An Efficient Multi-Feature Best Decision Based Forest Fire Detection (MF-BD-FFD) From Still Images
M. Senthil Vadivu1, M.N. Vijayalakshmi2
1M. Senthil Vadivu, Research Scholar, Department of MCA, Bharathiyar University, Jyoti Nivas College, Bangalore (Karnataka), India.
2Dr. M.N. Vijayalakshmi, Department of MCA, R.V. Engineering College, Bangalore (Karnataka), India.
Manuscript received on 14 December 2018 | Revised Manuscript received on 26 December 2018 | Manuscript Published on 24 January 2019 | PP: 207-213 | Volume-7 Issue-4S2 December 2018 | Retrieval Number: Es2060017519/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Fire attack in forest makes major degradation in the forest environment and ecosystems. Forest fire detection in the early stage can prevent major causes due to fire attack. A novel digital image processing based on multi-feature best decision-based forest fire detection (MF-BD-FFD)is proposed in this work. To increase the sensitivity of detection, color and texture feature with hybrid decision making algorithms such as artificial neural networks (ANN), Support Vector machine (SVM), k- nearest classifier (KNN) is used and optimized output will be selected. By using proposed method, the accuracy of the system is increased with a factor of 5% when compared to the conventional technique.
Keywords: Forest Fire Detection (FFD), Artificial Neural Networks (ANN), Support Vector Machine (SVM), k- nearest Classifier (KNN), Digital Image Processing (DIP).
Scope of the Article: Image Security