面向叶子图像的植物归类的特征序列描述方法

被引:2
作者
谢从华 [1 ]
王立军 [2 ]
常晋义 [1 ]
机构
[1] 常熟理工学院计算机科学与工程学院
[2] 北京北大千方科技有限公司
关键词
局部特征; 全局特征; 图像归类; 混合模型;
D O I
暂无
中图分类号
TP391.41 [];
学科分类号
080203 ;
摘要
针对叶子图像的植物数据库的归类系统,提出了一种新的基于高斯混合模型特征函数的图像特征序列描述方法。定义了图像的高斯混合模型、特征函数及其性质,用自适应的方法把图像分解为K个模型,并在每个分量模型和混合模型上定义由频谱、相位角和功率谱组成的局部特征序列和全局特征序列。在中国科学院智能计算所的叶子图像数据集leaves(ICL)上进行了K-means归类实验,结果表明该图像描述方法比LBP局部综合特征和高斯混合密度函数有更好的归类结果。
引用
收藏
页码:4740 / 4742+4746 +4746
页数:4
相关论文
共 22 条
[1]  
A Comparative Study of PCA, LDA and Kernel LDA for Image Classification. Fei Ye. ISUVR’’09. International Symposium on . 2009
[2]  
Leaf shape based plant species recognition. DU Ji-xiang,,WANG Xiao-feng,ZHANG Guo-jun. Applied Mathematics and Computa-tion . 2007
[3]   基于加权局部线性嵌入的植物叶片图像识别方法 [J].
张善文 ;
王献峰 .
农业工程学报, 2011, 27 (12) :141-145
[4]  
A comparison of EM and GMVQ estimating Gauss mixtures:application to probabilistic image retrieval. JEONG S,GRAY R M. Proc of IEEE International Conference on Acoustics,Speech,and Signal Processing . 2005
[5]  
Farthest point distance:a new shape signature for Fourier descriptors. AKREM E G,OTMAN B,SAEID B. Signal Processing:Im-age Communication . 2009
[6]  
A novel Fourier descriptor based image alignment algorithm for automatic optical inspection. CHEN C S,YEH C W,YIN P Y. Jour-nal of Visual Communication and Image Representation . 2009
[7]  
Histogram of Gabor phase pat-terns(H3GPP):a novel object representation approach for face recog-nition. ZHANG B,SHAN S,,CHEN X,et al. IEEE Transactions on Image Processing . 2007
[8]  
Combining different local binary pattern variants to boost performance. NANNI L,BRAHNAM S,LUMINI A. Expert Systems with Ap-plications . 2011
[9]  
PLBP:an effective local binary patterns texture descriptor with pyramid representation. QIAN Xue-ming,HUA Xian-sheng,CHEN Ping. Pattern Recognition . 2011
[10]  
Texture segmentation using independent-scale component-wise Riemannian-covariance Gaussian mixture model in KL measure based multi-scale nonlinear structure tensor space. Han S D,Tao W B,Wu X L. Pattern Recognition . 2011