摘要
基于内容的图像检索的关键在于对图像进行特征提取。提出一种基于形状的高分辨率遥感图像特征提取方法。首先使用最小吸收同值核区SUSAN(Smallest Univalue Segment Assimilating Nucleus)算子对高分辨率遥感图像进行边缘检测,生成边缘图像。之后,对边缘图像计算其不变矩,作为该遥感图像形状特征的描述向量。试验结果说明,所使用的方法计算简便,速度快,而且该描述向量能够很好地代表图像的特征,具有较高的应用价值。
Image feature extraction is the most important thing of content-based image retrieval.This paper presents a method for shape-based feature extraction of high resolution remote sensing image.Firstly the edges in the original image are detected using Smallest Univalue Segment Assimilating Nucleus (SUSAN) principle.Then,the moment invariants of the edge map are calculated, and the result is used as the shape feature vector of the original image.Experimental results show that this method is simple and efficient,and the image feature can be well represented by this shape feature vector,and it is of high application significance.
出处
《计算机工程与应用》
CSCD
北大核心
2007年第19期26-29,63,共5页
Computer Engineering and Applications
基金
国家自然科学基金(the National Natural Science Foundation of China under Grant No.60272032)
中国遥感卫星地面站创新课题(No.062103)
关键词
最小吸收同值核区SUSAN
不变矩
特征提取
Smallest Univalue Segment Assimilating Nucleus(SUSAN)
moment invariants
feature extraction