基于HOG特征的显微镜自动对焦算法研究

Research on Microscopic Auto Focus Algorithm Based on HOG Feature

针对图像背景复杂、目标物体相对较小,当前显微镜自动对焦算法普遍稳健性较差的问题,提出一种改进的自动对焦算法.该算法将HOG特征与拉普拉斯梯度结合协同判断显微镜同一视野下具有最佳清晰度的图片,选用基于Tenengrad梯度函数作为图像清晰度评价参数.实验结果表明:在拍摄目标物体较小且背景复杂的情况下,该算法能更有效地找出显微镜同一视野图像中最清晰的一张,并且加快了图像清晰度的判断速度,实现显微图像的快速对焦.

An improved auto-focusing algorithm is proposed,aiming at the fact that the current microscope auto-focusing algorithm has poor robustness sharpness evaluation parameters when the image background is complex and the object is small.The algorithm combines HOG feature with Laplacian gradient to synergisyically judge images with the best resolution under the same field of vision,and Tenengrad gradient function is chosen as the evaluation parameter of image definition.The experimental results show that this algorithm can find the clearest image in the same field of view When the object is small and the background is complex,and it also speeds up the judgment of image definition and realizes the fast focusing of microscopic images.