计算机应用 ›› 2010, Vol. 30 ›› Issue (06): 1622-1625.

• 图形图像处理与模式识别 • 上一篇    下一篇

基于结构方向信息的图像质量评价方法

王强1,梁德群1,毕胜1,薄瑜2   

  1. 1. 大连海事大学信息科学技术学院
    2.
  • 收稿日期:2009-11-30 修回日期:2010-01-26 发布日期:2010-06-01 出版日期:2010-06-01
  • 通讯作者: 王强

Image quality assessment based on structural orientation information

  • Received:2009-11-30 Revised:2010-01-26 Online:2010-06-01 Published:2010-06-01

摘要: 结构相似度(SSIM)方法通过度量原图像和失真图像之间的结构相似程度,达到了比传统PSNR方法更好的图像质量评价效果。但SSIM算法本身并没有充分利用图像的结构信息,在SSIM算法的基础上进一步挖掘图像结构中包含的方向信息,提出了局部结构方向相似度(LSOS),将LSOS方法和现有的SIExt算法相结合,提出基于结构方向信息的图像质量评价算法(SOI)。实验表明,该方法能够达到比SIExt和SSIM方法更好的图像质量评价结果。

关键词: 图像质量评价, 结构信息, 结构相似度, 结构方向相似度, 人眼视觉系统

Abstract: Compared with the traditional Peak Signal-to-Noise Ratio (PSNR) method, the Structural Similarity (SSIM) method can achieve better image assessment by measuring the SSIM between the reference image and the distortion image, but the structural information is not completely extracted. Based on SSIM method, the orientation information was further extracted and the Local Structural Orientation Similarity (LSOS) was proposed. Then, the LSOS method was incorporated with the existing SIExt algorithm and an image quality assessment method based on Structural Orientation Information (SOI) was presented. The experiments show that the SOI model can assess the distortion image more precisely than the SIExt and SSIM methods.

Key words: image quality assessment, structural information, structural similarity, structural orientation similarity, human visual system