<![CDATA[Use of protective gear helmet head is often considered unimportant and trivial by workers. Whereas the use of protective headgear helmet is very important and affect the safety and health of workers. Kedisiplina workers to use protective gear head is still low so that the risk of accidents that could endanger workers large enough. In this research aims to detect protective equipment head helmet on video. In this study, the method used is the Haar Cascade Classifier. The system consists of two main processes, namely the process of training data and the detection process. This method of training process has four main processes, haar-like feature, integral image, no-boost and cascade classifier. Haar-like feature is a collection of special features presented the head, face and helmet. Citra is how to quickly calculate integrals haar feature. While no-boost are statistically weighted feature values are obtained and filtered using a cascade classifier. The detection process in this study there are two processes, the first detection process whether human or not, if the result of human detected will continue the process of detection of whether to use a helmet or not. Detection system testing is done individually using helmet colors red, blue and yellow. It obtained accuracy rate of 92%, while the testing group obtained the degree of accuracy of 71%.]]>
Copyrights © 2019
