论文部分内容阅读
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
Comprehensive application of image recognition, neural network and data fusion technology is an important research direction of multi-sensor ATR system. An image recognition system based on BP network and multi-sensor data fusion is designed. From the point of view of information theory, the mechanism of BP network data fusion in image target recognition / classification is discussed in theory. The correct interpretation of the experimental results with this theory proves the correctness of the theory. Both theoretical analysis and experimental results demonstrate the effectiveness and feasibility of neural network data fusion for image recognition / classification