【摘要】 传统的图像边缘检测算子一般都只能得到多像素宽度的边缘,这为后续的图像处理带来了一定困难。对大米二值图像的细化的程度直接影响颗粒特征的提取以及颗粒的识别,这也是开发大米检测系统软件部分又一个关键的课题。结合边缘走向趋势的估计技术以及对关键点判断的方法,提出一种新型的边缘细化算法—保持关键点的边缘细化算法。实验证明该算法能在保持边缘原有信息(连通和走向)的前提下,以较小的计算开销,满足物体骨架单像素宽为1的细化要求,实用性比较强。更多还原

【Abstract】 The traditional image edge detectors can only get multiple pixel wide edges usually,thus it is difficult to operate for post processing methods.Edge thinning results of Rice Binary Image directly affect character segmentation and object recognition and it is also the critical part of the software for Rice Detection System.A novel edge thinning algorithm named as critical point preserved edge thinning algorithm is presented in this paper,which combines the detecting strategy of the connectivity critical point with the estimating method of the edge direction.It can preserve the origin edge information such as connection and direction.It is proved by experiments that an ideal or acceptable single pixel wide edge with lower computing cost is obtained.更多还原