Article Per Year (5 Year)
p-Index From 2020 - 2025
0.702
P-Index
This Author published in this journals
All Journal JURNAL PENGABDIAN KEPADA MASYARAKAT J-SAKTI (Jurnal Sains Komputer dan Informatika) J-SAKTI (Jurnal Sains Komputer dan Informatika)
Maftukhah, Ainin
Unknown Affiliation
Arts Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Energy Languange, Linguistic, Communication & Media Social Sciences

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : J-SAKTI (Jurnal Sains Komputer dan Informatika)

 1 
Segmentasi Citra Kupu-Kupu Menggunakan Metode Multilevel Thresholding Maftukhah, Ainin; Fadlil, Abdul; Sunardi, S
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 7, No 2 (2023): EDISI SEPTEMBER
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v7i2.665

Abstract

Land conversion, pollution, logging, and the use of pesticides are the main causes of butterfly extinction. This used 50 types of butterflies using different RGB colors obtained from the Kaggle website. The goal is to separate the butterfly object from the background and produce the best accuracy from the segmentation proses. The method used is Multilevel Thresholding. The results of preprocessing on the image using Multilevel Thresholding segmentation are able to identify colors and butterfly objects. The first step is RGB image input, then the image is Segmented using Multilevel Thresholding. After that, the output is displaying the image, and using a threshold value of 0-255 with the results of image segmentation, the threshold value separates the object and the background. Multilevel Thresholding segmentation with color and shape identification obtains threshold values of 100 from the dataset train, 100, and 110 from the test dataset and 140, and 150 from the validation dataset. It was concluded that the results of threshold value of the Multilevel Thresholding segmentation obtained good results
Co-Authors Abdul Fadlil Rusydi Umar S Sunardi Subandi, Rio