An efficient corner detector based on ratio of parallelogram diagonal

Abstract

Corner is an important local feature of image which has been widely applied on various computer vision and image processing tasks. Here, a contour-based corner detector is developed by using the ratio of parallelogram diagonals (RPD) to estimate the curve curvature. The main advantage of RPD detector is that only once square root operation is required to calculate the curvature value at each point on a contour while maintaining good noise robustness. The contributions of this paper include the following three aspects: First, the motivation of the proposed RPD curvature is illustrated by means of parallelogram theory; second, a complete corner detector is proposed based on RPD curvature; third, comprehensive experiments are carried out and the experimental results show superior performances of the proposed method against another five strong baselines. In these experiments, RPD runs 100% faster than the prior works. Moreover, a mean accuracy of 83.87% is reported on GCM dataset which is an improvement of about 0.9% and a mean accuracy of 74.21% is reported on CPDA dataset which is an improvement of about 0.2%.