Image quality metric based on regular structure features

Abstract The objective assessment of image quality has been extensively studied in recent years, and a large number of evaluation algorithms have been presented. The existing evaluation algorithms of image quality has already exhibited satisfactory performances in many common image distortion models, such as additive noise, grayscale adjustment, low pass filter, motion blurring, lossy compression, etc. However, most of them have no effect on the geometric distortion, which is widely existed in the digital images. In view of geometric distortion, a full-reference image quality assessment method is presented in this paper. The core idea of this method is that only the geometric distortion acting on regular structure features of image can have significant impacts on the perceptive quality of the image, and the physical strength and spatial irregularity of geometric distortion are the main factors causing the decline of image quality. According to experimental data, the proposed assessment method can be well applied to geometric distortion model, the evaluation results are better than most of the existing methods, and it has showed significant correlation with MOS.

[1]  Ernest Valveny,et al.  A new use of the ridgelets transform for describing linear singularities in images , 2006, Pattern Recognit. Lett..

[2]  Zhou Wang,et al.  Applications of Objective Image Quality Assessment Methods [Applications Corner] , 2011, IEEE Signal Processing Magazine.

[3]  E. Supriyanto,et al.  Automatic image quality monitoring system for low cost ultrasound machine , 2008, 2008 International Conference on Information Technology and Applications in Biomedicine.

[4]  Lining Sun,et al.  A novel Hough transform method for line detection by enhancing accumulator array , 2011, Pattern Recognit. Lett..

[5]  Mauro Barni,et al.  A Full-Reference Quality Metric for Geometrically Distorted Images , 2010, IEEE Transactions on Image Processing.

[6]  L. November,et al.  Measurement of geometric distortion in a turbulent atmosphere. , 1986, Applied optics.

[7]  Mauro Barni,et al.  Perceptual quality evaluation of geometric distortions in images , 2007, Electronic Imaging.

[8]  A. Bovik,et al.  A universal image quality index , 2002, IEEE Signal Processing Letters.

[9]  Ming Zhang,et al.  A weight-constrained FxLMS algorithm for feedforward active noise control systems , 2002, IEEE Signal Process. Lett..

[10]  Zhou Wang,et al.  Applications of Objective Image Quality Assessment Methods , 2011 .

[11]  Rabab Kreidieh Ward,et al.  Image quality monitoring using spread spectrum watermarking , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[12]  Gerik Scheuermann,et al.  Clifford Fourier transform on vector fields , 2005, IEEE Transactions on Visualization and Computer Graphics.

[13]  A. Ardeshir Goshtasby,et al.  Registration of images with geometric distortions , 1988 .

[14]  Mark Holden,et al.  Detection and correction of geometric distortion in 3D MR images , 2001, SPIE Medical Imaging.

[15]  Heung-Kyu Lee,et al.  Invariant image watermark using Zernike moments , 2003, IEEE Trans. Circuits Syst. Video Technol..

[16]  Iwan Setyawan,et al.  Perceptual quality evaluation of geometrically distorted images using relevant geometric transformation modeling , 2003, IS&T/SPIE Electronic Imaging.

[17]  Ming Zhou,et al.  Anti-Geometrical Attacks Image Watermarking Scheme Based on Template Watermark , 2009, 2009 International Symposium on Computer Network and Multimedia Technology.

[18]  Prateek Gupta,et al.  A modified PSNR metric based on HVS for quality assessment of color images , 2011, 2011 International Conference on Communication and Industrial Application.

[19]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[20]  Hany Farid,et al.  Medical image registration with partial data , 2006, Medical Image Anal..