Blur detection for digital images using wavelet transform

With the prevalence of digital cameras, the number of digital images increases quickly, which raises the demand for image quality assessment in terms of blur. Based on the edge type and sharpness analysis, using the Harr wavelet transform, a new blur detection scheme is proposed in this paper, which can determine whether an image is blurred or not and to what extent an image is blurred. Experimental results demonstrate the effectiveness of the proposed scheme.

[1]  Wilfried Philips,et al.  Estimating image blur in the wavelet domain. , 2001 .

[2]  Stéphane Mallat,et al.  Singularity detection and processing with wavelets , 1992, IEEE Trans. Inf. Theory.

[3]  Wei-Ying Ma,et al.  Blur determination in the compressed domain using DCT information , 1999, Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348).

[4]  A. Murat Tekalp,et al.  Maximum likelihood parametric blur identification based on a continuous spatial domain model , 1992, IEEE Trans. Image Process..

[5]  Yuan Yan Tang,et al.  Characterization and detection of edges by Lipschitz exponents and MASW wavelet transform , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[6]  Michael W. Marcellin,et al.  Blur identification from vector quantizer encoder distortion , 1998, IEEE Trans. Image Process..

[7]  Yuan Yan Tang,et al.  Characterization of Dirac-structure edges with wavelet transform , 2000, IEEE Trans. Syst. Man Cybern. Part B.

[8]  Yonglin Sun,et al.  Fast wavelet transform for color image compression , 1996, Proceedings of 3rd IEEE International Conference on Image Processing.