Perceptual quality evaluation for image defocus deblurring

作者：

Highlights：

• A defocus deblurred image database (DDID) is constructed and subjective user study is conducted.

• Performances of the popular image deblurring algorithms are evaluated.

• A quality enhancement module is proposed to improve the existing quality models.

摘要

•A defocus deblurred image database (DDID) is constructed and subjective user study is conducted.•Performances of the popular image deblurring algorithms are evaluated.•A quality enhancement module is proposed to improve the existing quality models.

论文关键词：Image quality assessment,No-reference,Defocus deblurring,Texture naturalness,Gray level co-occurrence matrix

论文评审过程：Received 5 April 2016, Revised 27 August 2016, Accepted 18 September 2016, Available online 20 September 2016, Version of Record 28 September 2016.

论文官网地址：https://doi.org/10.1016/j.image.2016.09.005