作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2013, Vol. 39 ›› Issue (4): 267-271. doi: 10.3969/j.issn.1000-3428.2013.04.061

• 图形图像处理 • 上一篇    下一篇

基于稀疏表示的图像模糊度评价方法

张 涛1,2,梁德群1,王新年1   

  1. (1. 大连海事大学信息科学技术学院,辽宁 大连 116026;2. 辽宁师范大学物理与电子技术学院,辽宁 大连 116029)
  • 收稿日期:2012-05-11 出版日期:2013-04-15 发布日期:2013-04-12
  • 作者简介:张 涛(1976-),女,讲师、博士研究生,主研方向:数字图像处理;梁德群,教授、博士生导师;王新年,副教授、博士
  • 基金资助:
    教育部博士点基金资助项目(20070151014);中央高校基本科研业务费专项基金资助项目(2012JC038)

Image Fuzzy Degree Assessment Method Based on Sparse Representation

ZHANG Tao   1,2, LIANG De-qun    1, WANG Xin-nian    1   

  1. (1. College of Information Science and Technology, Dalian Maritime University, Dalian 116026, China; 2. School of Physics and Electronic Technology, Liaoning Normal University, Dalian 116029, China)
  • Received:2012-05-11 Online:2013-04-15 Published:2013-04-12

摘要: 根据自然图像稀疏表示基函数类似Vl区简单细胞感受野的反应特性,以及系数反映神经元响应程度的特性,提出基于稀疏表示的图像模糊度评价方法。将输入图像分成互不重叠的块,采用训练好的词典对各块进行稀疏分解,并计算每块的关注度系数。将每块稀疏系数的p范数与关注度系数的加权和作为模糊度评价的依据。实验结果表明,该算法计算的模糊度相对于图像的模糊程度是单调的,具有较好的抗噪性,符合人眼视觉系统特性。

关键词: 图像质量评价, 模糊度, 图像稀疏表示, 向量范数, 人眼视觉系统, 感受野

Abstract: Based on the facts that natural images can be sparsely coded, and their basis functions are similar to the particular shapes of V1 simple-cell receptive fields and the sparse coefficients correspond to the response properties of visual neurons for the fixed patterns, a novel image fuzzy degree assessment method based on sparse representation is proposed. The flow chart of the proposed method is to divide the input image into no overlapped patches. The coefficient vectors and the visual attention weights of each patch are computed, and the fuzzy degree is represented by the linear superposition of the p-norm of sparse coefficient vectors and visual attention weights of each patch. Experimental results show that the proposed method is monotonic, robust to additive noises, and also consistent with human visual system.

Key words: image quality assessment, fuzzy degree, image sparse representation, vector norm, human visual system, receptive field

中图分类号: