A sparse representation method of bimodal biometrics and palmprint recognition experiments
A sparse representation method of bimodal biometrics and palmprint recognition experiments
复制标题
DOI：
10.1016/j.neucom.2012.08.038
复制
发表时间：
2013-03
期刊：
影响因子：
6
通讯作者：
Yong Xu;Zizhu Fan;Minna Qiu;D. Zhang;Jing-yu Yang
中科院分区：
文献类型：
--
作者：
Yong Xu;Zizhu Fan;Minna Qiu;D. Zhang;Jing-yu Yang
在本文中，我们提出了一种稀疏表示方法的双峰生物特征。该方法首先通过将两个生物特征的样本预先组合成一个真实的向量来完成特征级融合。然后，该方法认为测试样本的近似表示可能对分类更有用，并使用近似表示对测试样本进行分类。该方法利用测试样本的训练样本集的邻域的加权和来产生测试样本的近似表示，并基于该表示来执行分类。各种实验表明，所提出的近似表示使我们能够实现更高的精度。该方法有以下合理的假设：测试样本可能来自测试样本的邻居来自的类之一。在本文中，我们还正式显示所提出的方法和传统的基于外观的方法之间的差异，并证明所提出的方法是能够更准确地代表测试样本比传统的基于外观的方法。
In this paper, we propose a sparse representation method for bimodal biometrics. The proposed method first accomplishes the feature level fusion by combining the samples of the two biometric traits into a real vector in advance. This method then considers that an approximate representation of the test sample might be more useful for classification and uses the approximate representation to classify the test sample. The proposed method exploits a weighted sum of the neighbors from the set of training samples of the test sample to produce the approximate representation of the test sample and bases on this representation to perform classification. A variety of experiments demonstrate that the proposed approximate representation enables us to achieve a higher accuracy. The proposed method has the following reasonable assumption: the test sample is probably from one of the classes which the neighbors of the test sample are from. In this paper, we also formally show the difference between the proposed method and conventional appearance-based methods, and demonstrate that the proposed method is able to more accurately represent the test sample than conventional appearance-based methods.