Skin Classification Via RGB Values and Machine Learning Algorithms
Isabela State University Linker Journal of Engineering Computing and Technology · 2024
DOI: 10.65141/ject.v1i1.n8 ↗Kurz gefasst
Fachartikel in der Zeitschrift Isabela State University Linker Journal of Engineering Computing and Technology, 2024. Verfasst von Vince Gallardo und 3 weiteren Autor:innen. Die Arbeit nennt 11 Literaturangaben.
Abstract (Originalsprache)
This research proposed a skin and non-skin classification method using R, G, and B color space and machine learning algorithms. The methodology created a dataset of skin and non-skin samples and used MATLAB's Classification Learner App with 25 different algorithms. The Weight KNN training model was identified as the most accurate and fastest, achieving 100% classification accuracy with 0.20881 seconds of time accuracy. This approach has potential applications in medical image analysis, computer vision, and facial recognition. The study suggests the Weight KNN training model is the most effective and accurate for skin and non-skin classification using R, G, and B color space and machine learning algorithms.
Zitieren
APA
Gallardo, V., Arboleda, E., Dones, J. P., & Panganiban, J. M. (2024). Skin Classification Via RGB Values and Machine Learning Algorithms. Isabela State University Linker Journal of Engineering Computing and Technology. https://doi.org/10.65141/ject.v1i1.n8
Vancouver
Gallardo V, Arboleda E, Dones JP, Panganiban JM. Skin Classification Via RGB Values and Machine Learning Algorithms. Isabela State University Linker Journal of Engineering Computing and Technology. 2024. doi:10.65141/ject.v1i1.n8
BibTeX
@article{Gallardo2024,
author = {Gallardo, Vince and Arboleda, Edwin and Dones, James Patrick and Panganiban, John Mark},
title = {Skin Classification Via RGB Values and Machine Learning Algorithms},
journal = {Isabela State University Linker Journal of Engineering Computing and Technology},
year = {2024},
doi = {10.65141/ject.v1i1.n8}
}
EUVIMED