identify Potassium Deficiency In Cacao Plants Through Leaf Images

Andi Hildayanti; Muhammad Sya’rani Machrizzandi

doi:10.26740/vubeta.v2i1.34587

Authors

Andi Hildayanti Universitas Islam Negeri Alauddin Makassar
Muhammad Sya’rani Machrizzandi Universitas Islam Negeri Alauddin Makassar

DOI:

https://doi.org/10.26740/vubeta.v2i1.34587

Keywords:

Cocoa leaves, Local Binary Pattern, Multilayer Perceptron, Potassium Deficiency

Abstract

Cocoa plants (Theobroma cacao, L.) are the best plantation crops in Indonesia that play an important role in the economy. However, in cultivation, cocoa farmers often face problems that can cause a decrease in cocoa production, one of which is the lack of potassium nutrients. Therefore, how to implement digital image processing which can help analyze image objects in the form of normal leaf characteristics and potassium-deficient leaf characteristics using the Local Binary Pattern (LBP) method for image feature extraction and classified using the Multilayer Perceptron (MLP) method in identifying potassium deficiencies in cocoa plants based on their leaf characteristics. In the image object in the form of leaf characteristics, each will be identified with 250 in the background dataset and 100 in the non-background dataset. So that the feature extraction process by LBP can be analyzed using the MLP parameter approach in the form of variations in the Learning_rate network and several solvers. In the case study conducted as the methodology applied starting from data collection, algorithm development, to validation and measurement using ROC, it was found that the results of the study using the LBP method and MLP classification showed that the best accuracy results in testing the background dataset using the learning_rate network 10(-4) with Solver lbfgs were 86.66% and the best accuracy in testing the non-background dataset using the learning_rate network 10(-3) with Solver adam was 80.00%.

Author Biographies

Andi Hildayanti, Universitas Islam Negeri Alauddin Makassar

He is a lecturer in the Department of Information Systems, Universitas Islam Negeri Alauddin Makassar, Indonesia. He is received the BSc from Universitas Islam Negeri Alauddin Makassar, Indonesia in Informatics Engineering, Makassar in 2014. He is received the M.Eng from the STMIK Handayani in Computer Systems, Makassar in 2017. He is mainly researches in Internet of Things and web Software Applications, . He can be contacted at sya’rani.machrizzandi@uin-alauddin.ac.id.

Muhammad Sya’rani Machrizzandi, Universitas Islam Negeri Alauddin Makassar

She is a lecturer in the Department of Architecture, Universitas Islam Negeri Alauddin Makassar, Indonesia. He is received the BSc from the Hasanuddin University in Architecture, Makassar in 2012. She is received the M.Eng from the Sepuluh Nopember Institute of Technology (ITS) in Urban Design, Surabaya in 2015. She is mainly research in the Housing and Settlement Design, Urban Design, and Architecture. She can be contacted at email: andi.hildayanti@uin-alauddin.ac.id.

References

[1] I. M. Fahmid et al., “Downstreaming, Policy Supporting the Competitiveness of Indonesian Cocoa in the Global Market”, Frontiers in Sustainable Food Systems, vol. 6, 2022. doi: https://doi.org/10.3389/fsufs.2022.821330.

[2] L.D.M. Santos et al., “Production and Characterization of Kombucha-Like Beverage by Cocoa (Theobroma Cacao) by-Product as Raw Material”, Future Food, vol. 11, 2025. doi: https://doi.org/10.1016/j.fufo.2024.100528.

[3] İ. Atalar, A. Apaydın, C. Elmacı, T. ElObeid, and N. Konar, “Effect of different alkaline solutions in cocoa powder alkalization: Effects on pasteurized chocolate milk”, Applied Food Research, vol. 5, no. 1, 2025. doi: https://doi.org/10.1016/j.afres.2025.100692.

[4] S. Dröge et al.,”No Effect of Rainforest Alliance Cocoa Certification on Shade Cover and Bird Species Richness in Sulawesi, Indonesia”, Journal for Nature Conservation, vol. 84, 2025. doi: https://doi.org/10.1016/j.jnc.2025.126849.

[5] A.B. TunjungSari et al.,” Effects of Processing Methods of Unfermented Cocoa Beans From Indonesia on the Chemical and Physical Characteristics of Butter and Cake”, Journal of Agriculture and Food Research, vol. 19, 2025. doi: https://doi.org/10.1016/j.jafr.2024.101563.

[6] S. Zaid, Nasrul, W. Hamid, “Application of the Six Sigma Method to Improve the Quality of Cocoa Oil Industry Products in Southeast Sulawesi Province, Indonesia”, Journal of Global Innovations in Agricultural Sciences, vol. 13, no. 1, pp. 95-102, 2025. doi: https://doi.org/10.22194/JGIAS/25.1464.

[7] S. Dröge, L.B Prasetyo, B. Muys, “Acoustic Indices as Proxies for Biodiversity in Certified and Non-certified Cocoa Plantations in Indonesia”, Environmental Monitoring and Assessment, vol. 197, no. 1, 2025. doi: https://doi.org/10.1007/s10661-024-13441-0.

[8] S. Dröge et al., “From chocolate to palm oil: The future of Indonesia’s cocoa plantations”, Ambio, vol. 54, no. 1, pp. 152-161, 2025. doi: https://doi.org/10.1007/s13280-024-02061-0.

[9] A.B.T Sari et al., “Differentiation of Indonesian Specialty Cocoa (Theobroma cacao) Varieties and Origins using Phenolic Contents, Antioxidant Activities, and Spectrometric Fingerprints for Traceability”, Food Bioscience, vol. 62, 2024. doi: https://doi.org/10.1016/j.fbio.2024.105434.

[10] R. Ratnawati, A. Arfan, K. Jaya, and A. Annisa, “Potential of Cocoa Derived-Endophytic Fungi in the Biocontrol of Phytophthora Palmivora”, International Journal of Design and Nature and Ecodynamics, vol. 16, no. 6, pp. 2179-2185, 2025. doi: https://doi.org/10.18280/ijdne.190634.

[11] A. Asman, T. Iwanami, A. Rosmana, and N. Amin,”Assessing the Response of Local Cocoa Clones of South Sulawesi for Resistance to Dieback Disease Caused by Lasiodiplodia theobromae”, Journal of Phytopathology, vol. 172, no. 6, 2024. doi: https://doi.org/10.1111/jph.13424.

[12] Safaruddin, H. Iswoyo, M. Arsyad, and D. Salman, “Land Dynamics of Cocoa Plantations Towards Healthy Landscape”, International Journal of Sustainable Development and Planning, vol. 19, no. 7, pp. 2737-2744, 2024. doi: https://doi.org/10.18280/ijsdp.190730.

[13] P. Matous and Ö, Bodin, “Hub-and-Spoke Social Networks Among Indonesian Cocoa Farmers Homogenise Farming Practices”, People Nature, vol. 6, no. 2, pp. 598-609, 2024. doi: https://doi.org/10.1002/pan3.10578.

[14] M. U Bustami and S.P.O Werbrouck, “Cyclic Somatic Embryogenesis in Indonesian Elite Theobroma cacao L. Clones”, Horticulture, vol. 10, no.1, 2024. doi: https://doi.org/10.3390/horticulturae10010024.

15A.A. Sulaiman and A.H. Bahrun, “Agriculture Resource Conflict and Poverty of Cocoa Smallholders in Indonesia

[15] Borders: An Interpretative Structural Modelling”, Universal Journal of Agricultural Research, vol. 11, no. 6, pp. 1022-1031, 2023. doi: https://doi.org/10.13189/ujar.2023.110609.

[16] I. M. Fahmid et al., “Downstreaming” Policy Supporting the Competitiveness of Indonesian Cocoa in the Global Market”, Frontiers in Sustainable Food Systems, vol. 6, 2022. doi: https://doi.org/10.3389/fsufs.2022.821330.

[17] L. Pérez-Marulanda, M.R. Jepsen, A. Castro-Nunez, “Boosting the Adoption of Sustainable Land-Use Systems For Achieving Colombian Land-Based Climate Action and Peacebuilding Goals”, World Development, vol. 188, 2025. doi: https://doi.org/10.1016/j.worlddev.2024.106888.

[18] M.R. Dago et. al.,” What Motivates West African Cocoa Farmers to Value Trees? Taking the 4 W Approach to the Heart of the Field”, People and Nature, vol. 7, no.1, pp. 215-230, 2025. doi: https://doi.org/10.1002/pan3.10754.

[19] S M, R Nahon et al., “Impact of Agroforestry Practices on Soil Microbial Diversity and Nutrient Cycling in Atlantic Rainforest Cocoa Systems”, International Journal of Molecular Science, vol. 25, no. 21, 2024. doi : https://doi.org/10.3390/ijms252111345.

[20] L. Adet et al., “Genotypic Differences in Water Deficit Effects on Leaf and Crown Traits in Mature Field-Grown Cocoa”, Scientia Horticultura, vol. 325, 2024. doi : https://doi.org/10.1016/j.scienta.2023.112658.

[21] J. J Reyes-Pérez, R.A. Pincay-Ganchozo, M.D. Carrillo-Zenteno, K.Peña-Salazar, and W. Tezara, “Macronutrient Fertilization and Cadmium Absorption in Two Cocoa Clones”, Horticulturae, vol. 9, no.11, 2023. doi : https://doi.org/10.3390/horticulturae9111223.

[22] J. Milkereit, M. Burger, and A.K Hodson, “ Influence of Recycled Organic Waste Amendments on Carbon Pools, Greenhouse Gas Emissions, and Nematode Indicators of Soil Health”, Applied Soil Ecology, vol. 208, 2025. doi: https://doi.org/10.1016/j.apsoil.2025.105967.

[23] A. Cainglet, H. Postila, P.M. Rossi, A.K Ronkanen, and E. Heiderscheidt, “Influence of Coagulant Type on Nutrient Uptake of Plants and The Nutrient and Micropollutants Leaching from Anaerobically Digested Sludge Amended Soils”, Journal of Environmental Chemical Engineering, vol. 13, no. 2, 2025. doi : https://doi.org/10.1016/j.jece.2025.115346.

[24] L. Shuo et al., “Mechanisms of Phosphorus Conversion in Chicken Manure and Straw Composting Systems Regulated by Flax-Retting Wastewater and a Combination of Flax-Retting Wastewater and Biochar”, Chemical Engineering Journal, vol 507, 2025. doi: https://doi.org/110.1016/j.cej.2025.160773.

[25] L. He, Y. Zhao, X. Zhao, Y. Wang, and Q. Dan “Regulating Method of Microbial Driving the Phosphorus Bioavailability in Factory Composting”, Bioresource Technology, vol. 387, 2023. doi : https://doi.org/110.1016/j.biortech.2023.129676.

[26] S. Li et al., “Carbon-Containing Additives Changes the Phosphorus Flow by Affecting Humification and Bacterial Community During Composting”, Bioresource Technology, vol. 379, 2023. doi : https://doi.org/110.1016/j.biortech.2023.129066.

[27] J. Montenegro et al., “Molecular Response of Cocoa (Theobroma Cacao) to Water Deficit Conditions”, Journal of Animal and Plant Science, vol 33, no. 6, pp. 1314-1321, 2023. doi : https://doi.org/10.36899/JAPS.2023.6.0671.

[28] U. Khalid, B. Kaya, and M. Kaya, “Contrastive Self-Supervised Learning for Cocoa Disease Classification”, 10th International Conference on Smart Computing and Communication, pp. 413-416, 2024. doi : https://doi.org/10.1109/ICSCC62041.2024.10690626.

[29] R. Lloren, “Unveiling Ceratocystis Wilt Disease: a Review of Cocoa’s Unforgiving Foe”, IOP Conference Series: Earth and Environmental Science, vol. 1263, 2023. doi : https://doi.org/10.1088/1755-1315/1263/1/012008.

[30] R. Dong, A. Shiraiwa, and T. Hayashi, “A Simple Diagnostic Method for Citrus Greening Disease with Deep Learning”, Electronics and Communications in Japan, 2025. doi: https://doi.org/10.1002/ecj.12472.

[31] H. Yang et al., “Exploring Optimal Soil Moisture for Seedling Tomatoes Using Thermal Infrared Imaging and Chlorophyll Fluorescence Techniques”, Scientia Horticulturae, vol. 339, 2025. doi : https://doi.org/10.1016/j.scienta.2024.113846.

[32] Y. Wang et al., “Automatic Damage Identification of Sanskrit Palm Leaf Manuscripts with SegFormer”, Heritage Science, vol. 12, no. 1, 2024. doi : https://doi.org/10.1186/s40494-023-01125-w.

[33] V. Maß et al., “Development of a Digital Monitoring System for Fire Blight in Fruit Orchards”, Acta Horticulturae, vol. 1, no. 1412, 2024. doi : https://doi.org/10.17660/ActaHortic.2024.1412.60.

[34] V. Maß et al., “Annotated Image Dataset of Fire Blight Symptoms for Object Detection in Orchards”, Data in Brief, vol. 56, 2024. doi : https://doi.org/10.1016/j.dib.2024.110826.

[35] Z. Wang, Y. Jiang, A.B Diallo, A.B. Diallo, and S.W Kembel, “Deep Learning- and Image Processing-Based Methods for Automatic Estimation of Leaf Herbivore Damage”, vol. 15, no. 4, pp. 732-743, 2024. doi : https://doi.org/10.1111/2041-210X.14293.

[36] S. Saidah et al., “Comparative Analysis of LBP and CLBP Methods on Individual Recognition System Through Iris", JEPIN (Journal of Informatics Education and Research), vol. 6, no. 3, 2020. doi : https://doi.org/10.26418/jp.v6i3.41521.

[37] M. Irfan, B.A.A Sumbodo, and I. Candradewi, “Vehicle Classification System Based on Digital Image Processing with Multilayer Perceptron Method”. IJEIS, vol. 7, no. 2, pp. 139–148, 2017. doi : https://doi.org/10.1051/shsconf/202213903016.

[38] Y.D. Amerta, Y. A Sari, and P.P Adikara, “Food Recipe Search Based on Food Image Using Simple Morphological Shape Descriptors”, Cie L * A * B * Color Moment and Local Binary Pattern, vol. 3, no. 3, pp. 3028–3032, 2019.

[39] J. Ruiz de Miras et al., “Ultra-Fast Computation of Fractal Dimension for RGB Images”, Pattern Analysis and Applications, vol. 28, no. 1, 2025. doi: https://doi.org/10.1007/s10044-025-01415-y.

[40] X. Chen et al., “Coarse-To-Fine Text Injecting for Realistic Image Super-Resolution”, Neurocomputing, vol 626, 2025. doi : https://doi.org/10.1016/j.neucom.2025.129591.

[41] J.M Molina, J.P Llerena, L. Usero, and M.A Patricio, “Advances in Instance Segmentation: Technologies, Metrics And Applications In Computer Vision”, Neurocomputing, vol. 625, 2025. Doi : https://doi.org/10.1016/j.neucom.2025.129584.

[42] L. Cui et al., “Advances of Deep Learning Application in Qualitative And Quantitative Detection Of Road Subsurface Distress Using Ground Penetrating Radar: A Review”, Measurement: Journal of the International Measurement Confederation, vol. 247, 2025. doi : https://doi.org/10.1016/j.measurement.2025.116760.

[43] C. Pham, B. C. Kim, and H.S Shin, “Deep Learning-Based Identification of Rock Discontinuities on 3D Model of Tunnel Face”, Tunnelling and Underground Space Technology, vol. 158, 2025. doi : https://doi.org/10.1016/j.tust.2025.106403.

[44] A.M Udefi, S. Aina, A.R. Lawal, and A.I Oluwaranti, “A Comparative Analysis and Review of Techniques for African Facial Image Processing”, International Journal of Computing and Digital Systems, vol. 17, no. 1, 2025. doi: https://doi.org/10.12785/ijcds/1571020029.

[45] R. Ahamad and K. N Mishra, “Exploring Sentiment Analysis in Handwritten and E-Text Documents using Advanced Machine Learning Techniques: a Novel Approach”, Journal of Big Data, vol. 12, no. 11, 2025. doi : https://doi.org/10.1186/s40537-025-01064-2.

[46] H. Hezi, M. Gelber, A. Balabanov, Y.E Maruvka, and M. Freiman, “CIMIL-CRC: A Clinically-Informed Multiple Instance Learning Framework for Patient-Level Colorectal Cancer Molecular Subtypes Classification from H&E Stained Images”, Computer Methods and Programs in Biomedicine, vol. 259, 2025. doi : https://doi.org/10.1016/j.cmpb.2024.108513.