AbstrakSemua tanaman, termasuk kopi membutuhkan unsur hara yang cukup untuk penunjang pertumbuhan dan perkembangannya secara normal. Apabila kebutuhan hara tidak tercukupi dengan baik, tanaman akan kekurangan suplai makanan dan gejala khas muncul pada tanaman, seperti perubahan ukuran daun, klorosis, nekrosis dan lainnya yang akan terlihat jelas terutama pada organ daun. Gejala – gejala tersebut memberikan ciri khas atau pola pada daun berdasarkan defisiensi hara yang dialami suatu tanaman. Ciri khas tersebut kemudian diekstraksi menggunakan pengolahan citra digital (PCD) dengan menerapkan Multi Texton Cooccurrence Descriptor (MTCD). Metode MTCD akan melakukan penelusuran pada tiap bagian citra, kemudian mengekstrak piksel – piksel yang memiliki kesamaan nilai warna dan tepi. Fitur-fitur hasil ekstraksi digunakan untuk mewakili setiap citra dalam basis data, dan kemudian digunakan untuk klasifikasi dengan menerapkan jaringan saraf tiruan (JST). Hasil akurasi tertinggi yang dihasilkan klasifikasi adalah 0.706. Kata kunci: Defisiensi Hara, PCD, MTCD, JST AbstractAll plants, including coffee, need enough nutrients to support their normal growth and development. If nutrient needs are not fulfilled properly, plants will lack of food supply and typical symptoms appear in plants, such as changes in leaf size, chlorosis, necrosis and others that will be clearly visible, especially in leaf organs. These symptoms give a characteristic or pattern to the leaves based on nutrient deficiencies experienced by a plant. Then these characteristics are extracted using digital image processing (DIP) by applying Multi Texton Cooccurrence Descriptor (MTCD). The MTCD method will search for each part of the image, then extract pixels that have the same color and edge values. Extracted features are used to represent each image in the database, and then used for classification by applying artificial neural networks (ANN). The highest accuracy of the resulting classification is 0.706. Keywords: Nutrient Deficiency, DIP, MTCD, ANN
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.