计算机应用 ›› 2012, Vol. 32 ›› Issue (07): 1871-1874.DOI: 10.3724/SP.J.1087.2012.01871

• 图形图像技术 • 上一篇    下一篇

基于模糊径向基神经网络和稀疏表示的毫米波图像恢复

尚丽1,2,苏品刚1,3,陈杰1   

  1. 1. 苏州市职业大学 电子信息工程系,江苏 苏州215104
    2. 中国科学技术大学 自动化系，合肥230026
    3. 毫米波国家重点实验室(东南大学)，南京210098
  • 收稿日期:2011-12-13 修回日期:2012-02-01 发布日期:2012-07-05 出版日期:2012-07-01
  • 通讯作者: 尚丽
  • 作者简介:尚丽(1972-)，女，安徽砀山人，副教授，博士，主要研究方向：人工智能、模式识别、数字图像处理；苏品刚（1971-），男，江苏苏州人，副教授，硕士，主要研究方向：毫米波焦平面成像技术、测控技术；陈杰（1980-），男，浙江绍兴人，讲师，硕士，主要研究方向：传感器检测、数字信号处理。
  • 基金资助:

    国家自然科学基金资助项目（60970058）;江苏省“青蓝工程”资助项目;2010苏州市职业大学创新团队资助项目（3100125)

Millimeter wave image restoration based on fuzzy radial basis function neural networks and sparse representation

SHANG Li1,2,SU Pin-gang1,3,CHEN Jie1   

  1. 1. Department of Electronic Information Engineering, Suzhou Vocational University, Suzhou Jiangsu 215104, China
    2. Department of Automation, University of Science and Technology of China, Hefei Anhui 230026, China
    3. State Key Laboratory of Millimeter Wave (Southeast University), Nanjing Jiangsu 210096, China
  • Received:2011-12-13 Revised:2012-02-01 Online:2012-07-05 Published:2012-07-01
  • Contact: SHANG Li

PDF

摘要： 针对毫米波（MMW）图像包含大量未知噪声、图像分辨率较低的问题，考虑模糊径向基函数神经网络(F-RBFNN)的非线性滤波特性和基于K-奇异值分解（K-SVD）稀疏表示（SR）的自适应消噪特性，提出了一种级联消噪的毫米波图像恢复方法。F-RBFNN将模糊逻辑的知识表达和推理能力与RBFNN的快速学习能力和泛化能力结合起来，可根据实际问题调整网络结构参数，对MMW图像达到非线性滤波的目的。进一步利用K-SVD稀疏表示具有人眼视觉特性，在保持目标特征的同时可有效消噪的优点，对FRBFNN的训练结果再次进行局部图像降噪，得到分辨率较高的MMW图像。采用相对信噪比（RSNR）作为消噪图像的评价标准，实验结果表明，与F-RBFNN、K-SVD消噪、小波消噪等方法相比，基于F-RBFNN和SR的降噪方法能够获得较好的MMW图像恢复质量。

关键词: 毫米波图像, 模糊径向基神经网络, 稀疏表示, 非线性滤波, 图像消噪

Abstract: As to the problems that Millimeter Wave (MMW) image is contaminated by much unknown noise and has lower resolution, and considering the non-linear filter property of Fuzzy Radial Basis Function Neural Network (F-RBFNN) and the self-adaptive denoising property of Sparse Representation (SR) based on K-Singular Value Decomposition (K-SVD), a MMW restoration method was proposed by combining F-RBFNN and sparse representation. In F-RBFNN, the knowledge expression of fuzzy logic and the reasoning ability were combined with the RBFNN's capabilities of fast learning and generalization. In order to realize the non-linear filtering to the MMW image, F-RBFNN's structure and parameters were adjusted according to the real problem. Furthermore, utilizing the advantages of sparse representation method, which the sparse representation behaves the visual characteristic and can denoise effectively when maintaining features of the object, the training results of F-RBFNN were locally denoised once again, and the MMW image with high resolution was obtained. Using the Relative Single Noise Ratio (RSNR) criterion to measure the quality of denoised images, the simulation results show that, compared with other denoising methods such as F-RBFNN, K-SVD denoising, and wavelet denoising, the proposed method combining F-RBFNN and SR can better restore the quality of MMW image.

Key words: Millimeter Wave (MMW) image, Fuzzy Radial Basis Function Neural Network (F-RBFNN), Sparse Representation (SR), non-linear filtering, image denoising

中图分类号: 

版权所有 © 2021 四川计算机应用杂志社有限公司
蜀ICP备 05010208 号-3　新出网证(川)字026号
技术支持：北京玛格泰克科技发展有限公司
访问总数：
今日访问：