No-reference blurred image quality assessment

In the aim to reduce blur in images, one could perform a No-Reference image quality assessment to control blur reduction. In this paper, a novel No-Reference blur image quality metric is proposed. This approach is based on a new Multiplicative Multiresolution Decomposition MMD. The blur is analyzed through MMD scales and a blur metric is deduced. We have also shown that the highlighted transform can be used to reduce blur. Some tests have been conducted on LIVE database images. The experimental results show that the proposed assessment method gives high correlation with subjective ratings.