Image quality assessment based on S-CIELAB model

Publication Type:
Journal Article
Citation:
Signal, Image and Video Processing, 2011, 5 (3), pp. 283 - 290
Issue Date:
2011-09-01
Full metadata record
Files in This Item:
Filename Description Size
Thumbnail2011000267OK.pdf864.67 kB
Adobe PDF
This paper proposes a new image quality assessment framework which is based on color perceptual model. By analyzing the shortages of the existing image quality assessment methods and combining the color perceptual model, the general framework of color image quality assessment based on the S-CIELAB color space is presented. The S-CIELAB color model, a spatial extension of CIELAB, has an excellent performance for mimicking the perceptual processing of human color vision. This paper incorporates excellent color perceptual characteristics model with the geometrical distortion measurement to assess the image quality. First, the reference and distorted images are transformed into S-CIELAB color perceptual space, and the transformed images are evaluated by existing metric in three color perceptual channels. The fidelity factors of three channels are weighted to obtain the image quality. Experimental results achieved on LIVE database II shows that the proposed methods are in good consistency with human subjective assessment results. © 2011 Springer-Verlag London Limited.
Please use this identifier to cite or link to this item: