江汉大学学报(自然科学版) ›› 2016, Vol. 44 ›› Issue (2): 131-136.doi: 10.16389/j.cnki.cn42-1737/n.2016.02.006

• 计算机科学与应用 • 上一篇    下一篇

基于深度学习神经网络的SAR图像目标识别算法

梁鑫,徐慧   

  1. 南京林业大学 信息科学技术学院,江苏 南京 210037
  • 出版日期:2016-04-28 发布日期:2016-05-05
  • 作者简介::梁鑫(1989—),男,硕士生,研究方向:仪器科学与技术、图像处理。

SAR Images Target Recognition Algorithm Based on Deep Learning Neural Network

LIANG Xin,XU Hui   

  1. College of Information Science and Technology,Nanjing Forestry University,Nanjing 210037,Jiangsu,China
  • Online:2016-04-28 Published:2016-05-05

摘要: 提出了一种有效的SAR图像目标识别新方法。首先采用改进后的增强Lee滤波和HOG变换对SAR图像进行特征提取,然后通过层叠RBM和GRNN相结合的混合神经网络对SAR图像进行目标分割和目标识别。利用测试图像库的MATLAB算法仿真,结果表明该方法可以明显提高目标识别率,正确率可以达到97%。

关键词: 目标识别, Lee滤波, HOG变换, 深度学习, 神经网络

Abstract: A new effective target recognition method for SAR images is proposed. First of all,take the improved enhanced Lee filtering and HOG transformation for feature extraction of SAR images,then through a hybrid neural network by cascading RBM and GRNN combination to operate object segmentation and target recognition of SAR images. Using MATLAB algorithm simulation of the test image database,in this paper,the method of object recognition based on the deep learning neural network algorithm can obviously increase the recognition rate,and accuracy reaches 97%.

Key words: target recognition, Lee filtering, HOG transformation, deep learning, neural network

中图分类号: