计算机科学 ›› 2020, Vol. 47 ›› Issue (11): 192-198.doi: 10.11896/jsjkx.191000101
赵亮, 彭宏京, 杜振龙
ZHAO Liang, PENG Hong-jing, DU Zhen-long
摘要: 图像重定向是一种通过调整图像大小,使其适合于任意显示终端高宽比的数字媒体处理技术。现有的图像重定向研究大多集中在重要对象的形状保持上,而对人类视觉系统敏感的图像关键特征缺乏充分考虑,导致视觉接受度较低。由此,提出了一种新的基于显式的SURF特征保留的图像重定向算法。不同于一般的基于顶点或轴对齐的网格编码形式的网格变形技术,该方法采用基于网格边的网格变形技术。首先定义一个仿射矩阵,使得每条网格边根据仿射矩阵进行变形,从而形成一个基本的基于网格边的变形模型;然后通过SURF特征检测得到SURF特征区域,再将网格边范围约束至SURF特征区域,以此达到特征保留的效果;最后得到一个新的网格变形模型。另外,通过在基本网格变形模型的基础上设置一个稀疏能量项,即给每条网格边赋初始权重以使网格线彼此稀疏,来解决网格线自交的问题;而且在必要时在迭代求解的过程中还可更新此权重。通过实验将所提方法与两种现有的图像重定向方法进行图像质量评估,结果表明所提方法能够在图像重定向过程中最小化失真,同时产生较好的视觉效果,得分增益最高可分别达到16.0%和9.7%。
中图分类号:
[1] AVIDAN S,SHAMIR A.Seam carving for content-aware image resizing[J].ACM Transactions on Graphics,2007,26(3):10. [2] RUBINSTEIN M,SHAMIR A,AVIDAN S.Improved seamcarving for video retargeting[J].ACM Transactions on Gra-phics,2008,27(3):1. [3] HWANG D S,CHIEN S Y.Content-aware image resizing using perceptual seam carving with human attention model[C]//IEEE International Conference on Multimedia & Expo.IEEE,2008. [4] CHOI J,KIM C.Sparse Seam-Carving for Structure Preserving Image Retargeting[J].Journal of Signal Processing Systems,2015,85(2):1-9. [5] BATTIATO S,FARINELLA G M,PUGLISI G,et al.Saliency-Based Selection of Gradient Vector Flow Paths for Content Aware Image Resizing[J].IEEE Transactions on Image Proces-sing,2014,23(5):2081-2095. [6] WANG Y S,TAI C L,SORKINE O,et al.Optimized scale-and-stretch for image resizing[C]//Acm Siggraph Asia.2008:118. [7] GUO Y,LIU F,SHI J,et al.Image Retargeting Using Mesh Parametrization[J].IEEE Transactions on Multimedia,2009,11(5):856-867. [8] ZHANG G X,CHENG M M,HU S M,et al.A Shape-Preserving Approach to Image Resizing[J].Computer Graphics Forum,2009,28(7):1897-1906. [9] ZHOU B,WANG X,CAO S,et al.Optimal bi-directional seam carving for compressibility-aware image retargeting[J].Journal of Visual Communication and Image Representation,2016,41(NOV.):21-30. [10] LIN S S,YEH I C,LIN C H,et al.Patch-Based Image Warping for Content-Aware Retargeting[J].IEEE Transactions on Multimedia,2013,15(2):359-368. [11] CHANG C H,CHUANG Y Y.A Line-Structure-PreservingApproach to Image Resizing[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).IEEE,2012. [12] PANOZZO D,WEBER O,SORKINE O.Robust Image Retar-geting via Axisâ-Aligned Deformation[J].Computer Graphics Forum,2012,31(2pt1):229-236. [13] CHOI S,HAM B,SOHN K.Fast image retargeting via axis-aligned importance scaling[C]//2013 IEEE International Conference on Image Processing.IEEE,2014. [14] DAS B C,GOPALAKRISHNAN V,IYER K N,et al.Similarity and rigidity preserving image retargeting[C]//2016 IEEE International Conference on Image Processing (ICIP).IEEE,2016. [15] KIM Y,JUNG S,JUNG C,et al.A structure-aware axis-aligned grid deformation approach for robust image retargeting[J].Multimedia Tools and Applications,2018,77(6):7717-7739. [16] HUA S,CHEN G,WEI H,et al.Similarity measure for image resizing using SIFT feature[J].EURASIP Journal on Image and Video Processing,2012,2012(1):6. [17] BAY H,ESS A,TUYTELAARS T,et al.Speeded-Up Robust Features (SURF)[J].Computer Vision and Image Understan-ding,2008,110(3):346-359. [18] LOWE D G.Distinctive Image Features from Scale-InvariantKeypoints[J].International Journal of Computer Vision,2004,60(2):91-110. [19] UMEYAMA S.Least-squares estimation of transformation parameters between two point patterns[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1991,13(4):376-380. [20] RUBINSTEIN M,GUTIERREZ D,SORKINE O,et al.A Comparative Study of Image Retargeting[J].ACM Transactions on Graphics,2010,29(6):160. [21] LIU Y J,LUO X,XUAN Y M,et al.Image Retargeting Quality Assessment[J].Computer Graphics Forum,2011,30(2):583-592. |
[1] | 李凯文, 徐琳, 陈强. 基于CPNet的相对图像质量评估 Relative Image Quality Assessment Based on CPNet 计算机科学, 2020, 47(11): 159-167. https://doi.org/10.11896/jsjkx.190900052 |
|