北京航空航天大学学报 ›› 2006, Vol. 32 ›› Issue (09): 1031-1034.

• 论文 • 上一篇    下一篇

基于NN与SVM的图像质量评价模型

佟雨兵1, 张其善1, 常青1, 祁云平3   

  1. 1. 北京航空航天大学 电子信息工程学院, 北京 100083;
    2. 西北师范大学 物理与电子信息工程学院, 兰州 730070
  • 收稿日期:2005-11-29 出版日期:2006-09-30 发布日期:2010-09-19
  • 作者简介:佟雨兵(1977-),男,山东济宁人,博士生, ybtong@ee.buaa.edu.cn.

Image quality assessing model by using neural network and support vector machine

Tong Yubing1, Zhang Qishan1, Chang Qing1, Qi Yunping3   

  1. 1. School of Electronics and Information Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100083, China;
    2. College of Physics and Electrical & Information, Northwest Normal University, Lanzhou 730070, China
  • Received:2005-11-29 Online:2006-09-30 Published:2010-09-19

摘要: 为了有效地评价图像质量,利用峰值信噪比(PSNR,Pear Signal to Noise Ratio)和结构相似度(SSIM,Structure Similarity)作为图像质量的描述参数,给出"野点"的定义,提出"野点预测"并基于神经网络(NN,Neural Network)与支持向量机(SVM,Support Vector Machines)建立新的质量评价模型:神经网络用来获取质量评价映射函数,支持向量机实现样本分类.采用UTexas图像库数据进行仿真试验,质量评价模型预测图像质量的单调性比PSNR提高7.42% ,质量评价模型预测结果的均方误差平方根比PSNR提高36.06%,模型性能测试中"野点"的数目相对减少,模型性能得以提高.试验结果表明该模型的输出能有效地反映图像的主观质量.

Abstract: Pear signal to noise ratio(PSNR) and structure similarity(SSIM) as two indexes describing image quality were used with neural network(NN) and support vector machine(SVM) to set up new effective image quality assessing model. The definition of isolated points and the prediction of isolated points were illuminated. NN was used to obtain the image quality assessing mapping functions and SVM was used to classify the samples into different types. UTexas image database was used in simulation experiment. With the same level of consistency of quality assessing model, the prediction monotonicity of the model is 7.42% higher than PSNR. The root mean square error (rmse) of the model is 36.06% higher than PSNR. The number of isolated points with the new model was reduced and the performance of the model was enhanced. The results from simulation experiment show the model valid. The output of the new model can effectively reflect the image subjective quality.

中图分类号: 


版权所有 © 《北京航空航天大学学报》编辑部
通讯地址:北京市海淀区学院路37号 北京航空航天大学学报编辑部 邮编:100191 E-mail:jbuaa@buaa.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发