Visual privacy-preserving level evaluation for multilayer compressed sensing model using contrast and salient structural features

作者:

Highlights:

• We propose a MCS model to balance visual privacy-preserving and recognition.

• An improved Gaussian random measurement matrix are adopted in MCS model.

• Our MCS visual evaluation is based on contrast and saliency structural features.

• The proposed method acquires desirable performances on threeconstructed datasets.

摘要

•We propose a MCS model to balance visual privacy-preserving and recognition.•An improved Gaussian random measurement matrix are adopted in MCS model.•Our MCS visual evaluation is based on contrast and saliency structural features.•The proposed method acquires desirable performances on threeconstructed datasets.

论文关键词:Multilayer compressed sensing,Privacy-preserving,Visual privacy-preserving level evaluation,Contrast feature,Salient structural feature

论文评审过程:Received 23 September 2019, Revised 4 September 2020, Accepted 4 September 2020, Available online 6 September 2020, Version of Record 8 September 2020.

论文官网地址:https://doi.org/10.1016/j.image.2020.115996