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 ›› 2007, Vol. 33 ›› Issue (19): 199-200,. doi: 10.3969/j.issn.1000-3428.2007.19.070

• 人工智能及识别技术 • 上一篇    下一篇

双尺度边缘结构相似度的图像质量评估

廖 斌,陈 岩   

  1. (华北电力大学电气与电子工程学院,北京 102206)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-10-05 发布日期:2007-10-05

Image Quality Assessment Based on Dual-scale Edge Structure Similarity

LIAO Bin, CHEN Yan   

  1. (School of Electric and Electronical Engineering, North China Electric University, Beijing 102206)
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-10-05 Published:2007-10-05

摘要: 图像质量评价对于各种视频图像应用具有重要的意义。结构相似度准则SSIM在模糊图像及噪声污染的图像判定方面,存在偏差。该文提出了基于双尺度边缘结构特征的图像质量评价算法——MDESSIM,充分考虑了边缘信息在结构信息中的重要性,通过增加边缘结构的失真度量来综合评价图像质量。实验结果表明了MDESSIM算法的有效性。

关键词: 图像质量评价, 结构相似度, 双尺度边缘结构, 主观感知质量

Abstract: The quality assessment of images is meaningful for most video and images applications. The structure similarity index(SSIM) shows some defects when evaluating the quality of blur images and noise images, the results don’t match the HVS system well. This paper proposes a new image quality assessment algorithm based on dual-scale edge structure similarity(MDESSIM). The edge information is appreciated sufficiently during the structure information in this algorithm. The distortion metric of edge structure is included in the assessment of the image quality. Experimental results demonstrate the MDESSIM algorithm is effective.

Key words: image quality assessment, structure similarity, dual-scale edge structure, subjective perceptual quality

中图分类号: