计算机科学 ›› 2017, Vol. 44 ›› Issue (7): 293-298.doi: 10.11896/j.issn.1002-137X.2017.07.053

• 图形图像与模式识别 • 上一篇    下一篇

多尺度下幅度谱与相位谱相融合的视觉注意建模

袁小艳,王安志,潘刚,王明辉   

  1. 四川大学计算机学院 成都610064;四川文理学院智能制造学院 达州635000,四川大学计算机学院 成都610064,四川文理学院智能制造学院 达州635000,四川大学计算机学院 成都610064
  • 出版日期:2018-11-13 发布日期:2018-11-13
  • 基金资助:
    本文受国家重点研究与发展计划(2016YFB0700802,6YFB0800600),国家海洋局海洋遥感工程技术研究中心创新青年项目(2015001),四川文理学院2015年度特色培育一般项目(2015TP001Y),四川文理学院智能制造产业技术开发研究专项项目(2017ZZ006Y)资助

Visual Attention Modeling Based on Multi-scale Fusion of Amplitude Spectrum and Phase Spectrum

YUAN Xiao-yan, WANG An-zhi, PAN Gang and WANG Ming-hui   

  • Online:2018-11-13 Published:2018-11-13

摘要: 针对现有大多数频域显著性检测算法仅单独使用频域幅度谱或相位谱的不足,提出了多尺度下频域幅度谱与相位谱相结合的视觉注意模型。该模型先对图像进行四元变换以得到幅度谱和相位谱,然后对幅度谱进行了伽马修正和高斯滤波,最后采用信息熵作为权重对多尺度显著图进行融合。在两个公开数据集Bruce和Judd上,采用ROC曲线、AUC值和F-Measure测量方法对算法进行了验证和评估。实验结果表明提出的算法优于现有的5种视觉注意模型,能够更准确地预测出人们注意的显著区域,取得了更令人满意的结果。

关键词: 多尺度,幅度谱,相位谱,信息熵,视觉注意

Abstract: Aiming at the deficiency of most existing frequency domain saliency detection algorithms which only use frequency domain amplitude spectrum or phase spectrum information alone,a visual attention model combining multi-scale frequency amplitude spectrum and phase spectrum was proposed.Firstly,the amplitude spectrum and the phase spectrum are obtained by quaternary transforming the image,and then the gamma correction and Gaussian filtering are performed on the amplitude spectrum.Finally,the entropy is used as weight to fuse the multi-scale saliency map.On the two published data sets,Bruce and Judd,the ROC curve,AUC value and F-Measure method were used to validate and evaluate the algorithm.The experimental results show that the proposed algorithm outperforms five visual attention models, predicts the significant attention areas more accurately,and achieves more satisfactory results.

Key words: Multi-scale,Amplitude spectrum,Phase spectrum,Information entropy,Visual attention

[1] QIAN X L,GUO L,HAN J W,et al.A Spectral AlgorithmBased on Weighted Sparse Coding for Visual Saliency Detection[J].Acta electronica Sinica,2013,41(6):1159-1165.(in Chinese) 钱晓亮,郭雷,韩军伟,等.一种基于加权稀疏编码的频域视觉显著性检测算法[J].电子学报,2013,41(6):1159-1165.
[2] WANG F J,TIAN M,HUANG Y P,et al.Classification Model of Visual Attention Based on Eye Movement Data[J].Computer Science,2016,43(1):85-89.(in Chinese) 王凤娇,田媚,黄雅平,等.基于眼动数据的分类视觉注意模型[J].计算机科学,2016,43(1):85-89.
[3] LI C,LI Y L,AN D X,et al.UWB SAR Change Detection of Foliage-Concealed Targets Based on Visual Attention[J].Acta Electronica Sinica,2016,44(1):39-46.(in Chinese) 李超,李悦丽,安道祥,等.基于视觉注意机制的UWBSAR叶簇隐蔽目标变化检测[J].电子学报,2016,44(1):39-46.
[4] ZHOU J B,REN Y F,YAN Y Y.Unsupervised Image Segmentation Based on Saliency Detection[J].Computer Science,2015,2(8):52-56.(in Chinese) 周静波,任永峰,严云洋.基于视觉显著性的非监督图像分割[J].计算机科学,2015,2(8):52-56.
[5] HOU X D,ZHANG L Q.Saliency Detection:A Spectral Resi-dual Approach[C]∥Proceedings of IEEE Computer Vision and Pattern Recognition.Minneapolis,MN,2007:1-8.
[6] GUO C L,MA Q,ZHANG L M.Spatio-temporal Saliency Detection Using Phase Spectrum of Quaternion Fourier Transform[C]∥Proceedings of IEEE Computer Vision and Pattern Recognition.Anchorage,AK,2008:1-8.
[7] CASTLEMAN K.Digital Image Processing[M].Prentice-Hall,New York,1996.
[8] LI J,LEVINE M D,AN X J,et al.Visual Saliency Based onScale-Space Analysis in the Frequency Domain[J].IEEE Tran-sactions on Pattern Analysis and Machine Intelligence,2013,5(4):996-1010.
[9] ACHANTA R,HEMAMI S,ESTRADA F,et al.Frequency-tuned salient region detection[C]∥Proceedings of IEEE Confe-rence on Computer Vision and Pattern Recognition.Miami,FL,2009:1597-1604.
[10] YU Y,WANG B,ZHANG L M.Pulse discrete cosine transform for saliency-based visual attention[C]∥Proceedings of IEEE International Conference on Development and Learning.Shanghai,2009:1-6.
[11] SCHAUERTE B,STIEFELHAGEN R.Predicting human gaze using quaternion DCT image signature saliency and face detection[C]∥Proceedings of IEEE Workshop on the Applications of Computer Vision(WACV).Breckenridge,CO,2012:137-144.
[12] HOU X,HAREL J,KOCH C.Image Signature:HighlightingSparse Salient Regions[J].IEEE Transactions on Pattern Analy-sis and Machine Intelligence,2012,4(1):194-201.
[13] JUNG C,KIM C.A Unified Spectral-Domain Approach for Sa- liency Detection and Its Application to Automatic Object Segmentation[J].IEEE Transactions on Image Processing,2012,1(3):1272-1283.
[14] ZHAO B,DELP E J.Visual Saliency Models Based on Spectrum Processing[C]∥Proceedings of IEEE Winter Conference on Applications of Computer Vision.Waikoloa,HI,2015:976-981.
[15] MA X L,XIE X D,LAM K M,et al.Efficient saliency analysis based on wavelet transform and entropy theory[J].Journal of Visual Communication and Image Representation,2015,0(7):201-207.
[16] CHEN D Y,JIA T,WU C D.Visual saliency detection:From space to frequency[J].Signal Processing:Image Communication,2016,4(5):57-68.
[17] ITTI L,KOCH C,NIEBUR E.A Model of Saliency-Based Vi-sual Attention for Rapid Scene Analysis[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,0(11):1254-1259.
[18] LI M.Design and Implementation of a Biological PlausibilityVisual Attention Model In frequency Domain[D].Xinxiang:Henan Normal University,2015.(in Chinese) 李铭.生物可信性频域视觉注意模型的设计与实现[D].新乡:河南师范大学,2015.
[19] LI X H,LU H C,ZHANG L H,et al.Saliency Detection via Dense and Sparse Reconstruction[C]∥Proceedings of IEEE International Conference on Computer Vision.Sydney,NSW,2013:2976-2983.
[20] WANG A,WANG M,PAN G,et al.Salient object detection with high-level prior based on bayesian fusion[J].IET ComputerVision,2017,11(3):199-206.
[21] QIN Y,LU H,XU Y,et al.Saliency detection via Cellular Automata[C]∥Proceedings of IEEE Computer Vision and Pattern Recognition.Boston,MA,2015:110-119.
[22] BRUCE N D,TSOTSOS J K.Saliency,attention,and visual sear-ch:an information theoretic approach[J].Journal of Vision,2009,9(3):1-24.
[23] JUDD T,EHINGER K,DURAND F,et al.Learning to predict where humans look[C]∥Proceedings of IEEE International Conference on Computer Vision.Kyoto,2009:2106-2113.
[24] MURRAY N,VANRELL M,OTAZU X,et al.Saliency estimation using a non-parametric low-level vision model[C]∥Proceedings of IEEE Computer Vision and Pattern Recognition.Providence,RI,2011:433-440.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!