基于支持向量机的植物图像分割  

Plant Image Segmentation Based on Support Vector Machine

作　　者：马晓丹[1] 关海鸥[1] 黄燕[2] 

机构地区：[1]黑龙江八一农垦大学信息学院,黑龙江大庆163319 [2]黑龙江八一农垦大学工程学院,黑龙江大庆163319

出　　处：《农机化研究》2009年第10期46-48,共3页Journal of Agricultural Mechanization Research

基　　金：黑龙江省教育厅面上课题(11531256)

摘　　要：图像分割是计算机视觉领域的关键技术之一。支持向量机方法被认为是好的学习分类方法之一,特别在小样本、高维情况下,具有较好的泛化性能。为此,以植物图像为例,结合数字图像处理技术,采用支持向量机法实现了植物叶片图像与背景图像的分割。实验证明,与传统的分割方法比较,该方法是高效和准确的。Image segmentation is critical to computer vision.Support vector machine approach is considered a good candidate because of its good generalization performance,especially when the number of training samples is very small and the dimension of feature space is very high.This paper set soybean image for example,complete the segmentation between leaf and background using SVM and digital image processing.The result shows that,SVM is high efficient and accurate,which comparing to the traditional segmentation methods.

关 键 词：植物 图像分割 支持向量机 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] S126[自动化与计算机技术—计算机科学与技术]