18612094. IMAGE DENOISING METHOD simplified abstract (Samsung Electronics Co., Ltd.)
Contents
IMAGE DENOISING METHOD
Organization Name
Inventor(s)
IMAGE DENOISING METHOD - A simplified explanation of the abstract
This abstract first appeared for US patent application 18612094 titled 'IMAGE DENOISING METHOD
- Simplified Explanation:**
The patent application describes a method for denoising images using deep learning technology.
- Key Features and Innovation:**
- Extracting a noise patch from a noisy image.
- Estimating noise parameters using a neural network.
- Generating virtual noise based on the estimated parameters.
- Training a deep learning model to denoise images.
- Outputting a denoised image by removing noise using the trained model.
- Potential Applications:**
This technology can be used in various fields such as medical imaging, surveillance, photography, and video processing.
- Problems Solved:**
The method addresses the challenge of removing noise from images effectively and efficiently.
- Benefits:**
- Improved image quality.
- Enhanced visual clarity.
- Automation of the denoising process.
- Commercial Applications:**
The technology can be applied in industries such as healthcare, security, media, and entertainment for enhancing image quality and reducing noise.
- Prior Art:**
Researchers can explore prior art related to image denoising methods using deep learning models to understand the evolution of this technology.
- Frequently Updated Research:**
Stay updated on advancements in deep learning algorithms for image denoising to leverage the latest innovations in this field.
- Questions about Image Denoising:**
1. How does this method compare to traditional image denoising techniques? 2. What are the potential limitations of using deep learning for image denoising?
Original Abstract Submitted
There is provided an image denoising method including extracting a noise patch from a noisy image, outputting a noise parameter by inputting the noise patch to a noise parameter estimation network (NPE-net), generating imitated virtual noise based on the output noise parameter, generating a noisier image by adding the imitated virtual noise to the noisy image, training a denoise deep learning model by inputting the noisy image and the noisier image as a pair to the denoise deep learning model, inputting the noisy image to the trained denoise deep learning model, and outputting a denoise image obtained by removing noise from the noisy image by the trained denoise deep learning model.
