Threshold Value Optimization to Improve Fire Performance Classification Using HOG and SVM

Abstract

Fire is a disaster caused by accidental fire, unexpected or unwanted, difficult to control, and detrimental. Many factors cause fires. Humans may directly or indirectly cause these factors, or they may also be caused by nature. Total 913 residential fires were recorded in Indonesia from 2013 to 2015. There are still many incidents of a fire occurring. This research is carried out to reduce the incident to detect fire objects by applying the histogram of oriented gradient (HOG) method and then classified using the support vector machine (SVM) method. The proposal is expected to help in the early identification of fires to reduce the number of fires that occur. This study has several stages: inserting images, converting images to grayscale, thresholding methods, object detection with HOG, and classification using SVM. The system implementation is carried out using the Python programming language with the Django web framework. The final result will be tested using a confusion matrix with four matrices: accuracy, precision, recall, and F1-Score. The results showed that the HOG and SVM methods using the RBF kernel and the sharing of training-test data 70:30 obtained accuracy of 88.33%, precision of 85.71 %, recall of 88.89%, and F1-Score of 87. 27%.