基于小波和自学习神经网络的图像分割

Image Segmentation Based on Wavelet Neural Networks with Adaptive Learning

提出了一种新颖的基于小波神经网络构架的FLIR图像分割技术,旨在将小波变换的时—频局域特性与神经网络的自学习能力相结合,从而使FLIR图像的分割算法具有较强的逼近和容错能力。该算法在FLIR?ATR系统中得到应用,对于FLIR目标图像轮廓的提取和抑制杂散背景方面获得了良好的效果。

This paper presents a new FLIR image segmentation technique based on wavelet neural networks, aiming to fusing both local characteristic of wavelet time-frequency and adaptive learning by neural networks, and resulting in the powerful abilities of approximation and tolerate error in IR image segmentation.This new algorithm has been applied in a FLIR-ATR system, and got favorable results in achieving IR target contours and damping background noises.