A SURVEY ON EFFICIENT NO-REFERENCE BLUR ESTIMATION METHODS

Abstract

Blur estimation in image processing has come to be of great importance in assessing the quality of ima ges. This work presents a survey of no-reference blur estimation methods. A n o-reference method is particularly useful, when the input image used for blur estimation does not have an available corresponding reference image. This paper provides a comparison of the methodologies of four no-reference blur estimation methods. The first met hod applies a scale adaptive technique of blur esti mation to get better accuracy in the results. The second blur metric involves findin g the energy using second order derivatives of an i mage using derivative pair of quadrature filters. The third blur metric is based on the kurtosis measurement in the discrete dyadic wavelet transform (DDWT) of the images. The fourth method of blur estimation is obt ained by finding the ratio of sum of the edge width s of all the detected edges to the total number of edges. The results provided are use ful in comparing the methods based on metrics like Spearman correlation coefficient. The results are obtained by evaluation on images from the Laboratory for Image and Video Engineering (LIVE) database. The various methods are evaluated on the images by adding varying content of noise. The performance is evaluated for 3 different categories namely Gaussian blur, motion blur and al so JPEG2000 compressed images. Blur estimation fin ds its application in quality assessment, image fusion and auto-focusing in image s. The sharpness of an image can also be found from the blur metric as sharpness is inversely proportional to blur. Sharpness metric s can also be combined with other metrics to measur e overall quality of the image.