基于颜色特征的桔子树干图像分割方法  

Image Segmentation Methods for Orange Trunk Based on Color Features

作　　者：陈庆丰[1] 邱白晶[1] 

机构地区：[1]江苏大学现代农业装备与技术省部共建教育部重点实验室,江苏镇江212013

出　　处：《农机化研究》2010年第2期174-176,共3页Journal of Agricultural Mechanization Research

基　　金："十一五"国家"863计划"项目(2006AA10Z263)

摘　　要：根据桔子树干颜色的特点,提出了一种图像分割方法。首先,利用颜色特征定位ROI;然后,计算该区域的颜色特征向量提取桔子树干;最后,对不连续的桔子树干区域利用数学形态学方法进行自动修补。实验结果表明,该方法能够有效地提取出桔子树干,并确定其质心和面积,算法的平均识别率达到了86.93%。An image segmentation algorithm was proposed according to the characteristics of the Orange -tree trunk Firstly, the ROI was located by color features, Secondly, the Orange - tree trunk were vectors which were computed in ROI. Finally, some unconnected regions of the Orange extracted using the color feature -tree trunk were automatically repaired by Mathematical Morphology methods. The experimental results showed that this algorithm could effectively ex- tract the Orange - tree trunk and computed its centroid and area. The average accurate rate of image segmentation for the Orange-tree trunk was 86.93%.

关 键 词：树干 颜色特征 图像分割 数字图像处理 

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]