Sparse coding model based on structural similarity

被引：1
|
作者：
Li Z.-Q. [1 ,2 ,3 ]
Shi Z.-P. [1 ]
Li Z.-X. [1 ,2 ]
Shi Z.-Z. [1 ]
机构：
[1] Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, The Chinese Academy of Sciences
[2] Graduate University, The Chinese Academy of Sciences
[3] College of Information Engineering, Xiangtan University
来源：
Ruan Jian Xue Bao/Journal of Software | 2010年 / 21卷 / 10期
关键词：
Biological visual system; Computational model; Natural image; Sparse coding; Structural similarity;
D O I：
10.3724/SP.J.1001.2010.03675
中图分类号：
学科分类号：
摘要：
Current existing sparse coding models employ the mean square of the error between the actual image and the reconstructed image to measure how well the code describes the image. Under the assumption that human visual perception is highly adapted for extracting structural information from a scene or a video, an alternative measure for information preservation assessment, based on the structural similarity, is introduced. After minimizing the cost function, the improved model attains a complete family of localized, oriented, and bandpass receptive fields, similar to those found in the primary visual cortex. The experimental results show that the improved sparse coding model is more consistent in human visual system. © by Institute of Software, the Chinese Academy of Sciences.
引用
收藏
页码：2410 / 2419
页数：9
相关论文
共 29 条
  • [1] Marr D., Vision: A Computational Investigation into the Human Representation and Processing of Visual Information, (1982)
  • [2] Barlow H.B., Possible principles underlying the transformation of sensory messages, Proc. of the Sensory Communication, pp. 217-234, (1961)
  • [3] Atick J.J., Redlich A.N., What does the retina know about natural scenes, Neural Computation, 4, 2, pp. 196-210, (1992)
  • [4] Olshausen B.A., Field D.J., Emergence of simple-cell receptive field properties by learning a sparse code for natural images, Nature, 381, 6583, pp. 607-609, (1996)
  • [5] Field D.J., What is the goal of sensory coding, Neural Computation, 6, 44, pp. 559-601, (1994)
  • [6] Field D.J., Relations between the statistics of natural images and the response properties of cortical cells, Journal of the Optical Society of America A: Optics, Image Science, and Vision, 4, 12, pp. 2379-2394, (1987)
  • [7] Hyvarinen A., Hoyer P.O., A two-layer sparse coding model learns simple and complex cell receptive fields and topography from natural images, Vision Research, 41, 18, pp. 2413-2423, (2001)
  • [8] Tenenbaum J.B., Freeman W.T., Separating style and content with bilinear models, Neural Computation, 12, 6, pp. 1247-1283, (2000)
  • [9] Grimes D.B., Rao R.P.N., Bilinear sparse coding for invariant vision, Neural Computation, 17, 1, pp. 47-73, (2005)
  • [10] Hoyer P.O., Modeling receptive fields with non-negative sparse coding, Neurocomputing, 52-54, 1, pp. 547-552, (2003)
123