# Weighted Fuzzy-Based PSNR for Watermarking

arXiv: https://arxiv.org/abs/2101.08502 · HTML: https://mlsanity.com/paper/2101.08502/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 18 references that are in the map.
- First posted on arXiv 21 Jan 2021.

## Builds on (most cited first, 3 of 3)

- [ReDMark: Framework for Residual Diffusion Watermarking on Deep Networks](https://mlsanity.com/paper/1810.07248/) (2018)
- [Subjective and Objective Quality Assessment of Image: A Survey](https://mlsanity.com/paper/1406.7799/) (2014)
- [No-Reference Image Quality Assessment via Feature Fusion and Multi-Task Learning](https://mlsanity.com/paper/2006.03783/) (2020)

## Built on by (most cited first, 1 of 1)

- [Real-World Deep Local Motion Deblurring](https://mlsanity.com/paper/2204.08179/) (2022)

## Abstract (arXiv)

One of the problems of conventional visual quality evaluation criteria such as PSNR and MSE is the lack of appropriate standards based on the human visual system (HVS). They are calculated based on the difference of the corresponding pixels in the original and manipulated image. Hence, they practically do not provide a correct understanding of the image quality. Watermarking is an image processing application in which the image's visual quality is an essential criterion for its evaluation. Watermarking requires a criterion based on the HVS that provides more accurate values than conventional measures such as PSNR. This paper proposes a weighted fuzzy-based criterion that tries to find essential parts of an image based on the HVS. Then these parts will have larger weights in computing the final value of PSNR. We compare our results against standard PSNR, and our experiments show considerable consequences.