A noise-immune no-reference metric for estimating blurriness value of an image

作者：

Highlights：

• We propose a simple yet accurate no-reference blur metric with low computational cost which is robust against noise.

• The proposed blur metric is based on the observation that there is a considerable difference between the DCT of a sharp image and the one associated with its blurred version.

• The experiments, performed on four databases (including CSIQ, TID, IVC, and LIVE), indicate the capability of the proposed metric for measuring the amount of blurriness in images, especially at the presence of noise.

摘要

•We propose a simple yet accurate no-reference blur metric with low computational cost which is robust against noise.•The proposed blur metric is based on the observation that there is a considerable difference between the DCT of a sharp image and the one associated with its blurred version.•The experiments, performed on four databases (including CSIQ, TID, IVC, and LIVE), indicate the capability of the proposed metric for measuring the amount of blurriness in images, especially at the presence of noise.

论文关键词：No-reference metric,Discrete cosine transform,Blur metric

论文评审过程：Received 21 June 2015, Revised 18 June 2016, Accepted 18 June 2016, Available online 23 June 2016, Version of Record 4 July 2016.

论文官网地址：https://doi.org/10.1016/j.image.2016.06.009