Segmentasi Citra Luka Luar Berbasis Warna Menggunakan Teknik Active Contour

Syifa’ah Setya Mawarni(1*), M Murinto(2), S Sunardi(3),

(1) Universitas Ahmad Dahlan, Yogyakarta, Indonesia
(2) Universitas Ahmad Dahlan, Yogyakarta, Indonesia
(3) Universitas Ahmad Dahlan, Yogyakarta, Indonesia
(*) Corresponding Author

Abstract


Wounds are often underestimated by many people because sometimes all they feel is a little sore and a little bleeding. Unknowingly, wounds can cause infection which causes swelling of the skin and requires long treatment for healing. The purpose of this research is to build educational media for external wound recognition by performing image segmentation in determining wound detection using Active Contour.In the image processing process, the pre-processing stage is carried out to improve the image by removing noise. The success of image recovery was measured using MSE and PSNR values which in this study resulted in MSE = 0.1495 and PSNR = 56.43 with Uniform noise identification and a median low-pass filter of 3x3. Image processing using the Acive Contour technique can segment external wound images well using Matlab 2018b as a tool for image processing and uses 278 wound datasets with details of 59 data on burns, 85 data on abrasions, 111 data on lacerations, and 23 data on stab wounds.

Full Text:

PDF

References


K. Ryan, Wound Care: Nursing and Health Survival Guides, New York: Rouledge, 2014.

A. Pamungkas, "Segmentasi Citra," Januari 2018. [Online]. Available: https://pemrogramanmatlab.com/pengolahan-citra-digital/segmentasi-citra/#trackbacks. [Accessed 14 Maret 2023].

V. M. Sutama, Identifikasi Objek Dominan Citra Digital Menggunakan Metode Makrov Random Field (MFR), Bandung: Universitas Telkom, 2018.

M. Ickhsan, Implementasi Metode Segmentasi Active Contour Untuk Memperjelas Tepi Pada CItra Penyakit Paru-paru, vol. VIII, pp. 357-360, 2020.

R. Muliriasari dan Murinto, Analisis Perbandingan Metode Li dan Chan-Vese Pada Proses Segmentasi Citra Digital, vol. I, pp. 666-679, 2013.

H. P. Hadi, E. Faisal and E. H. Rachmawanto, Brain Tumor Segmentation Using Multi-level Otsu Thresholding and Chan-Vase Active Contour Model, vol. XX, pp. 825-833, 2022.

R. B. K, C. S. T. L.S.P. Sairan Nadipalli dan P. V. G. Bharath Kumar, CNN Fusion Based Brain Tumor Detection From MRI Images Using Active Contour Segmentation Techniques, pp. 1742-6596, 2020.

D. M. Anisuzzaman, Y. Patel, B. Rostami, J. Niezgoda, S. Gopalakrishnan dan Z. Yu, Multi-modal Wound Classification using Wound Image and Location by Deep Neural Network, 2021.

A. R. W. Putri, A. Yudhana dan Sunardi, Klasifikasi Kanker Payudara Menggunakan Metode Digital Mammogram, vol. IX, no. 4, pp. 2752-2761, Desember 2022.

S. R. Sulistiyanti, F. A. Setyawan and M. Komarudin, Pengolahan Citra; Dasar dan Contoh Penerapannya, Yogyakarta: Teknosain, 2016.

R. Ajitha dan N. Punitha, Active Contour-based Segmentation of Normal and Fetal Spina Bifida Ultrasound Images, vol. I, pp. 1742 - 6596, 2022.

D. U. Dewangga, Adiwijaya and D. Q. Utama, Identifikasi Citra Berdasarkan Gigitan Ular Menggunakan Metode Active Contour Model dan Support Vector Machine, vol. III, no. 4, pp. 299-306, Oktober 2019.




DOI: https://doi.org/10.30645/kesatria.v4i2.175

DOI (PDF): https://doi.org/10.30645/kesatria.v4i2.175.g174

Refbacks

  • There are currently no refbacks.


Published Papers Indexed/Abstracted By: