FIRE RECOGNITION USING RGB AND YCBCR COLOR SPACE

This project was inspired by the imperfect of vision based system to detect fire which sometimes causing detection of false alarm due to the interruption of environment (lighting). In this work, a system for fire recognition is developed based on a set of rules of conforming the value of R, G, B, Y, Cb and Cr component in an image. The performance of the system is tested on one hundred images of fire and non-fire, and they are taken during morning, afternoon and evening to ensure the system is robust to different surrounding brightness. However, the images will undergoes several steps of pre-processing to minimize noises. As a result, both color spaces, RGB and YCbCr have high detection rate of fire which is 90% and 100% respectively. YCbCr color space shows the best performance compared to RGB because it can separate luminance from chrominance more effectively than RGB color space.