Title :
Research on CCD Infrared Image Method
Author :
Zhang, Ye ; Yang, Wei ; Zhang, Wendong ; Wang, Zhengyan ; Shao, Xingling ; Yin, Qiang
Author_Institution :
Key Lab. of Instrum. Sci. & Dynamic Meas., North Univ. of China, Taiyuan, China
Abstract :
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.
Keywords :
image enhancement; image segmentation; iterative methods; maximum entropy methods; pattern recognition; CCD infrared image method; double-hump method; image enhancement; image segmentation; infrared image pattern recognition system; iterated method; maximum entropy method; pattern classification; Charge coupled devices; Entropy; Gray-scale; Histograms; Image segmentation; Pixel; Switches; CCD infrared image; Threshold segmentation; method;
Conference_Titel :
Pervasive Computing Signal Processing and Applications (PCSPA), 2010 First International Conference on
Conference_Location :
Harbin
Print_ISBN :
978-1-4244-8043-2
Electronic_ISBN :
978-0-7695-4180-8
DOI :
10.1109/PCSPA.2010.173
