原位根系CT图像的分割算法研究  

Research on Plant Roots in Situ CT Slice Image Segmentation Algorithm

作　　者：陈旭锋[1] 马量[1] 杨凯[1] 

机构地区：[1]中国人民解放军63888部队

出　　处：《现代电子技术》2009年第6期116-118,共3页Modern Electronics Technique

摘　　要：在介绍原位植物根系观测技术方法的基础上,对近年来国内外植物根系原位观测方法的研究进展和存在的问题进行了总结。结合根系构型研究的需要,提出一种基于阈值分析和区域生长相结合的用于植物根系CT图像的图像分割算法。首先通过直方图分析,初步确定根系区域的分割阈值,再利用经过改进的区域生长法分割得到目标区域。结果表明,该分割算法的计算量小,分割精度高,能够有效地分离介质像素。Based on situ plant roots measuring method, the development and problems at home and abroad are analysed. A segmentation algorithm based on threshold analysis and region growing method is proposed for the CT images of plant root. Firstly,the method of histogram analysis is used to obtain the basic segmenting threshold of root region. Then,all the region of root is completely segmented from the original image by the improved region growing method. The experiments indicate that the segmentation method presented has the advantages of real - time and segmentation precision, and the target can be extracted without ant pixel of background.

关 键 词：根系 图像分割 阈值分析 区域生长 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]