Adaptive optimal multi-features learning based representation for face hallucination

作者：

Highlights：

• Multiple image features are obtained for an input image and the LR training samples.

• The optimal proportion of each image feature is obtained through the GWO.

• The representation of the LR image features is done by the nearest training features.

摘要

•Multiple image features are obtained for an input image and the LR training samples.•The optimal proportion of each image feature is obtained through the GWO.•The representation of the LR image features is done by the nearest training features.

论文关键词：Face hallucination,Multiple-image-features,GWO,Optimization,Gaussian noise,Thresholding

论文评审过程：Received 6 May 2021, Revised 15 August 2021, Accepted 20 October 2021, Available online 6 November 2021, Version of Record 10 November 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.116141