International Conference on Computational Science and Engineering (ICCSE 2015)
Harris Corner Detection Algorithm at Sub-pixel Level and Its Application
a b * c
Yuanfeng Han , Peijiang Chen and Tian Meng
School of Automobile, Linyi University, Shandong, 276000, China
a b * c
hyf2012413018@163.com, chenpeijiang@163.com, 1257398576@
Keywords Ha is corner, Sub-pixel, Gaussian surface, Image matching
Abstract. The corner is one of the most important features of image and the corner detection plays an
important role in digital image processing technology. The performance of Harris corner detection
algorithm is stable and it is widely applied, but the corner location is pixel level which affects the
subsequent image processing. In order to improve the performance of corner detection, the harris
algorithm is improved. On the basis of analyzing the principle of Harris corner detection algorithm,
the sub-pixel level corner position based on the Gauss surface method is extracted. The extracted
corners is applied in images matching. The experimental results show that the Harris corner detection
algorithm can extract high accurate corners. At the same time, the image matching based on this
algorithm has higher precision.
Introduction
The corner reflects the characteristics of image’s essence which brightness changes strongly [1]. The
real corner can effectively simplifies the information amount of data processing. Then, it significantly
improves the speed of image processing and matching accuracy and realizes the efficiency of image
processing. Therefore, in the enti