A single image enhancement method based on full convolution neural network

A convolutional neural network, single-image technology, applied in the field of single-image enhancement based on full convolutional neural network, can solve the problem of unable to recover the details of the low dark area of ​​the image and so on

Active Publication Date: 2019-03-08
NINGBO UNIV
View PDF5 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method can improve the overall brightness of the image and restore the details of the saturated area, but considering the noise in the low and dark areas of the image, this method cannot restore the details of the low and

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
  • A single image enhancement method based on full convolution neural network
  • A single image enhancement method based on full convolution neural network
  • A single image enhancement method based on full convolution neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.

[0046] Due to the limitation of the dynamic range of the camera sensor, there is a phenomenon of information loss in the single-exposure image. For this, the present invention proposes a single-image enhancement method based on a fully convolutional neural network. Therefore, the single-exposure image is used to generate a low / high-exposure image different from its exposure to restore the lost information; and then the neural network is used to extract the fusion features of the multi-exposure sequence to reconstruct the final enhanced image.

[0047] The overall realization flow chart of the inventive method is as figure 1 Shown, the inventive method comprises the following steps:

[0048] Step 1: Construct two cascaded networks, the first network is the prediction exposure network, and the second network is the exposure fusion network;

[...

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 discloses a single image enhancement method based on a full convolution neural network. Firstly by considering that the lost information of a single exposure image can be described by amulti-exposure sequence, a low-exposure image and a high-exposure image different from the input image exposure are generated by using the constructed predictive exposure network, so as to construct amulti-exposure sequence. Secondly, in order to avoid the problem of low robustness caused by manual feature extraction, the exposure fusion network is used to complete feature extraction, feature fusion and image reconstruction. Finally, by considering that the deconvolution layer in the predictive exposure network will cause the chessboard artifacts, the structure anisotropy loss related to human perception is used to train the predictive exposure network to alleviate the artifacts. The invention has the advantages that the whole contrast of the image can be improved, and certain informationof the underexposed and over-exposed regions of the image can be recovered.

Description

technical field [0001] The invention relates to a single image enhancement technology, in particular to a single image enhancement method based on a fully convolutional neural network. Background technique [0002] Due to the limitation of the dynamic range of the camera sensor, the details of the single-exposure image are lost. In order to improve the image quality, multi-image fusion technology is often used. However, the multi-image shooting process is to expose the same scene multiple times, and there is a certain time interval. For dynamic scenes, ghost images will be introduced. Therefore, multi-image fusion technology needs to additionally consider the detection and removal of ghost images. The single-image enhancement technology only needs to adjust the tone curve of the single-exposure image and will not introduce ghosting, so it is more practical, but the single-exposure image cannot represent the content of the entire scene, and the quality of the enhanced image w...

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): G06T5/00G06T5/50G06N3/04G06N3/08
CPCG06N3/08G06T5/007G06T5/50G06T2207/20081G06T2207/20084G06T2207/20221G06T2207/20208G06N3/045
Inventor 郁梅陈晔曜邵华姜浩蒋刚毅
Owner NINGBO UNIV
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