Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Journal of Information Technology and Computer Engineering
Rizka Hadelina
Departemen Teknik Komputer, Universitas Andalas
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering

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

Found 1 Documents
Search

 1 
Color Identification System Based on Single Board Computer for Color Blind Individuals Using HSV and CLAHE Jevon Al Salgus; Rifki Suwandi; Rizka Hadelina
JITCE (Journal of Information Technology and Computer Engineering) Vol. 10 No. 1 (2026): Journal of Information Technology and Computer Engineering
Publisher : Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Color vision deficiency (CVD) affects approximately 8% of males and 0.5% of females globally, causing difficulties in distinguishing certain colors in daily activities. This condition often leads to social misunderstandings and psychological impacts, including embarrassment when identifying colors incorrectly. This research aims to design and implement a portable wearable system capable of automatically detecting and identifying colors to assist CVD individuals. The system utilizes computer vision technology with HSV (Hue, Saturation, Value) color space analysis combined with adaptive CLAHE (Contrast Limited Adaptive Histogram Equalization) and gamma correction preprocessing, implemented on a Raspberry Pi 4 Model B integrated into a jacket. A JETE W7 USB webcam captures images, and color detection results are conveyed through pre-recorded audio feedback via earphones. The system employs a 4-stage multi-stage detection algorithm with weighted scoring to handle HSV range overlapping among 12 target colors. Testing was conducted using color palettes and real-world objects under three lighting conditions: bright (1000-1100 lux), normal (90-100 lux), and dim (33-35 lux). Results demonstrate that the system achieved an overall accuracy of 86.39%, with 91.11% accuracy on color palettes and 81.67% on real objects. The system operates stably on Raspberry Pi 4 with average CPU usage of 35.7% and maintains thermal stability at 43.2°C. User testing with color-blind participants confirmed that the system effectively assists in color identification and increases user confidence in social situations.
Co-Authors Jevon Al Salgus Rifki Suwandi