Rico Andrian, RA and Saipul Anwar, SA and Meizano Ardhi Muhammad, MAM and Akmal Junaidi, Akmal Identifikasi Kupu-Kupu Menggunakan Ekstraksi Fitur Deteksi Tepi (Edge Detection) dan Klasifikasi K-Nearest Neighbor (KNN). Jurnal Teknik Informatika dan Sistem Informasi (JuTISI). ISSN 2443-2229

[img] Text

Download (24kB)
Official URL: https://journal.maranatha.edu/index.php/jutisi/ind...


Lampung has the only breeding site of butterflies in Indonesia namely Gita Persada Butterfly Park, which has approximately 211 butterfly species. Butterflies can be classified according to patterns found on the wings of a butterfly. Butterfly species have different patterns based on pigment, the structure of the scales and the fall of sunlight. The weakness of the human eye in distinguishing patterns on butterflies is the foundation in building butterfly identification based on pattern recognition. This study uses 6 species of butterflies: Papilio memnon, Troides helena, Papilio nephelus, Cethosia penthesilea, Papilio peranthus, and Pachliopta aristolochiae. The butterfly dataset used is 600 images form of the upper wing side. The pre-processing stage uses the method of scaling, segmentation, and grayscale. The feature extraction stage uses the canny edge detection method by applying smoothing, edge strength, edge direction, non-maximum suppression, and hysteresis threshold. The classification phase uses the K-Nearest Neighbor (KNN) method with values k = 1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21 and 23 obtained under the Rule of Thumb. The identification of butterfly requires a classification time of 8 seconds. The highest accuracy is obtained from testing with a value of k = 5 by 80%.

Item Type: Article
Subjects: Q Science > QA Mathematics
Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Fakultas Matematika dan Ilmu Pengetahuan Alam (FMIPA) > Prodi Ilmu Komputer
Depositing User: Rico Andrian
Date Deposited: 27 Nov 2019 08:47
Last Modified: 27 Nov 2019 08:47
URI: http://repository.lppm.unila.ac.id/id/eprint/17167

Actions (login required)

View Item View Item