Research Of Aircraft Recognition Based On Neural Networks

With the rapid development of electronic computer and IT industry, image processing and pattern recognition has been progressing greatly. It is now widely used in all kinds of fields. Specially, it is decisive and important to recognize exactly the targets in high-tech wars. As a typical application in military field, aircraft recognition has become a study focus. Many organizations and institutes have done much research and made great progress. The main work is listed as follows:First, the thesis gives a brief presentation on the development status of image processing and relative mathematical theories. Then, a platform is designed which ingrates with many functions to be used for aircraft recognition including median filter, image smoothing and so on. The platform has an expansion button for deeper operations such as image segmentation, edge detection.Second, the thesis discusses the theory of neural network used in pattern recognition and the studying and training of BP network. Then, by using BP network, it performs the pattern recognition experiment of the invariable moments' features of the image extracted last stage. And the results prove the validity of the algorithm of flat image recognition.Finally it summarizes the whole research work as the prospect of the project, and points out some features that need improving in future.