NISA’, CHILYATUN (2021) KLASIFIKASI CITRA PENYAKIT DAUN APEL DENGAN ALGORITMA CONVOLUTIONAL NEURAL NETWORK. Undergraduate thesis, UPN"VETERAN" JATIM.
|
Text (COVER)
Cover.PDF Download (1MB) | Preview |
|
|
Text (BAB 1)
1.PDF Download (139kB) | Preview |
|
![[img]](http://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (BAB 2)
21.PDF Restricted to Repository staff only Download (2MB) |
|
|
Text (BAB 3)
3.PDF Restricted to Repository staff only Download (1MB) |
|
|
Text (BAB 4)
4.PDF Restricted to Repository staff only Download (2MB) |
|
|
Text (BAB 5)
5.PDF Download (129kB) | Preview |
|
|
Text (DAFTAR PUSTAKA)
Dapus.PDF Download (190kB) | Preview |
|
|
Text (LAMPIRAN)
Lam.PDF Restricted to Repository staff only Download (140kB) |
Abstract
Apple plant (Malus sylvestris) is one of the become an economic commodity. According to fruit production data in Indonesia, apple production in 2017 decreased by 3.3% from 2016. This was caused by various diseases that often occur in apple production, especially the leaves. Various ways have been done to detecting apple leaf disease, one of which is by doing image processing digital. In this study, the author proposes the Convolutional Neural Algorithm Network (CNN) as feature extractor and leaf color image classifier Apple. CNN was chosen because it can perform effective image feature classification klasifikasi and automated than traditional feature extraction methods. Datasets used is Plant Pathology 2020 - FGV C7. The dataset contains four categories images based on the type of apple leaf disease, namely healthy, multiple diseases, rust, and scab with a total of 1,821 data. Image data is preprocessed first before entering the classification stage, the CNN algorithm is trained on the training data and performance testing on test data with a ratio of 70:30 of the total data. The result is CNN which has 8, 16, 32 filters in the convolution layer and 1024 nodes in the hidden layer perform best if compared to CNN which has a number of filters and other nodes. This matter evidenced by the average precision value of 0.88, the recall value of 0.7925, and the F1-score of 0.83 and the test accuracy value of 92%. Keywords: Classification, Convolutional Neural Network Algorithm, Processing Digital Image, Apple Leaf Disease, Apple Leaf Disease Detection System
| Item Type: | Thesis (Undergraduate) | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||
| Subjects: | Q Science > QA Mathematics > QA76.76.E95 Expert Systems | ||||||||
| Divisions: | Faculty of Computer Science > Departemen of Informatics | ||||||||
| Depositing User: | Mujari Mujari | ||||||||
| Date Deposited: | 22 Jun 2021 03:02 | ||||||||
| Last Modified: | 22 Jun 2021 03:11 | ||||||||
| URI: | http://repository.upnjatim.ac.id/id/eprint/2082 |
Actions (login required)
 |
View Item |