File(s) under permanent embargo

A new color space based on K-medoids clustering for fire detection

conference contribution
posted on 2015-01-01, 00:00 authored by Seyedamin Khatami, S Mirghasemi, Abbas KhosraviAbbas Khosravi, Saeid NahavandiSaeid Nahavandi
Pixel color has proven to be a useful and robust cue for detection of most objects of interest like fire. In this paper, a hybrid intelligent algorithm is proposed to detect fire pixels in the background of an image. The proposed algorithm is introduced by the combination of a computational search method based on a swarm intelligence technique and the Kemdoids clustering method in order to form a Fire-based Color Space (FCS), in fact, the new technique converts RGB color system to FCS through a 3*3 matrix. This algorithm consists of five main stages:(1) extracting fire and non-fire pixels manually from the original image. (2) using K-medoids clustering to find a Cost function to minimize the error value. (3) applying Particle Swarm Optimization (PSO) to search and find the best W components in order to minimize the fitness function. (4) reporting the best matrix including feature weights, and utilizing this matrix to convert the all original images in the database to the new color space. (5) using Otsu threshold technique to binarize the final images. As compared with some state-of-the-art techniques, the experimental results show the ability and efficiency of the new method to detect fire pixels in color images.



IEEE International Conference on Systems, Man, and Cybernetics (2015 : Hong Kong, China)


IEEE International Conference on Systems Man and Cybernetics Conference Proceedings


2755 - 2760




City Univ Hong Kong, Hong Kong, PEOPLES R CHINA

Place of publication

Piscataway, N.J.

Start date


End date






Publication classification

E Conference publication; E1 Full written paper - refereed

Copyright notice

2015, IEEE

Title of proceedings

SMC 2015 : Proceedings of 2015 IEEE International Conference on Systems, Man and Cybernetics