论文部分内容阅读
年轮宽度值是在树木的横切面上直接读取的,人工读数需要借助放大镜或读数显微镜,容易引起测量者的视觉疲劳,导致测定数据误差较大;而采用计算机视觉技术自动识别年轮的方法可以很好地解决这个问题。为此,针对环孔材年轮图像中管孔颗粒干扰分布密集且相对孤立的特点,提出了基于区域生长的分割算法提取年轮边界,并给出了区域生长和算法实现的过程。对比中值滤波,该方法能够较好地去除管孔干扰,并且边界保持较好,有利于年轮宽度的自动识别。
The value of annual ring width is read directly on the cross section of the tree. The manual reading needs the aid of a magnifying glass or a reading microscope to easily cause the visual fatigue of the surveyor, resulting in a large error in the measurement data. However, the automatic identification of the ring with computer vision technology Method can be a good solution to this problem. Therefore, in view of the dense and relatively isolated interference of tube-hole particles in ring-ring images, a segmentation algorithm based on region growth is proposed to extract the growth rings and the process of regional growth and algorithm implementation. Compared with the median filter, this method can well remove the interference of the borehole and keep the boundary well, which is good for the automatic identification of the width of the ring.