期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2013
卷号：4
期号：4
页码：572-576
出版社：TechScience Publications
摘要：Supervised learning is based on the target value or the desired outputs. Various successful techniques have been proposed to solve the problem in the binary classification case. The multiclass classification case is more delicate one. In this short survey we investigate the various techniques for solving the multiclass classification problem. Various authors and research modified the multiclass classification approach such as one against one, one against all and Directed Acyclic Graph (DAG) which creates many binary classifiers and combines their results to determine the class label of a test pixel. They also describe the various extensible methods that are extended from binary class to solve the multiclass problem and also explain the method in which the classes are arranged into a tree.
