Zafar, Ahmad (2025) IMPLEMENTASI ALGORITMA CONVOLUTIONAL NEURAL NETWORK (CNN) PADA SISTEM KLASIFIKASI BUNGA ANGGREK. S1 / D3 thesis, Universitas Kuningan.
ABSTRAK.pdf
Download (1MB)
BAB I.pdf
Download (1MB)
BAB II.pdf
Restricted to Repository staff only
Download (804kB) | Request a copy
BAB III.pdf
Restricted to Repository staff only
Download (1MB) | Request a copy
BAB IV.pdf
Restricted to Repository staff only
Download (749kB) | Request a copy
BAB V.pdf
Download (357kB)
DAFTAR PUSTAKA.pdf
Download (285kB)
LAMPIRAN.pdf
Restricted to Repository staff only
Download (2MB) | Request a copy
Abstract
Penelitian ini bertujuan untuk mengembangkan sistem klasifikasi jenis bunga anggrek menggunakan algoritma Convolutional Neural Network (CNN). Tiga jenis anggrek yang diklasifikasikan dalam penelitian ini adalah Dendrobium, Phalaenopsis, dan Vanda. Proses klasifikasi dilakukan melalui tahapan pengumpulan data, pra-pemrosesan citra, pelatihan model CNN, dan evaluasi performa menggunakan metrik seperti precision, recall, dan f1-score. Hasil pengujian menunjukkan bahwa model CNN yang dibangun mampu mengklasifikasikan gambar bunga anggrek dengan akurasi tinggi. Kelas Vanda memperoleh nilai f1-score tertinggi sebesar 95,89%, diikuti oleh Dendrobium sebesar 85,49%, dan Phalaenopsis sebesar 84,36%. Beberapa kendala dalam klasifikasi masih ditemukan, terutama pada gambar dengan pencahayaan rendah, sudut pengambilan yang ekstrem, serta latar belakang yang bervariasi. Secara keseluruhan, sistem ini menunjukkan kinerja yang baik dalam membedakan ketiga jenis bunga anggrek yang diuji
This research aims to develop an orchid flower type classification system using the Convolutional Neural Network (CNN) algorithm. The three types of orchids classified in this research are Dendrobium, Phalaenopsis, and Vanda. The classification process is carried out through the stages of data collection, image pre-processing, CNN model training, and performance evaluation using metrics such as precision, recall, and f1-score. The test results show that the CNN mode built is able to classify orchid flower images with high accuracy. The Vanda class obtained the highest f1-score value of 95.89%, followed by Dendrobium at 85.49%, and Phalaenopsis at 84.36%. Some classification problems were still encountered, especially in images with low lighting, extreme capture angles, and varied backgrounds. Overall, the system showed good performance in distinguishing between the three types of orchid flowers tested.
| Item Type: | Thesis (S1 / D3) |
|---|---|
| Uncontrolled Keywords: | Klasifikasi bunga anggrek, pengolahan citra digital, Convolutional Neural Network, orchid flower classification, Deep Learning, digital image processing. |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software |
| Divisions: | Fakultas Ilmu Komputer > S1 Teknik Informatika |
| Depositing User: | S.Kom Ahmad Zafar |
| Date Deposited: | 25 Sep 2026 01:15 |
| Last Modified: | 25 Sep 2026 01:15 |
| URI: | https://rama.uniku.ac.id/id/eprint/6838 |

