计算机工程 ›› 2012, Vol. 38 ›› Issue (22): 186-189.doi: 10.3969/j.issn.1000-3428.2012.22.046

• 图形图像处理 • 上一篇    下一篇

基于Zernike矩和前馈神经网络的图像配准

吴健珍,李洪芹,王宇嘉   

  1. (上海工程技术大学电子电气工程学院自动化系,上海 201615)
  • 收稿日期:2012-01-18 修回日期:2012-03-16 出版日期:2012-11-20 发布日期:2012-11-17
  • 作者简介:吴健珍(1979-),女,讲师、博士,主研方向:图像处理,模式识别;李洪芹、王宇嘉,副教授、博士
  • 基金项目:
    上海市自然科学基金资助项目“基于偏好的多目标群体智能算法及应用研究”(10ZR1413000)

Image Registration Based on Zernike Moment and Feedforward Neural Network

WU Jian-zhen, LI Hong-qin, WANG Yu-jia   

  1. (Department of Automation, School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201615, China)
  • Received:2012-01-18 Revised:2012-03-16 Online:2012-11-20 Published:2012-11-17

摘要: 提出一种基于Zernike矩和多级前馈神经网络的图像配准算法。利用低阶Zernike矩表征图像的全局几何特征,通过多级前馈神经网络学习图像所经历的旋转、缩放和平移等仿射变换参数,在一级前馈神经网络的基础上添加二级前馈网络,以提高参数估计精度。仿真结果表明,与基于DCT系数的神经网络算法相比,该算法旋转、缩放和平移估计精度较高,对噪声的鲁棒性较强。

关键词: Zernike矩, 前馈神经网络, 图像配准, 仿射变换, 参数估计

Abstract: This paper proposes a novel image registration algorithm based on Zernike moments and multilevel feedforward neural networks. Low order Zernike moments are used as image global pattern features and the algorithm feeds them into multilevel feedforward neural networks to provide translation, rotation and scaling parameters. The second level feedforward neural network is utilized behind the first level neural network to improve parameter estimation accuracy. Experimental results show that the proposed algorithm can provide accurate registration and robust to noise attack.

Key words: Zernike moment, feedforward neural network, image registration, affine transform, parameter estimation

中图分类号: