Residual neural network based on hole convolution and two-stage image demosaicing method

A neural network and demosaicing technology, applied in biological neural network model, neural architecture, image data processing and other directions, can solve the problems of reducing the network perception field, reducing the network depth, etc., to improve the modeling ability, optimize the understanding space, The effect of enhancing learning ability and modeling ability

Active Publication Date: 2020-09-22
UNIV OF ELECTRONIC SCI & TECH OF CHINA
View PDF10 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the document "Color Image Demosaicking via Deep Residual Learning", CNN is used to implement image demosaicing, which has achieved a good performance gain compared with traditional methods,

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Residual neural network based on hole convolution and two-stage image demosaicing method
  • Residual neural network based on hole convolution and two-stage image demosaicing method
  • Residual neural network based on hole convolution and two-stage image demosaicing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The present invention will be further described below with reference to the accompanying drawings and in combination with preferred embodiments.

[0046] This embodiment provides a residual neural network based on atrous convolution and a two-stage image demosaicing method, the flow chart of which is shown in Figure 6 shown; includes the following steps:

[0047] Step 1: Build a residual neural network model based on hole convolution;

[0048] The residual neural network G based on dilated convolution is as figure 1 As shown, it includes: 1 shallow feature extraction unit, 3 local residual units and 1 deep feature extraction unit; the 3 local residual units are connected end to end; the input image is transformed into a shallow feature extraction unit through a shallow feature extraction unit. Layer features, shallow features in turn pass through three local residual units to form main features, and main features output residual images through deep feature extraction...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention belongs to the field of digital image processing, and particularly relates to a residual neural network based on hole convolution and a two-stage image demosaicing method. According to the invention, a shallow feature extraction unit, a local residual unit and a deep feature extraction unit are introduced based on a residual neural network; the interaction of the three basic units greatly enhances the learning ability and modeling ability of the target neural network. Accurate mapping from the mosaic image to the RGB color image can be established for the image demosaicing problem, and finally the mosaic image in the Bayer CFA mode can be processed through the established effective mapping to obtain the RGB color image; meanwhile, a two-stage image demosaicing model is introduced, prior information is fully utilized, the modeling capability of the network is improved, and the understanding space is optimized; by means of the image demosaicing method, the peak signal-to-noise ratio of the image can be remarkably increased, the image demosaicing efficiency, quality and robustness are greatly improved, and the image demosaicing method has far-reaching significance in thefield of image processing.

Description

technical field [0001] The invention belongs to the field of digital image processing, in particular to a residual neural network based on hole convolution and a two-stage image demosaic method. Background technique [0002] Single-sensor color imaging technology using CFA is widely used in the current digital camera industry. In a single-sensor camera with CFA, each pixel only records one pixel in the R-channel image, G-channel image, and B-channel image. When restoring an RGB color image, it is necessary to estimate the values ​​of the other two lost pixels; This process is often called image demosaicing, and it plays a vital role in the field of obtaining high-quality RGB color images. The most popular and widely used CFA is BayerCFA. In the BayerCFA model, green pixels are sampled by a quincunx grid, and red and blue pixels are sampled by a rectangular grid, where the number of green sample points is the number of red or blue samples double the number of points. [00...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06T3/40G06K9/46G06N3/04
CPCG06T3/4015G06T3/4046G06V10/454G06N3/048G06N3/045
Inventor 朱树元王岩王忠荣刘光辉曾辽原
Owner UNIV OF ELECTRONIC SCI & TECH OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap