Synaptics has patented a method for denoising low-light images using neural networks. The technology involves scaling brightness levels of input images to match ground truth images, training a neural network, and inferring denoised images. This innovation aims to improve image quality in low-light conditions. GlobalData’s report on Synaptics gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Access deeper industry intelligence
Experience unmatched clarity with a single platform that combines unique data, AI, and human expertise.
According to GlobalData’s company profile on Synaptics, Wearable computers was a key innovation area identified from patents. Synaptics's grant share as of April 2024 was 64%. Grant share is based on the ratio of number of grants to total number of patents.
Method for denoising images using neural network-based brightness scaling
A recently granted patent (Publication Number: US11967042B2) discloses a method for denoising images using a neural network. The method involves receiving pixel values representing an input image and a ground truth image with different brightness levels and noise amounts. By determining scaling factors and performing scaling operations on the pixel values, a neural network is trained to reproduce the ground truth image, resulting in a denoised image. The method also includes adjusting for color filter array values, black levels, and brightness levels to enhance the denoising process effectively.
Furthermore, the patent extends to an image processor that implements the denoising method by receiving pixel values, determining scaling factors, and training a neural network to reproduce the ground truth image. The processor also accounts for black levels, brightness levels, and color filter array values to optimize the denoising process. Additionally, a method for training neural networks is detailed, emphasizing the importance of scaling factors, black levels, and brightness levels in enhancing the training process for improved denoising results. Overall, the patent provides a comprehensive approach to denoising images using neural networks, offering a systematic and efficient method for enhancing image quality through noise reduction.
To know more about GlobalData’s detailed insights on Synaptics, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
