The Research Of Air Target Recognition Based On Image Processing

With the developing of image theory, digital image processing is widely used in every department of country economy. While the desire of modern war is becoming more and more severely, it is more and more important to recognize aircrafts.This thesis works mainly on the preprocessing and post processing of the image. This paper is structured as follows:Firstly, the image which is inputted is being preprocessed, including denoising , edge detection and binarization. Robert, Sobel, Prewitt, Gauss-Laplacian and wavelet methods are used to detect edges, and the image is binaried.Secondly, moment feature of the image is extracted. In this paper, Hu moment feature is extracted, normalized and modified.Thirdly, moment feature which is input in artificial neural network is used to recognize aircraft. In this paper, improved back-propagation network and Kohonen neural network and MLFNN network group classifier are proposed.Lastly, based on the methods we mentioned, software system using VC is designed to do experiments. Results indicated that this system can recognize aircrafts and the classifiers have high classification rate.