计算机科学 ›› 2021, Vol. 48 ›› Issue (8): 99-105.doi: 10.11896/jsjkx.200700106

• 计算机图形学& 多媒体 • 上一篇    下一篇

基于随机森林的空域-频域联合特征全参考彩色图像质量评价方法

杨小琴, 刘国军, 郭建慧, 马文涛   

  1. 宁夏大学数学统计学院 银川750021
  • 收稿日期:2020-07-16 修回日期:2020-09-03 发布日期:2021-08-10
  • 通讯作者: 刘国军(liugj@nxu.edu.cn)
  • 基金资助:
    宁夏自然科学基金(2018AAC03014);国家自然科学基金(61461043,51769026);宁夏回族自治区重点研发项目(2019BEG03056);宁夏大学研究生创新项目(GIP2019011)

Full Reference Color Image Quality Assessment Method Based on Spatial and Frequency Domain Joint Features with Random Forest

YANG Xiao-qin, LIU Guo-jun, GUO Jian-hui, MA Wen-tao   

  1. School of Mathematics and Statistics,Ningxia University,Yinchuan 750021,China
  • Received:2020-07-16 Revised:2020-09-03 Published:2021-08-10
  • About author:YANG Xiao-qin,born in 1996,postgra-duate.Her main research interests include image quality assessment and machine learning.(yxq258351@163.com)LIU Guo-jun,born in 1978,Ph.D,professor,Ph.D supervisor,master tutor.His main research interests include wavelet and partial differential equations for image processing,image quality assessment,and machine learning.
  • Supported by:
    Natural Science Foundation of Ningxia(2018AAC03014),National Natural Science Foundation of China(61461043,51769026),Key Research and Development Projects of Ningxia(2019BEG03056) and Graduate Innovation Project of Ningxia University(GIP2019011).

摘要: 文中旨在设计一种可以自动评估图像质量,并达到与人类视觉系统相一致的客观评价算法。针对大多数传统的全参考图像质量评价方法只在空域中分析图像,并且在池策略上存在不足,文中提出了一种基于随机森林的空域-频域联合特征全参考彩色图像质量评价方法。该方法首先在空域上提取色度和梯度特征,刻画图像的颜色信息和空间结构信息;在频域上提取log-Gabor滤波器组响应后的纹理细节信息以及空间频率特征,将二者作为联合特征;然后利用随机森林学习特征向量与主观意见得分之间的映射关系,预测客观质量得分。在TID2013,TID2008和CSIQ 3个标准数据库上的实验结果表明,所提方法的综合评价性能优于目前主流的全参考评价算法,尤其是在TID2013数据库上其皮尔逊线性相关系数值达到了0.9397。

关键词: 全参考图像质量评价, 空域, 频域, 随机森林

Abstract: This paper is to design an objective evaluation algorithm that automatically evaluates image quality and is consistent with the human visual system.In view of the fact that most traditional full reference image quality assessment methods only analyze images in the spatial domain,and have shortcomings in pooling strategies,this paper proposes a random forest based spatial-frequency domain joint feature full reference color image quality evaluation method.Firstly,this method extracts the chroma and gradient features in the spatial domain,which are used to characterize the color information and spatial structure information of images.The texture detail information of the response of the log-Gabor filter bank and spatial frequency features are extracted in the frequency domain,which are used to be joint features.Then,random forest is implemented for learning the mapping relationship between the feature vector and the subjective opinion score to predict the objective quality score.Experiments conducted on three standard databases,i.e.TID2013,TID2008,and CSIQ show that the comprehensive evaluation performance by our method is better than the state-of-the-art full reference assessment algorithms,especially on TID2013 database,the Pearson linear correlation coefficient value can reach 0.9397.

Key words: Image quality assessment, Spatial domain, Frequency domain, Random forest

中图分类号: 

  • TP391
[1]WANG Z,BOVIK A C,WANG Z,et al.Modern Image Quality Assessment[M].Morgan & Claypool,2006.
[2]WANG Z,BOVIK A C,SHEIKHH R,et al.Image quality assessment:from error visiblity to structural similarity[J].IEEE Transactions on Image Processing,2004,13(4):600-612.
[3]ZHANG L,ZHANG L,MOU X Q,et al.FSIM:a feature similarity index for image quality assessment[J].IEEE Transactions on Image Processing,2011,20(8):2378-2386.
[4]GU K,LI L,LU H,et al.A fast reliable image quality predictor by fusing micro and macro-structures[J].IEEE Transactions on Industrial Electronics,2017,64(5):3903-3912.
[5]XUE W F,ZHANG L,MOU X Q,et al.Gradient magnitudesimilarity deviation:a highly efficient perceptual image quality index[J].IEEE Transactions on Image Processing,2014,23(2):684-695.
[6]YANG G,LI D,LU F,et al.RVSIM:a feature similarity method for full-reference image quality assessment[J].EURASIP Journal on Image & Video Processing,2018,2018(1):6.
[7]DONG W,BIE H,LU L,et al.Image quality assessment by considering multiscale and multidirectional visibility differences in shearlet domain[J].IEEE Access,2019,7:78715-78728.
[8]ZHANG L,SHEN Y,LI H Y.VSI:A visual saliency-induced index for perceptual image quality assessment[J].IEEE Transactions on Image Processing,2014,23(10):4270-4281.
[9]SMOLA A J,GUNTUKU S C.A tutorial on support vector regression[J].Statistics and Computing,2004,14:199-222.
[10]BREIMAN L.Random forests[J].Machine Learing,2001,45(1):5-32.
[11]HUANG G B,ZHU Q Y,SIEW C K.Extreme learning ma-chine:theory and applications[J].Neurocomputing,2006,70(1):489-501.
[12]HANSEN L K,SALAMON P.Neural network ensembles[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1990,12(10):993-1001.
[13]NARWARIA M,LIN W.SVD-based quality metric for imageand video using machine learning[J].IEEE Transactions on Systems,Man and Cybernetics,Part B (Cybernetics),2012,42(2):347-364.
[14]LIU T J,LIN W,KUO C C J.Image quality assessment usingmulti-method fusion[J].IEEE Transactions on Image Proces-sing,2013,22(5):1793-1807.
[15]PEI S C,CHEN L H.Image quality assessment using human visual DOG model fused with random forest[J].IEEE Transactions on Image Processing,2015,24(11):3282-3292.
[16]GAO F,WANG Y,LI P,et al.DeepSim:Deep similarity forimage quality assessment[J].Neurocomputing,2017,257(27):104-114.
[17]LIU H,YANG H,PAN Z K,et al.A learning based image quality assessment model assisted with visual saliency and gradient features[C]//2019 IEEE 4th International Conference on Signal and Image Processing.
[18]GROSS M H,KOCH R.Visualization of multidimensional shape and texture features in laser range data using complex-valued Gabor wavelets[J].IEEE Transactions on Visualization and Computer Graphics,1995,1(1):44-59.
[19]FIELD D J.Relations between the statistics of natural images and the response properties of cortical cells[J].Journal of the Optical Society of America.A,Optics and Image Science,1987,4(12):2379-2394.
[20]PONOMARENKO N,JIN L,LEREMEIEV O,et al.Image database TID2013:Peculiarities,results and perspectives[J].Signal Processing:Image Communication,2015,1(30):55-77.
[21]PONOMARENKO N,LUKIN V,ZELENSKY A,et al.TID2008:a database for evaluation of full-reference visual quality assessment metrics[J].Advances of Modern Radio electro-nics,2009,1(10):30-45.
[22]LARSON E C,CHANDLER D M.Most apparent distortion:full reference image quality assessment and the role of strategy[J].Journal of Electronic Imaging,2010,19(1):1-21.
[23]WANG Z,LI Q.Information content weighting for perceptualimage quality assessment[J].IEEE Transaction on Image Processing,2011,20(5):1185-1198.
[24]BAE S H,KIM M.A novel image quality assessment with glo-bally and locally consilient visual quality perception[J].IEEE Transactions on Image Processing,2016,25(5):2392-2406.
[25]GAO L X,LIU G J,ZHANG X D.Fast lifting IQA algorithm of the structure similarity index[J].Journal of Computer-Aided Design and Computer Graphics,2017,29(7):1314-1323.
[1] 邢豪, 李明. 基于3D CNNS的深度伪造视频篡改检测[J]. 计算机科学, 2021, 48(7): 86-92.
[2] 郑建华, 李小敏, 刘双印, 李迪. 融合级联上采样与下采样的改进随机森林不平衡数据分类算法[J]. 计算机科学, 2021, 48(7): 145-154.
[3] 曹扬晨, 朱国胜, 祁小云, 邹洁. 基于随机森林的入侵检测分类研究[J]. 计算机科学, 2021, 48(6A): 459-463.
[4] 李娜娜, 王勇, 周林, 邹春明, 田英杰, 郭乃网. 基于特征重要度二次筛选的DDoS攻击随机森林检测方法[J]. 计算机科学, 2021, 48(6A): 464-467.
[5] 徐佳庆, 胡小月, 唐付桥, 王强, 何杰. 基于随机森林的高性能互连网络阻塞故障检测[J]. 计算机科学, 2021, 48(6): 246-252.
[6] 周益旻, 刘方正, 王勇. 基于混合方法的IPSec VPN加密流量识别[J]. 计算机科学, 2021, 48(4): 295-302.
[7] 刘振鹏, 苏楠, 秦益文, 卢家欢, 李小菲. FS-CRF:基于特征切分与级联随机森林的异常点检测模型[J]. 计算机科学, 2020, 47(8): 185-188.
[8] 杨威超, 郭渊博, 李涛, 朱本全. 基于流量指纹的物联网设备识别方法和物联网安全模型[J]. 计算机科学, 2020, 47(7): 299-306.
[9] 陈晓文, 刘光帅, 刘望华, 李旭瑞. 结合LoG边缘检测和增强局部相位量化的模糊图像识别[J]. 计算机科学, 2020, 47(12): 197-204.
[10] 赵瑞杰, 施勇, 张涵, 龙军, 薛质. 基于TF-IDF的Webshell文件检测[J]. 计算机科学, 2020, 47(11A): 363-367.
[11] 王晓晖, 张亮, 李俊清, 孙玉翠, 田捷, 韩睿毅. 基于遗传算法与随机森林的XGBoost改进方法研究[J]. 计算机科学, 2020, 47(11A): 454-458.
[12] 李兴国, 任益枚, 田竞, 唐竟淇. SFRA方法在交流伺服系统中的应用研究[J]. 计算机科学, 2020, 47(11A): 628-631.
[13] 张彬彬, 王娟, 岳昆, 武浩, 郝佳. 基于随机森林的虚拟机性能预测与配置优化[J]. 计算机科学, 2019, 46(9): 85-92.
[14] 庞宇, 刘平, 雷印杰. 基于移动端的“非受控”物体识别算法的实现[J]. 计算机科学, 2019, 46(6A): 153-157.
[15] 石雨鑫, 邓洪敏, 郭伟林. 基于混合卷积神经网络的静态手势识别[J]. 计算机科学, 2019, 46(6A): 165-168.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 李小薪, 周元申, 周旋, 李晶晶, 刘志勇. 基于奇异值分解的Gabor遮挡字典学习[J]. 计算机科学, 2018, 45(6): 275 -283 .
[2] 刘玉成, 理查德·丁, 张颖超. 一种BPNNs识别算法的医学检测泛实时性问题研究[J]. 计算机科学, 2018, 45(6): 301 -307 .
[3] 李小薪,吴克宋,齐盼盼,周旋,刘志勇. 局部球面规范化嵌入:PCANet的一种改进方案[J]. 计算机科学, 2018, 45(5): 238 -242 .
[4] 李普, 孙长乐, 熊伟, 王海涛. 一种基于半透明颜色叠加与深度值的碰撞检测算法[J]. 计算机科学, 2018, 45(6A): 193 -197 .
[5] 刘洋, 张杰, 张慧. 一种改进的Retinex算法在图像去雾中的研究与应用[J]. 计算机科学, 2018, 45(6A): 242 -243 .
[6] 尹亮,何明利,谢文波,陈端兵. 装备-标准知识图谱的过程建模研究[J]. 计算机科学, 2018, 45(6A): 502 -505 .
[7] 张宁. 基于扩维的卷积网络及脉象识别应用[J]. 计算机科学, 2018, 45(6A): 506 -507 .
[8] 张旋, 姜超, 李晓强, 燕莎. 基于变量节点更新的梯度下降比特翻转译码算法[J]. 计算机科学, 2018, 45(8): 80 -83 .
[9] 赵广辉, 卓松, 徐晓龙. 基于卡尔曼滤波的多目标跟踪方法[J]. 计算机科学, 2018, 45(8): 253 -257 .
[10] 姚艳玲. 2017年国际人工智能领域研究前沿的分析与研究[J]. 计算机科学, 2018, 45(9): 1 -10 .