基于多特征的图象目标识别分类

文中研究将多特征信息融合技术用于图象目标识别分类的方法，利用图象灰度表面的分形特征与图象的摘特征（非分形特征）所提供的信息进行融合处理，在决策层中运用Ｄｅｍｐｓｔｅｒ－Ｓｈａｆｅｒ证据推理理论，并使用决策规则对目标进行分类。在实验中，将经过信息融合分类的结果与单特征独自分类的结果进行比较。结果表明，多特征信息融合的目标识别方法具有良好的稳定性，准确性和可靠性，能够有效地提高图象分类识别系统的精确度与容错性。

Image Recognition and Classification Based on Multi-feature

Multi-feature fusion technique is used to recognize and classify the image target in this paper. We extract the fractal feature and gray entropy from the image,then use Dempster-Shafer's Evidential Reasoning to fuse the information at the report level.Some decision strategies are used to recognize and classify the image. In experiment, we compare the results obtained from Multi-feature fusion with those obtained from single feature. The final results indicate that the Multi-feature fusion method is stable, reliable, and can efficiently improve the accuracy and the ability of fault tolerance.