Research on CCD Infrared Image Method
Ye Zhang, Wei Yang, Wendong Zhang, Zhengyan Wang, Xingling Shao, Qiang Yin · 2010
infrared image pattern recognition system consists of image enhancement, segmentation and pattern classification. Image segmentation is realized through Threshold Segmentation. Generally speaking, there are several methods of threshold segmentation such as double-hump method, iterated method and maximum entropy method and the otsu method and so on. These segmentation methods are used for the automatic segmentation of pedestrians in the infrared images. The results show that the Otsu threshold segmentation method can achieve infrared image segmentation better than others.