Tugas Akhir Informatika
DETEKSI API PADA VIDEO MENGGUNAKAN METODE ARTIFICIAL NEURAL NETRWORK
The camera is one of the tools used to collect images. Cameras are often used for the safety of homes, highways and
others. Then in this study camera captures are used to support fire objects because fire is one of the causes of safety that
can be controlled. Therefore, by utilizing a capture camera will see the best model of backpropagation neural network
by combining the local binary patern (LBP) feature extraction method and the Gray Level Co-occurrence Matrix (GLCM)
to access the fire. Then to evaluate the performance of the model created using three parameters that contain accuracy,
recall, precision. The data in this study consisted of videos with variations of fire and non-fire videos. Based on the final
results of the study, accuracy, remember, the best precision obtained simultaneously 96%, 97%, 97%. Then the validation
process was done using 30 videos with a variation of 15 fire videos and 15 non-fire videos and obtained an accuracy of
86.6% with an average time value of 6.029 minutes.
Tidak ada salinan data
Tidak tersedia versi lain