Automatic color segmentation of breast infrared images using a Gaussian mixture model

Optik ◽  
2015 ◽  
Vol 126 (21) ◽  
pp. 3288-3294 ◽  
Author(s):  
Saeed Kermani ◽  
Nasser Samadzadehaghdam ◽  
Mahnaz EtehadTavakol
2021 ◽  
Vol 3 (1) ◽  
pp. 108-119
Author(s):  
Ristirianto Adi ◽  
I Gede Pasek Suta Wijaya

Fire is a disaster that can endanger lives and cause property loss. The solution to detect fire that is commonly used today is to use a sensor. Fire sensors can be used together with surveillance cameras (CCTV) which are now being installed in many office buildings. This study tries to build a model for detecting fire in video with a digital image processing approach using the Gaussian Mixture Model for motion detection and fire color segmentation in the YCbCr color space. The model is then tested with metrics for accuracy, precision, recall, and processing speed. The dataset used is in the form of videos with small, medium, large fire sizes, and videos that only have fire-like objects. The test results show that the algorithm is able to detect fire when the size of the fire is not too small or the position of the fire is close enough to the camera. For videos with a resolution of 800x600 and a framerate of 30 fps, it can achieve 66.89% accuracy, 73.77% precision, and 66.66% recall. The performance during the day is relatively better than at night. Algorithm processing speed is too slow to be implemented in real-time


2018 ◽  
Vol 30 (4) ◽  
pp. 642
Author(s):  
Guichao Lin ◽  
Yunchao Tang ◽  
Xiangjun Zou ◽  
Qing Zhang ◽  
Xiaojie Shi ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document