基于灰度图像和矢量的圆心定位

Locating a Center-point of the Circular Projection Based on a Gray-scale Image and Vector Sum

摘要:

提出了基于矢量和的全局最优的圆心定位方法，并利用卷乘和频域方法实现定位的快速箅法。该方法是基于灰度图像上进行圆心定位和圆周投影，不仅可以尽量多地保持原始字符图像的特征信息，而且克服了传统的基于二值化图像进行圆心定位时．过分依赖于二值化箅法、抗干扰性差等弊病。实验表明，方法定位的圆心坐标的准确度和一致性都好于形心法或质心法，而且有较好的抗干扰性。

Abstract:

A new method of locating a center-point of the circular projection was proposed based on the vector sum and image template convolving a mask over the gray-scale image directly and using the frequency domain computation is to reduce the time complexity.The new method keeps integrity feature of gray-scale protuberant character information dramatically,and can overcome the main shortages of the traditional method on binary-scale image,such as to depend on a binarization algorithm extremely.The results show that the performance of the proposed method is better than the general method,and can yield an excellent veracity and consistency of the center-point location on the condition of noise and deformity.