高分辨率图像的指数矩描述

doi:10.3969/j.issn.0255-8297.2016.02.002

应用科学学报 ›› 2016, Vol. 34 ›› Issue (2): 127-134.doi: 10.3969/j.issn.0255-8297.2016.02.002

高分辨率图像的指数矩描述

孙景峰, 刘慧英, 纪超, 郭慧娟

西北工业大学自动化学院, 西安 710072

收稿日期:2014-11-05 修回日期:2015-12-03 出版日期:2016-03-30 发布日期:2016-03-30
通信作者: 孙景峰,博士生,研究方向:图像处理、机器视觉与智能控制,E-mail:sunjf2000@163.com;刘慧英:教授,博导,研究方向:机器视觉与图像处理、计算机控制及网络控制等,E-mail:lhy2005@nwpu.edu.cn E-mail:sunjf2000@163.com;lhy2005@nwpu.edu.cn
基金资助:
国家自然科学基金(No.61371123, No.61301165)资助

High-Resolution Image Based on Exponent Moments

SUN Jing-feng, LIU Hui-ying, JI Chao, GUO Hui-juan

School of Automation, Northwestern Polytechnical University, Xi'an 710072, China

Received:2014-11-05 Revised:2015-12-03 Online:2016-03-30 Published:2016-03-30

摘要/Abstract

摘要： 在指数矩定义与计算方法的基础上,提出应用指数矩矩阵描述高分辨率图像的方法.结合图像分割理论并延伸处理各子图,利用快速傅里叶变换计算高分辨率图像指数矩矩阵,然后逆向重构子图并重组原图.对重组图像进行基于Itti视觉注意模型的客观感兴趣区域信噪比分析.仿真结果表明,延伸处理可减弱由分割所带来的重组图像方块效应,也可提高重构图像的信噪比,验证了由图像指数矩矩阵描述高分辨率图像的可行性.

关键词: 指数矩, 图像归一化, 图像质量, 图像重构

Abstract: Based on the definition and calculation method of exponential moments, this paper describes a high-resolution image using the exponential moment matrix. Combining image segmentation and further treatment of sub-images, we use FFT to calculate the exponential moment matrix of a high-resolution image. Each sub-image is then reconstructed with the obtained exponential moment matrix. The original image is recomposed using the reconstructed sub-images. Meanwhile, based on Itti's visual attention model, SNR of the objectively interested area in the reconstructed image is analyzed. Simulation results show that the reconstructed image block effect caused by segmentation can be reduced, and SNR of the reconstructed image is improved. It is shown that describing a high-resolution image with image moment invariant matrix is feasible.

Key words: exponential moment, image normalization, image quality, image reconstruction

中图分类号:

TP311

孙景峰, 刘慧英, 纪超, 郭慧娟. 高分辨率图像的指数矩描述[J]. 应用科学学报, 2016, 34(2): 127-134.

SUN Jing-feng, LIU Hui-ying, JI Chao, GUO Hui-juan. High-Resolution Image Based on Exponent Moments[J]. Journal of Applied Sciences, 2016, 34(2): 127-134.

参考文献

[1] Hai H P, Ping Z L, Bo W R G, Sheng Y L, Chen S Z, Wu W K. Cell image recognition with radial harmonic Fourier moments[J]. Chinese Physics Letters, 2003, 12(6):610-614.

[2] Zeng J L, Zou Y R, Du D, Chang B H, Pan J L. Research on visual weld trace detection method based on invariant moment features[M]//Robotic Welding, Intelligence and Automation. Springer International Publishing, 2015:239-248.

[3] Xiang F, Yong H, Dandan S. An image retrieval method based on Hu invariant moment and improved annular histogram[J]. Elektronika ir Elektrotechnika, 2014, 20(4):67-71.

[4] Premaratne P, Premaratne M. Image matching using moment invariants[J]. Neurocomputing, 2014, 137:65-70.

[5] Wang X Y, Li W Y, Yang H Y, Niu P P, Li Y W. Invariant quaternion radial harmonic Fourier moments for color image retrieval[J]. Optics & Laser Technology, 2015, 66:78-88.

[6] Itti L, Koch C, Niebur E. A model of saliency-based visual attention for rapid scene analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(11):1254-1259.

[7] Ping Z L, Jiang Y J. An algorithm for computation of radial-harmonic-Fourier moments[C]//The Second International Conference on Functional Manufacturing Technologies (ICFMT2010), 2010:254-288.

[8] Ping Z, Jiang Y, Zhou S, Wu Y. FFT algorithm of complex exponent moments and its application in image recognition[C]//The Sixth International Conference on Digital Image Processing. International Society for Optics and Photonics (ICDIP2014), 2014:4177-4180.

[9] Hu H T, Zhang Y D, Shao C, Ju Q. Orthogonal moments based on exponent functions:exponent-Fourier moments[J]. Pattern Recognition, 201447(8):2596-2606.

[10] 姜永静. 指数矩及其在模式识别中的应用[D]. 北京:北京邮电大学,2011:71-73.

[11] Yang H Y, Wang X Y, Wang P, Niu P P. Geometrically resilient digital watermarking scheme based on radial harmonic Fourier moments magnitude[J]. AEU-International Journal of Electronics and Communications, 2015, 69(1):389-399.

[12] Schaefer G, Stich M. UCID:an uncompressed color image database[J]. Proceedings of SPIEthe International Society for Optical Engineering, 2004, 5307:472-480.

[13] 沈兰荪,张菁,李晓光. 图像检索与压缩域处理技术的研究[M]. 北京:人民邮电出版社,2009:40-45.

[14] Huynh-Thu Q, Ghanbari M. Scope of validity of PSNR in image/video quality assessment[J]. Electronics Letters, 2008, 44(13):800-801.

[15] Itti L, Koch C. Computational modelling of visual attention[J]. Nature Reviews Neuroscience, 2001, 2(3):194-203.

高分辨率图像的指数矩描述

High-Resolution Image Based on Exponent Moments

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价

[1]	曹欣, 李战明, 胡文瑾. 一种彩色图像质量评价方法[J]. 应用科学学报, 2019, 37(3): 398-406.
[2]	李洪均. 根据小波系数分布参数进行图像质量无参考评价[J]. 应用科学学报, 2013, 31(2): 170-176.
[3]	王保云，张荣，尹东. 基于局部结构信息的图像质量评价空间汇集策略[J]. 应用科学学报, 2011, 29(5): 473-482.