针对传统的图像角点检测方法精度不高、速度较慢的情况,为提高速度抑制噪声,提出了一种快速、高精度的图像角点检测算法.利用改进的Harris算法提取出候选角点,再通过USAN区域所对应的弧的像元灰度与角点的相似性来完成最终角点的提取,使得处理的数据大为减少,同时能保证检测准确性等其他指标.通过和SUSAN算法、Harris算法在正确性、漏检、精度以及抗噪声性能等方面的综合比较,结果表明算法无论对模拟图像还是真实图像均具有良好的性能.%In view of that the traditional image comer detection algorithm accuracy is not high and the speed is low, a fast and novel comer detection algorithm with high-precision is proposed. This method makes use of an improved Harris method first to extract potential corners. The difference between algorithm and former one is that the USAN area corresponding to the arc and the corner pixel gray similarity to complete the extraction comer are taken into consideration. Thus, computational cost is largely reduced and the detection precision as well as other performances are well guaranteed. The proposed method is compared with SUSAN and Harris comer detectors in accuracy rate, missing detection, precision and so on. The results show that algorithm has a good performance for both synthesized and real images.
展开▼
