Abstract: Based on the idea of nonparallel hyperplanes, a novel multi-class cluster support vector machine method was proposed to settle the multi-class classification problem of support vector machines. For a k-class classification problem, it trained k-hyperplanes respectively, and each one lay as close as possible to self-class while apart from the rest classes as far as possible. Then, labels of new samples were determined by the class of their nearest hyperplane belonging to, thus the inherent limitations of OAO and OAA methods can be avoided, such as “decision blind-area” and “unbalanced classes”. Finally, experiments on UCI and HCL2000 datasets showed that the proposed method outperformed traditional OAO and OAA etc. methods in terms of recognition accuracy significantly.

Key words: support vector machine, hyperplane, multi-class, handwritten Chinese character recognition, algorithm

摘要： 针对支持向量机的多分类问题，提出一种新颖的基于非平行超平面的多分类簇支持向量机。它针对k模式分类问题分别训练产生k个分割超平面，每个超平面尽量靠近自身类模式而远离剩余类模式；决策时，新样本的类别由它距离最近的超平面所属的类决定，克服了一对一（OAO）和一对多（OAA）等传统方法存在的“决策盲区”和“类别不平衡”等缺陷。基于UCI和HCL2000数据集的实验表明，新方法在处理多分类问题时，识别精度显著优于传统多分类支持向量机方法。

关键词: 支持向量机, 超平面, 多分类, 手写体汉字识别, 算法