Implementasi Pengolahan Citra Untuk Identifikasi Daun Tanaman Obat Menggunakan Levenberg-Marquardt Backpropagation
Digital Image processing implementation can be applied to identify medicinal leaves, because it can help the elderly and people with color-blindness in identifying medicinal leave to be consumed and in avoiding reading errors, since some leaves have similar shape and color . In this discussion, the...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | Indonesian |
| Published: |
Jurusan Teknik Elektro Politeknik Negeri Padang
2021-06-01
|
| Series: | Elektron |
| Subjects: | |
| Online Access: | https://jie.pnp.ac.id/index.php/jie/article/view/176 |
| Summary: | Digital Image processing implementation can be applied to identify medicinal leaves, because it can help the elderly and people with color-blindness in identifying medicinal leave to be consumed and in avoiding reading errors, since some leaves have similar shape and color . In this discussion, the feature-extractions are using color and shape features, and using Levenberg-Marquardt for pattern recognition algorithm. The success of this medicinal plant identification system resulted in fairly good accuracy. The backpropagation network architecture used two hidden layers with 10 and 5 neurons. Data training is using 60 training leaf images with 15 images each of 5 types: green betel leaf, red betel, soursop, castor and aloe vera. Then, offline testing is using 20 test images for each of 4 images from 5 types with the accuracy of 85%. Meanwhile the online (realtime) test is using 20 times for each leaf types so the accuracy is 88%. |
|---|---|
| ISSN: | 2085-6989 2654-4733 |