改进Zernike矩亚像素边缘检测算法研究

Research of improved subpixel edge detection algorithm using Zernike moments

针对Ghosal算法检测出的边缘较粗以及手动反复调节阶跃强度阈值引起的效率低的问题,提出了一种改进算法。首先,推导出模板系数,并计算得出Zernike矩。其次,利用推导出的公式计算出距离阈值和边缘阈值,利用Otsu法计算得到最佳阶跃强度。最后,通过设计三组实验,来验证改进算法的有效性。实验证明,改进算法能够更加有效地检测出图像的边缘,减少伪边缘的存在并且细化了边缘,提高了定位精度,同时降低了算法的执行时间。

The principle of sub-pixel edge detection based on Zernike moments is introduced in this paper. With the consideration of the limitation of the sub-pixel edge detection algorithm by Ghosal, such as the lower location precision of the edge and the ex- tracted wider edge than that of the original image, an improved algorithm is proposed. First of all, a mask of size seven by seven is calculated and Zernike moment is calculated. Secondly, the distance threshold and edge threshold are calculated by using the for- mula, and the best intensity of step is calculated by using Otsu method. Finally, a series of experiments are designed and it verity the validity of the improved algorithm. The experiment results show that the improved algorithm can effectively detect the edge, it reduces the existence of false edge and refines edge, and it can enhance the inspection accuracy and reduces the execution time of the algorithm.