论文部分内容阅读
论述了基于3种不变量的融合信息来识别缺损目标的方法.该方法采用Dempster-Shafer证据推理方法作为决策层的融合工具,将拐点、线矩、高阶神经网络的分类结果进行信息融合.分类实验证明,该方法可以有效地提高系统的识别精度.
The method of identifying missing objects based on three invariants of fusion information is discussed. The method uses Dempster-Shafer evidence reasoning method as the fusion tool of decision-making layer, and combines the classification results of inflection points, line moments and higher-order neural networks. Experimental results show that this method can effectively improve the recognition accuracy of the system.