A no-reference blur image quality measure based on wavelet transform

In this paper, a no reference blur image quality metric based on wavelet transform is presented. As blur affects specially edges and image fine details, most blur estimation algorithms, are based primarily on an adequate edge detection methods. Here we propose a new approach by analyzing edges through a multi-resolution decomposition. The ability of wavelets to extract the high frequency component of an image has made them useful for edge analysis through different resolutions. Moreover, the multi-resolution analysis is performed on reduced images size, and this could lead to an execution time improvement. In addition, the edges persistence through resolutions may be involved in accuracy blur quality measure estimation. To prove the validity of the proposed method, blurred images from LIVE data base have been considered. Results show that the proposed method provides an accurate quality measure.