期刊文献+

一种图像尺寸调整的纹理感知突出边缘模型

A Texture-Perceived Salient Edge Model for Image Resizing
下载PDF
导出
摘要 图像尺寸调整的目的是将一幅给定图像调整为任意指定大小而不产生视觉扭曲,为此,须定义可靠的图像重要性图.利用总变差正则化空间的高阶统计提出一种新的图像重要性图,称之为纹理感知突出边缘图,基于纹理感知突出边缘图利用重要性扩散方法对图像进行尺寸调整.数值实验结果显示,在图像背景杂乱且受到噪声干扰的情况下,与目前流行的其他方法相比,文中方法能获得更好的图像尺寸调整效果. Image resizing aims at adapting a given image to an arbitrary size without severe visual distortions .To do this ,it is essential to define a reliable Image Importance Image (IIM ) .By using the Higher Order Statistics (HOS ) of the Total Variation (TV ) regularization space .A novel IIM is introduced ,which is called Texture-Perceived Salient Edge (TPSE) map .The numerical experiments show that the proposed method is more effective for image resizing than the popular methods in the cluttered background and in the presence of noise as well .
作者 张文娟 何鑫
出处 《西安工业大学学报》 CAS 2014年第7期555-559,共5页 Journal of Xi’an Technological University
基金 陕西省教育厅项目(12JK0852) 陕西省科技厅项目(2014JM1018)
关键词 变差正则化空间 高阶统计 图像重要性图 纹理感知突出边缘图 total variation regularization space higher order statistics image importance image
  • 相关文献

参考文献11

  • 1AVIDAN S, SHAMIR A. Seam Carving for Content- aware hnage Resizing[J].ACM Trans Graph,2007, 26(3) :267. 被引量:1
  • 2PAVLOPOULOU C, YU S X. Indoor-Outdoor Clas-sification with Human Accuracies:Image or Edge Gist [C]//Proc IEEE Computer Vision and Pattern Rec- ognition Workshops (CVPRW), J un, 2010 : 41. 被引量:1
  • 3HOU X,ZHANG X. Saliency Detection: A Spectral Re- sidual Approach [C]//2007 IEEE Conference on Com- puter Vision and Pattern Recognition (CVPR).2007. 被引量:1
  • 4ZHANG L, TONG M, MARKS T, et al. A Bayesian Framework for Saliency Using Natural Statisties[J]. Journal of Vision,2008,8(7) ;1. 被引量:1
  • 5WANG D, I.I G Q,JIA W J. Saliency-driven Scaling Optimization for Image Retargeting[J]. The Visual Computer,2011,27(9) :853. 被引量:1
  • 6GOFERMAN S, MANOR L Z, TAL A. Context-a- ware Saliency Detection[J]. Pattern Analysis and Ma- chine Intelligence,2012,34(10) : 1915. 被引量:1
  • 7KIM W, JUNG C, KIM C. Spatiotemporal Saliency Detection and Its Applications in Static and Dynamic Scenes[J]. IEEE Trans CircuitsSyst Video Technol,2011,21(4):446. 被引量:1
  • 8ALEXE B, DESELASRS T, FERRARI V. What Is An Obieet[C]//2010 IEEE Conference on Computer Vision and Pattern Recognition(CVPR),2010. 被引量:1
  • 9BROX T, WEICKERT J. A TV Flow Based Local Scale Estimate and Its Application to Texture Dis- crimination[J]. Journal of Visual Communication and Image Representation, 2006,17(5) : 1053. 被引量:1
  • 10王会千,杨高波,张兆扬,夏中超.基于重要度扩散和自适应采样的图像/视频缩放技术[J].通信学报,2011,32(8):165-170. 被引量:9

二级参考文献10

  • 1LIU F, GLEICHER M. Automatic image retargeting with fish- eye-view warping[A]. Proceedings of the Eighteenth Annual ACM Symposium on User Interface Software and Technology[C]. Seattle, USA, 2005. 153-162. 被引量:1
  • 2时健 郭延文 杜振龙等.一种基于网格参数化的图像适应方法.软件学报,2008,19(1):19-30. 被引量:4
  • 3AVIDAN S, SHAMIR A. Seam carving for content-aware image resizing [J]. ACM Transactions on Graphics, 2007, 26(3): 267-276. 被引量:1
  • 4RUBINSTEIN M, AVIDAN S, SHAMIR A. Improved seam carving for video retargeting[J]. ACM Transactions on Graphics, 27(3): 1-9, 2008. 被引量:1
  • 5KIM J H, KIM J S, KIM C S. Image and video using adaptive scaling function[A]. ~gs of IEEE CVPR[C]. Florida, USA, 2009. 106-114. 被引量:1
  • 6CHIANG C K, WANG S F, CHEN Y L, et al. Fast JND-based video carving with GPU acceleration for real-time video retargeting[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2009,19(11): 1588-1597. 被引量:1
  • 7GRUNDMANN M, KWATRA V, HAN M, et al. Discontinuous seam-carving for video retargeting[A]. Proceedings of IEEE CVPR[C]. San Francisco, USA, 2010. 569-576. 被引量:1
  • 8ITrI L, KOCH C, NIEBUR E. A model of saliency-based visual attention for rapid scene analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(11): 1254-1259. 被引量:1
  • 9CHO S, CHOI H, MATSUSHITA Y, et al. Image retargeting using importance diffusion[A]. Proceedings of IEEE ICIP[C]. Cairo, Egypt, 2009. 977-980. 被引量:1
  • 10聂栋栋,马勤勇.基于全局图像结构信息的Seam Carving算法[J].计算机应用研究,2011,28(3):1198-1200. 被引量:2

共引文献8

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部