Deteksi Kekurangan Unsur Hara Pada Tanaman Padi Dengan Metode Linear Vector Quantization (LVQ) Berdasar Pada Citra Daun

Sulastri, Miftakhul Janah (2021) Deteksi Kekurangan Unsur Hara Pada Tanaman Padi Dengan Metode Linear Vector Quantization (LVQ) Berdasar Pada Citra Daun. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

Text 06111740000053-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2023. Download (4MB) | Request a copy

Abstract

Pada tahun 2019 hasil produksi padi mengalami penurunan yang cukup besar, salah satunya disebabkan oleh faktor cuaca yang menyebabkan kekeringan pada lahan, sehingga serapan unsur hara yang diberikan pada tanaman padi tidak maksimal. Melihat perkembangan di bidang teknologi citra, peneliti menggunakan image processing dan computer vision untuk mengetahui ketersediaan unsur hara yang terdapat pada citra daun tanaman padi, dengan mengaplikasikan metode ekstraksi ciri pada warna, tekstur, dan bentuk. Ekstraksi fitur menghasilkan 6 nilai ciri yang selanjutnya digunakan untuk deteksi dengan dua variasi metode Learning Vector Quantization (LVQ) yaitu LVQ 1 dan LVQ 2. Deteksi pengujian dilakukan dengan menggunakan citra daun padi tanpa penambahan noise dan dengan penambahan noise. Deteksi tersebut pada tugas akhir ini mampu mengenali citra tanaman padi kekurangan unsur hara N, P, dan K yang memiliki akurasi sebesar 87,5% pada nilai maxEpoch 50 dan learning rate 0,1 menggunakan variasi metode LVQ 1 dengan kondisi tanpa penambahan noise.
======================================================================================================
In 2019 the yield of rice production experienced a considerable decline, one of which was caused by weather factors that caused drought in the land, so that the absorption of nutrients given to rice plants was not optimal. Seeing developments in the field of image technology, researchers used image processing and computer vision to determine the availability of nutrients contained in the image of rice leaves, by applying feature extraction methods to color, texture, and shape. Feature extraction produces 6 feature values which are then used for detection with two variations of the Learning Vector Quantization (LVQ) method, namely LVQ 1 and LVQ 2. Detection testing is carried out using rice leaf images without the addition of noise and with the addition of noise. The detection in this final project is able to recognize the image of rice plants lacking nutrients N, P, and K which has an accuracy of 87.5% at a maxEpoch value of 50 and a learning rate of 0.1 using a variation of the LVQ 1 method with conditions without the addition of noise.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	citra daun padi, ekstraksi ciri, image processing, learning vector quantization. feature extraction, image processing, learning vector quantization, rice leaf image
Subjects:	Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science) S Agriculture > SB Plant culture S Agriculture > SB Plant culture > SB409.58 Plant propagation. Including in vitro propagation T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing--Digital techniques
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Mathematics > 44201-(S1) Undergraduate Thesis
Depositing User:	Miftakhul Janah Sulastri
Date Deposited:	25 Aug 2021 06:06
Last Modified:	25 Aug 2021 06:06
URI:	http://repository.its.ac.id/id/eprint/89639

Actions (login required)

View Item