基于神经网络数据融合的目标识别方法研究

综合应用图像识别、神经网络和数据融合技术是多传感器ATR系统的一个重要研究方向。设计了一种基于BP网络和多传感器数据融合的图像识别系统。从信息论的观点出发 ,在理论上探讨了BP网络数据融合用于图像目标识别 /分类的机理。以此理论对实验结果的合理解释证明了该理论的正确性。理论分析和实验结果都证明了神经网络数据融合用于图像目标识别 /分类的有效性和可行性

A Study on Target Recognition Based on Neural Network Data Fusion

Synthesizing the technology of image recognition, neural network and data fusion is one important trend of the multi-sensor ATR system. This paper designs an image recognition system based on BP neural network and multi-sensor data fusion. In theory, the mechanism of the BP network data fusion applied to image recognition is discussed based on information theory. The experimental results are explained reasonably by the mechanism, so this theory is proved. The theory analysis and the experimental results prove the validity and the feasibility of the neural network data fusion applying to image recognition/classifying.