光电工程, 2015, 42 (9): 8, 网络出版: 2016-02-02
基于复数核的鲁棒最大间距准则算法
Robust Maximum Margin Criterion Based on Complex Kernel
鲁棒特征提取 维数约减 最大间距准则 小样本问题 robust feature extraction dimensionality reduction maximum margin criterion (MMC) small sample size problem
摘要
现有的最大间距准则 (Maximum Margin Criterion, MMC)算法对噪声比较敏感, 为了克服这一问题, 本文提出了一种基于复数核的鲁棒最大间距准则算法 (Robust Maximum Margin Criterion, RMMC)。首先通过鲁棒的复数核将样本映射到复数再生核 Hilbert空间(Complex Reproducing Kernel Hilbert Spaces, CRKHS), 然后在 CRKHS空间内实施 MMC算法。另外, 本文也提出了一种求解 RMMC的高效算法。实验表明, 本文算法对于噪声图像有较好的鲁棒性, 其识别率较高。
Abstract
The conventional Maximum Margin Criterion (MMC) is sensitive to noise. To address this problem, a Robust Maximum Margin Criterion (RMMC) based on complex kernel is proposed. The samples are first mapped to the Complex Reproducing Kernel Hibert Spaces (CRKHS), and then the MMC is conducted in CRKHS. Besides, an efficient algorithm for implementing MMC is also proposed in this paper. The experimental results shows that RMMC is robust to the noise images and its recognition rates are higher.
卢桂馥, 邹健, 王勇. 基于复数核的鲁棒最大间距准则算法[J]. 光电工程, 2015, 42(9): 8. LU Guifu, ZOU Jian, WANG Yong. Robust Maximum Margin Criterion Based on Complex Kernel[J]. Opto-Electronic Engineering, 2015, 42(9): 8.
PDF全文
