Rayhan Suwito Suwito
Universitas Muhammadiyah Prof. DR. HAMKA

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

METODE PENDETEKSI API BERBASIS RUANG WARNA HUE SATURATION VALUE (HSV) Rayhan Suwito Suwito
Jurnal Teknik Informatika dan Komputer Vol. 4 No. 1 (2025): Jurnal Teknik Informatika dan Komputer
Publisher : Universitas Muhammadiyah Prof. DR. HAMKA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22236/jutikom.v4i1.24888

Abstract

Fires are frequent disasters caused by uncontrolled flames, leading to widespread casualties and material losses. Therefore, an early detection system is highly required to minimize the impact of such incidents. This study aims to design and develop a real-time fire detection prototype system using the Hue, Saturation, Value (HSV) color space algorithm. The methodology is conducted systematically, starting with the collection of a dataset comprising 200 videos (fire and non-fire), data preprocessing such as resizing frames and reducing noise using a Gaussian Blur filter, followed by feature extraction and HSV masking. The HSV algorithm was selected due to its capability to separate core color information (Hue) from lighting levels (Value) and color intensity (Saturation), thereby effectively isolating fire-colored areas from complex backgrounds. When the detected fire pixels exceed a 15,000-pixel threshold, the system triggers an alarm and sends an asynchronous e-mail notification using multithreading. System performance was evaluated using a Confusion Matrix, yielding an accuracy of 0.76, precision of 0.72, recall of 0.84, and an F1-score of 0.78. The developed prototype has proven successful in addressing basic detection problems, although system performance remains heavily dependent on lighting conditions and is susceptible to objects mimicking fire colors under high light intensity.