Convolutional Neural Network with Median Layers for Denoising Salt-and-Pepper Contaminations

2019/08/18 by Luming Liang, Liang, Luming, Sen Deng +9
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #Digital Media Forensic Detection #FOS: Computer and information sciences #Image Enhancement Techniques #Image and Signal Denoising Methods

paper · pdf · doi:10.48550/arxiv.1908.06452

openalex publication_date 2019/08/18 · openalex created_date 2019/08/22 · openalex updated_date 2026/07/28

Abstract

We propose a deep fully convolutional neural network with a new type of layer, named median layer, to restore images contaminated by the salt-and-pepper (s&p) noise. A median layer simply performs median filtering on all feature channels. By adding this kind of layer into some widely used fully convolutional deep neural networks, we develop an end-to-end network that removes the extremely high-level s&p noise without performing any non-trivial preprocessing tasks, which is different from all the existing literature in s&p noise removal. Experiments show that inserting median layers into a simple fully-convolutional network with the L2 loss significantly boosts the signal-to-noise ratio. Quantitative comparisons testify that our network outperforms the state-of-the-art methods with a limited amount of training data. The source code has been released for public evaluation and use (https://github.com/llmpass/medianDenoise).

Citations

• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising

Related

• A Convolutional Neural Networks Denoising Approach for Salt and Pepper Noise
• A Two-stage Method for Non-extreme Value Salt-and-Pepper Noise Removal
• Residual Transformer Fusion Network for Salt and Pepper Image Denoising
• Image Denoising for Strong Gaussian Noises With Specialized CNNs for Different Frequency Components
• Salt-and-Pepper Noise Removal Based on Sparse Signal Processing