Half and Full Helmet Wearing Detection in Thailand using Haar Like Feature and Circle Hough Transform on Image Processing

摘要

Helmet detection has a wide area of applications in image processing. A new helmet detection technique is proposed in this paper. The technique combines two methods for helmet detection to achieve better detection rates. The two methods are face detection using haar like feature for detection between without helmet and full helmet and circle hough transform for detection between without helmet and half helmet. In the first module of the technique, we proposed a fast algorithm for detecting helmet in color images. The algorithm uses haar like feature to detect helmet regions, that, face/ nose/ mouth/ left eye/ right eye detection method can not detection between full and half helmet. So, the second module of the technique, the circle hough transform is applied for detection it. In experiments on images, our technique has achieved high detection rates and low false positives due to the application of the new algorithm.