基于BP神经网络的图像质量评价参数优化

范媛媛; 桑英军; 沈湘衡

基于BP神经网络的图像质量评价参数优化

范媛媛^1,2,3, ,,
桑英军¹,
沈湘衡²

1.
淮阴工学院,江苏淮安 223003;
2.
中国科学院长春光学精密机械与物理研究所,吉林长春 130033;
3.
中国科学院研究生院,北京 100039

详细信息

通讯作者:
范媛媛（1979-），女，山东邹城人，博士研究生，主要从事图像处理及图像质量评价方面的研究。

中图分类号: TN206;TP391.4
计量
- 文章访问数: 3603
- HTML全文浏览量: 124
- PDF下载量: 509
出版历程
- 刊出日期: 2011-11-14

Optimization of image quality assessment parameters based on back-propagation neural network

1.
Huaiyin Institute of Technology,Huaian 223003,China;
2.
Changchun Institute of Optics,Fine Mechanics and Physics,CAS,Changchun 130033 China;
3.
Graduate University of Chinese Academy of Sciences,Beijing 100039,China

摘要

摘要: 在基于噪声图像的无参考峰值信噪比质量评价方法中，为了得到最优的阈值参数,提出以图像块均方误差阈值threshold1、噪声检测阈值threshold2为输入因子, 以Pearson相关系数和Spearman等级相关系数为输出因子, 以实验值为样本建立［2 7 2］单隐层BP神经网络模型，应用BP神经网络的泛化能力实现对相关阈值参数的预测优化，为阈值参数的选择提供理论依据。实验结果表明，所建立的数学模型可靠，预测结果与试验值的偏差小，训练好的BP神经网络能够比较准确地预测不同阈值参数下的相关系数。优化后，选取threshold1=101，threshold2=4，Pearson相关系数达到了-0.895 0，Spearman等级相关系数达到了-0.913 6，评价效果得到提高，且节省大量时间。
- 图像质量评价 /
- 参数优化 /
- BP神经网络 /
- 预测 /
- 泛化
Abstract: In no reference peak signal to noise ratio (PSNR) image quality assessment based on noisy images, in order to get optimal threshold parameters, it is proposed that taking experiment values as a sample, a ［2 7 2］ back-propagation (BP) neural network model is established with the mean square error (MSE) threshold1 of image block and the noise detection threshold2 as the input factors, and the Person and Spearman correlation coefficients as the output factors. The model realizes the prediction of relevant parameters by its generalization capability and offers a theoretical foundation for parameters selection. Experiments indicate that the model is reliable. The prediction results show little difference from the experimental data. The trained BP neural network can precisely predict the relevant parameters. After optimizing, threshold1=101 and threshold2=4 are selected, Pearson Correlation Coefficient and Spearman Rank Order Correlation Coefficient reaches -0.895 0 and -0.913 6 respectively. The assessment result improves a lot, and much time is saved.
- image quality assessment /
- parameters optimization /
- back-propagation neural network /
- forecast /
- generalization

HTML全文

参考文献(1)

［1］SHEIKH H R.Image quality assessment using natural scene statistics［D］.Austin:The University of Texas,2004.
［2］MARZILIANO P,DUFAUX F,WINKLER S,et al.Perceptual blur and ringing metrics:application to JPEG2000［J］.Sigman Processing:Image Communication,2004,19(2):163-172.
［3］ONG E,LIN W,LU Z, et al,No-reference quality metric for measuring image blur［J］.IEEE International Conference on Image Processing,2003,1:467-472.
［4］谢小甫,周进,吴钦章. 一种针对图像模糊的无参考质量评价指标［J］. 计算机应用,2010,30(4):921-924.
XIE Xiao-fu,ZHOU Jin,WU Qin-zhang. No-reference quality index for image blur［J］. Journal of Computer Applications, 2010,30(4):921-924. (in Chinese with an English abstract)
［5］汪孔桥,Jari A Kangas.数字图像的质量评价［J］.测控技术, 2000,19(5): 14-16.
WANG Kong-qiao,KANGAS J A.Quality assessment of digital［J］.Images Measurment &Control Technology, 2000,19(5): 14-16. (in Chinese with an English abstract)
［6］ESKICIOGLN A, FISHER P. Image measures and their performance［J］. IEEE Transactions Communications, 1995, 43(12): 2959-2965.
［7］HOSAKA K. A new picture quality evaluation method［C］. ［S.l.］:Proceedings of the International Picture Coding Symposium,1986.
［8］葛哲学,孙志强.神经网络理论与MATLAB R2007实现［M］.北京:电子工业出版社, 2007.
GE Zhe-xue，SUN Zhi-qiang. Neural network theory and Matlab application［M］. Beijing: Publishing House of Electronics Industry，2007. (in Chinese)
［9］ZHANG L P, YU H J, HU S X. Optimal choice of parameters for particle swarm optimization ［J］. Journal of Zhejiang University Science, 2005, 6(6): 528-534.
［10］SHEIKH H, WANG Z, CORMACK L,et al. Live image quality assessment database ,release 2［EB/OL］. ［2008-08-27］.http:∥live.ece.utexas.edu/research/quality.
［11］赵彬,王新民,史良贵，等. 基于BP神经网络的爆破参数优选［J］.矿冶工程,2009,29(4):24-27.
ZHAO Bin,WANG Xin-min, SHI Liang-gui, et al. Optimization of blasting parameters based on back-propagation neural network［J］. Mining and Metallurgical Engineering, 2009,29(4):24-27. (in Chinese with an English abstract)

施引文献

资源附件(0)

计量

文章访问数: 3603
HTML全文浏览量: 124
PDF下载量: 509
被引次数: 0

基于BP神经网络的图像质量评价参数优化

通讯作者:
范媛媛（1979-），女，山东邹城人，博士研究生，主要从事图像处理及图像质量评价方面的研究。

计量

Optimization of image quality assessment parameters based on back-propagation neural network

计量

目录

相关数据库

广告合作

友情链接

帮助中心

基于BP神经网络的图像质量评价参数优化

通讯作者: 范媛媛（1979-），女，山东邹城人，博士研究生，主要从事图像处理及图像质量评价方面的研究。

计量

出版历程

Optimization of image quality assessment parameters based on back-propagation neural network

计量

出版历程

目录

相关数据库

广告合作

友情链接

帮助中心

通讯作者:
范媛媛（1979-），女，山东邹城人，博士研究生，主要从事图像处理及图像质量评价方面的研究。