Reasearch of flame image recognition algorithm based on SVM

Zongfang Ma, Yongmei Cheng, Huiqin Wang, Najuan Yang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

9 Scopus citations

Abstract

The key problem of fire detection is the recognition and classification for fire flame and interference. Support vector machine (SVM) is a potential data classification tool developed from statistical theory. Aiming at the shortcomings of traditional fire detection, An image fire detection algorithm based on support vector machine is presented. The algorithm overcomes the disadvantages of neural network such as over learning, trapping in local minimum easily etc., and overcomes the complexity of doing a lot of experiments and statistical analysis to obtain recognition threshold. The experiment results show that the image fire detection algorithm based on SVM has high accuracy and notable effect on solving the recognition problem of small samples and nonlinear problem.

Original languageEnglish
Title of host publication2009 1st International Conference on Information Science and Engineering, ICISE 2009
Pages1399-1401
Number of pages3
DOIs
StatePublished - 2009
Event1st International Conference on Information Science and Engineering, ICISE2009 - Nanjing, China
Duration: 26 Dec 200928 Dec 2009

Publication series

Name2009 1st International Conference on Information Science and Engineering, ICISE 2009

Conference

Conference1st International Conference on Information Science and Engineering, ICISE2009
Country/TerritoryChina
CityNanjing
Period26/12/0928/12/09

Keywords

  • Feature extraction
  • Flame image
  • Support vector machine

Fingerprint

Dive into the research topics of 'Reasearch of flame image recognition algorithm based on SVM'. Together they form a unique fingerprint.

Cite this