PRIYO UTOMO, TEGAR (2023) IMPLEMENTASI METODE WAVELET DAN BACKPROPAGATION NEURAL NETWORK PADA DETEKSI RETAK JALAN RAYA BERBASIS PENGOLAHAN CITRA. S1 thesis, Fakultas Teknik Universitas Sultan Ageng Tirtayasa.
![[img]](https://eprints.untirta.ac.id/style/images/fileicons/text.png) |
Text
Tegar Priyo Utomo_3332160055_Fulltext.pdf Download (1MB) |
|
Text
Tegar Priyo Utomo_3332160055_CP.pdf Download (5MB) |
|
Text
Tegar Priyo Utomo_3332160055_01.pdf Download (2MB) |
|
Text
Tegar Priyo Utomo_3332160055_02.pdf Download (2MB) |
|
Text
Tegar Priyo Utomo_3332160055_03.pdf Download (2MB) |
|
Text
Tegar Priyo Utomo_3332160055_04.pdf Download (2MB) |
|
Text
Tegar Priyo Utomo_3332160055_05.pdf Download (231kB) |
|
Text
Tegar Priyo Utomo_3332160055_Ref.pdf Download (638kB) |
|
Text
Tegar Priyo Utomo_3332160055_Lamp.pdf Download (2MB) |
Abstract
One method that can be used in image processing for crack detection is CNN. The amount of image data used in this study is 876 images consisting of 560 training data, 140 validation data, and 176 testing data. The CNN model architecture used consists of three convolution layers and three max pooling layers. In the training stage, the model is introduced to the image patterns of crocodile cracks, line cracks and no cracks and then validated. In the testing stage, the model classifies crocodile crack, line crack and no crack images. The accuracy of the model in the training stage is 96,43% and in the testing stage is 96,65%.
| Item Type: | Thesis (S1) | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
|||||||||
| Additional Information: | Salah satu metode yang dapat digunakan dalam pengolahan citra untuk deteksi retak adalah CNN. Jumlah data citra yang digunakan pada penelitian ini yaitu 876 citra yang terdiri dari 560 data pelatihan, 140 data validasi, dan 176 data pengujian. Arsitektur model CNN yang digunakan terdiri dari tiga lapisan konvolusi dan tiga lapisan max pooling. Tahap pelatihan, model dikenalkan dengan pola citra retak buaya, retak garis dan tidak retak kemudian divalidasi. Tahap pengujian, model mengklasifikasikan citra retak buaya, retak garis dan tidak retak. Tingkat akurasi model pada tahap pelatihan sebesar 96,43% dan pada tahap pengujian sebesar 96,65%. | |||||||||
| Subjects: | Q Science > Q Science (General) T Technology > T Technology (General) T Technology > TK Electrical engineering. Electronics Nuclear engineering |
|||||||||
| Divisions: | 03-Fakultas Teknik 03-Fakultas Teknik > 20201-Jurusan Teknik Elektro |
|||||||||
| Depositing User: | Mr Tegar Priyo Utomo | |||||||||
| Date Deposited: | 29 Sep 2023 14:34 | |||||||||
| Last Modified: | 29 Sep 2023 14:34 | |||||||||
| URI: | http://eprints.untirta.ac.id/id/eprint/30124 |
Actions (login required)
 |
View Item |