18448590. METHOD OF PROCESSING IMAGE BASED ON SUPER-RESOLUTION WITH DEEP LEARNING AND METHOD OF PREDICTING CHARACTERISTIC OF SEMICONDUCTOR DEVICE USING THE SAME simplified abstract (SAMSUNG ELECTRONICS CO., LTD.)
METHOD OF PROCESSING IMAGE BASED ON SUPER-RESOLUTION WITH DEEP LEARNING AND METHOD OF PREDICTING CHARACTERISTIC OF SEMICONDUCTOR DEVICE USING THE SAME
Organization Name
Inventor(s)
METHOD OF PROCESSING IMAGE BASED ON SUPER-RESOLUTION WITH DEEP LEARNING AND METHOD OF PREDICTING CHARACTERISTIC OF SEMICONDUCTOR DEVICE USING THE SAME - A simplified explanation of the abstract
This abstract first appeared for US patent application 18448590 titled 'METHOD OF PROCESSING IMAGE BASED ON SUPER-RESOLUTION WITH DEEP LEARNING AND METHOD OF PREDICTING CHARACTERISTIC OF SEMICONDUCTOR DEVICE USING THE SAME
The abstract describes a method of processing an image using super-resolution techniques, specifically utilizing a Super-Resolution Convolutional Neural Network (SRCNN) to enhance image quality.
- The method involves performing multiple computing operations on a low-resolution input image to generate a residual image.
- An interpolation operation is then applied to the low-resolution input image to create an interpolation image.
- The residual image is added to the interpolation image to produce a high-resolution output image.
- The SRCNN consists of computation layers, including convolutional layers and a deconvolutional layer for post-up-sampling.
- The deconvolutional layer is the final computation layer in the network.
Potential Applications: - Enhancing image quality in photography and video production. - Improving the clarity of medical imaging for diagnostic purposes. - Enhancing satellite imagery for better analysis and monitoring.
Problems Solved: - Addressing the issue of low-resolution images lacking detail and clarity. - Providing a solution for upscaling images without losing quality.
Benefits: - Improved image quality for various applications. - Enhanced visual experience for users viewing the images. - Increased accuracy in image analysis and interpretation.
Commercial Applications: "Super-Resolution Image Processing Technology for Enhanced Visual Quality in Various Industries"
Prior Art: Research on super-resolution techniques in image processing and computer vision.
Frequently Updated Research: Ongoing advancements in deep learning and neural network technologies for image enhancement and super-resolution techniques.
Questions about Super-Resolution Image Processing Technology: 1. How does the SRCNN differ from traditional image upscaling methods? 2. What are the potential limitations of using super-resolution techniques in image processing?
Original Abstract Submitted
A method of processing an image based on super-resolution includes: sequentially performing a plurality of computing operations on a low-resolution input image using a super-resolution convolutional neural network (SRCNN) to generate a residual image, performing an interpolation operation on the low-resolution input image to generate an interpolation image and adding the residual image to the interpolation image to generate a high-resolution image. The high-resolution output image has a resolution higher than that of the low-resolution input image. The SRCNN includes a plurality of computation layers for performing the plurality of computing operations. The plurality of computation layers include a plurality of convolutional layers, and a deconvolutional layer for post-up-sampling. The deconvolutional layer is a last computation layer among the plurality of computation layers.
