黎曼流形上的核稀疏表示及折痕识别  

Kernel Sparse Representation on Riemannian Manifold and its Application to Crease Recognition

作　　者：岳洪伟[1,2] 金迎迎[3] 

机构地区：[1]五邑大学信息工程学院,广东江门529020 [2]广东工业大学自动化学院,广州510006 [3]五邑大学数学与计算科学学院,广东江门529020

出　　处：《小型微型计算机系统》2015年第4期886-890,共5页Journal of Chinese Computer Systems

基　　金：广东省自然科学基金项目(S2013040014993)资助;广东省自然科学基金项目(S2012010010652)资助;广东省科技计划项目(2012B020314005)资助

摘　　要：在毛杆折痕识别中,光照不均和边缘绒毛等干扰因素在一定程度上影响识别的准确性.为尽可能排除这些影响折痕识别的因素,将图像稀疏表示思想引入到折痕检测,提出了黎曼流形上的核稀疏表示方法进行目标识别.首先采用协方差矩阵描述子来表征图像,并利用Bregman散度作为黎曼流形上的距离度量,进而构造了流形上的核函数.然后通过核方法把样本数据映射到再生核希尔伯特空间,结合稀疏表示获取高维特征空间的核稀疏表示系数.最后建立了字典学习的数学模型,结合凸理论提出了字典学习的有效算法.实验结果表明了所提方法的有效性.In feather quill crease detection, the existences of uneven illumination and fluff usually influence the detection accuracy. Ai- ming at the detection difficult problem, the idea of image sparse representation is introduced into the field of crease recognition. A feather quill crease recognition method based on sparse representation on Riemannian manifold is proposed for target recognition. First- ly, covariance matrices are computed as the crease descriptors of feather quill, and Bregman divergence which is adopted to make the space meet the requirement of Riemannian manifold is used to measure the distance between the two samples, then kernel function on Riemannian manifold is constructed. Secondly, the sample datasets are mapped into the reproducing kernel Hilbert space by kernel method, and kernel sparse representation coefficient of high dimensional feature space is obtained based on sparse representation. Final- ly, a mathematical model of dictionary learning is constructed and an efficient algorithm is proposed for dictionary learning according to the convex theory. The simulated experimental results verify the effectiveness of the proposed method which achieves better per- formance compared with many popular recognition algorithms.

关 键 词：羽毛杆折痕 稀疏表示 核方法 Bregman散度 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]