采用区域生长法分割根系CT图像的改进算法  

An Improved Region Growing Algorithm for the CT Images Segmentation of Plant Root

作　　者：周学成[1] 罗锡文[1] 

机构地区：[1]华南农业大学工程学院

出　　处：《农业机械学报》2006年第12期122-125,共4页Transactions of the Chinese Society for Agricultural Machinery

基　　金：国家自然科学基金资助项目(项目编号:60375005)

摘　　要：提出了一种基于阈值分析和区域生长相结合的用于植物根系CT序列图像分割的算法。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。实验结果表明,该分割算法计算量小,分割精度高,在提取目标的同时,能够有效地分离介质(背景)像素;而且对于背景复杂、噪声较大、目标像素灰度不均匀的CT图像也能取得较好的分割效果。A segmentation algorithm based on histogram analysis and region growing method was proposed for the CT images of plant root. Firstly,the method of histogram analysis was used to obtain the basic segmenting threshold of root region. Then,all the region of root was completely segmented from the original image by the improved region growing method. The experiments indicated that the segmentation method presented had the advantages of real time and segmentation precision, and the target could be extracted without any pixel of the background.Moreover, this segmentation fits for those images with complex background and uneven graylevel.

关 键 词：植物根系 图像分割 阈值分析 区域生长 

分 类 号：TN911.73[电子电信—通信与信息系统]