基于HT的显微视觉亚像素定位算法

Sub-pixel localization algorithm of micro-vision based on Hough transform

根据显微图像的几何特点,提出了基于HT(HoughTransform)十字显微图像亚像素定位算法(SLACHT)和基于HT近似圆显微图像亚像素定位算法(SLARHT),对显微图像特征中的直线和近似圆的亚像素定位做了深入的研究。通过与经典直线HT定位算法和经典随机HT圆定位算法进行实验对比,验证了该定位算法的优越性;通过与Matlab中的直线HT定位算法和圆HT定位算法进行实验对比,验证了该算法的可靠性。大量实验表明,该算法的定位精度优于0.01像素,具有运行速度快、鲁棒性强的特点。

According to geometric characteristics of micro-image, Sub-pixel Localization Algorithm of Crisscross image based on Hough Transform （SLACHT） and Sub-pixel Localization Algorithm of Round Image based on Hough Transform （SLACHT） are presented. Sub-pixel localization of linear and round image of micro-image is studied in detail. In contrast with classic Hough Transform （HT） algorithm detecting straight line and classic Random Hough Transform （RHT） algorithm detecting circle, CSLHT and RSLHT show more advantages. Reliability of the algorithms is proved by comparing with algorithm written by Matlab software. Many experiments show that localization accuracy of the algorithms is less than 0.01 pixel, and that they are accurate, running fast and strong robust.