An ensemble image quality assessment algorithm based on deep feature clustering

作者：

Highlights：

• The proposed framework tailored for image processing can effectively extract features from various images.

• FCM clustering algorithm to ensure the clustering procedure more efficient.

• Moreover, the loss of clustering can be propagated to the encoder part for weights fine-tuning.

摘要

•The proposed framework tailored for image processing can effectively extract features from various images.•FCM clustering algorithm to ensure the clustering procedure more efficient.•Moreover, the loss of clustering can be propagated to the encoder part for weights fine-tuning.

论文关键词：Feature extraction,Clustering,Image quality assessment,PSNR,SIMM,VIF

论文评审过程：Received 25 June 2019, Revised 3 November 2019, Accepted 11 November 2019, Available online 15 November 2019, Version of Record 20 November 2019.

论文官网地址：https://doi.org/10.1016/j.image.2019.115703