Rizky, Aquar Alan (2017) Identifikasi Parameter Varietas Benih Tomat Menggunakan Machine Vision Dan Metode Artificial Neural Network (ANN). Sarjana thesis, Universitas Brawijaya.
Abstract
Penelitian ini bertujuan mengidentifikasi varietas benih tomat yang beredar di masyarakat menggunakan NNPred dan memberikan informasi mengenai Artificial Neural Network (ANN) serta mengetahui parameter gambar terhadap benih tomat. Penelitian ini terdiri dari beberapa tahapan yaitu: akuisisi citra, pengolahan data citra, penyusunan model dan NN-pred (Neural Network Prediction). Akuisisi citra menggunakan scanner canon pixma MP237 dengan resolusi 600 dpi sebanyak 500 gambar masing-masing varietas benih tomat sebanyak 100 gambar. Pengolahan citra dilakukan untuk memperbaiki resolusi citra sehingga gambar yang dipakai memiliki resolusi sama yaitu 526 x 526 piksel dengan format bitmap (.bmp) dan mengestrak data citra pada program feature extraction. Setelah itu didapatkan kombinasi nilai warna nilai red, green, blue, gray, hue, s(HSL), s(HSV), L*, a*, b* dari energy, entrophy, contrast, homogenity, invers, corelation, sum mean, variance, cluster, dan max probability. Selanjutnya proses penyusunan model dan NN-pred (Neural Network Prediction). Menggunakan ANN dibuat 2 model yaitu model 1 dengan 10 parameter input dan model 2 dengan 12 parameter input. Kedua model dipakai untuk menghasilkan nilai MSE terkecil. Hasil penelitian menunjukkan untuk model 1 laju pembelajaran 0,7 dan momentum 0,3 sedangkan model 2 laju pembelajaran 0,2 dan momentum 0,2. kedua model tersebut menggunakan data total sebanyak 500 dan menggunakan validasi 10% sehingga diperoleh hasil untuk model 1 nilai MSE validasi terkecil tiap varietas benih tomat terdapat pada warna lab_L sebesar 0.001 dan ARE 2,28%, pada model 2 nilai MSE validasi terkecil untuk tiap varietas benih tomat terdapat pada tekstur max.probability sebesar 0.001 dan ARE 3,05%.
English Abstract
The objective of this research is to identify the varieties of tomato seeds that circulate in the community using NNPred and provide information about Artificial Neural Network (ANN) and know the parameters of the image of the tomato seeds. This study consists of several stages: image acquisition, image data processing, modeling and NN-pred (Neural Network Prediction). Image acquisition using Canon Pixma MP237 scanner with a resolution of 600 dpi of 500 images each variety of tomato seed as many as 100 pictures. Image processing is done to improve the resolution of the image so that the image used has the same resolution that is 526 x 526 pixels with a bitmap format (.bmp) and extract the image data to the feature extraction program. After it, it obtained value combination of color red, green, blue, gray, hue, s (HSL), s (HSV), L *, a *, b * of energy, entrophy, contrast, homogenity, inverse, Correlation, sum mean , variance, cluster, and probability max. The next process is modelling and NNpred. Using ANN created 2 models of model 1 with 10 input parameters and model 2 with 12 input parameters. Both models are used to produce the smallest MSE value. The results showed for the first model of learning rate of 0,7 and 0,3 momentum while model 2 learning rate of 0,2 and 0,2 momentum. both models use the data using a total of 500 and 10% in order to obtain validation results for model 1 validation smallest MSE value each variety of tomato seeds contained in the color of lab_L 0,001 and ARE is 2,28%, in model 2 the smallest MSE value validation for each variety tomato seeds contained in the texture max.probability of 0001 and ARE is 3.05%.
Other obstract
-
| Item Type: | Thesis (Sarjana) |
|---|---|
| Identification Number: | SKR/FTP/2017/154/051703097 |
| Uncontrolled Keywords: | Artificial Neural Network, benih tomat, features extraction, machine vision |
| Subjects: | 300 Social sciences > 338 Production > 338.1 Agriculture |
| Divisions: | Fakultas Teknologi Pertanian > Keteknikan Pertanian |
| Depositing User: | Kustati |
| Date Deposited: | 30 Mar 2017 15:24 |
| Last Modified: | 17 Nov 2021 05:26 |
| URI: | http://repository.ub.ac.id/id/eprint/151383 |
Preview |
Text
1._Cover.pdf Download (1MB) | Preview |
Preview |
Text
3._BAB_1.pdf Download (1MB) | Preview |
Preview |
Text
2._Lembar_judul_-_kata_pengantar.pdf Download (1MB) | Preview |
Preview |
Text
6._BAB_4.pdf Download (2MB) | Preview |
Preview |
Text
5._BAB_3.pdf Download (2MB) | Preview |
Preview |
Text
4._BAB_2.pdf Download (2MB) | Preview |
Preview |
Text
7._BAB_5.pdf Download (1MB) | Preview |
Preview |
Text
9._Lampiran.pdf Download (11MB) | Preview |
Preview |
Text
8._Daftar_Pustaka.pdf Download (1MB) | Preview |
Actions (login required)
 |
View Item |