Image coloring method based on multi-residual network and regularization transfer learning

An image coloring and transfer learning technology, which is applied in the field of image coloring, can solve the problems of poor coloring effect of some scenes in the image and low accuracy of semantic feature extraction network, so as to reduce semantic confusion, reduce the phenomenon of low detail restoration, and improve The effect of precision

Active Publication Date: 2020-02-14
EAST CHINA UNIV OF TECH
View PDF8 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing image coloring method based on deep learning has the problem that the coloring effect of some scenes in the image is not good.
Most of these methods will use semantic features to guide the image model when coloring, and there will be a problem of low accuracy of semantic feature extraction network

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
  • Image coloring method based on multi-residual network and regularization transfer learning
  • Image coloring method based on multi-residual network and regularization transfer learning
  • Image coloring method based on multi-residual network and regularization transfer learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047]The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0048] The purpose of the present invention is to provide an image coloring method based on multiple residual networks and regularization transfer learning, so as to improve the accuracy of image coloring and the stability of the network.

[0049] In order to make the above objects, features and advantages of the present invention more comprehensible, the present invention will be further described in detail below in conjunction with the accompanying drawings an...

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 an image coloring method based on a multi-residual network and regularization transfer learning. The image coloring method comprises the steps that a gray level image data setis manufactured; extracting image features by using an image feature extraction module constructed based on a multi-residual network; training an image semantic feature extraction module based on a regularization transfer learning framework, and extracting image semantic features by utilizing the image semantic feature extraction module; inputting the image features and the image semantic featuresinto an image fusion module for fusion to obtain fusion features of the grayscale image; and inputting the fusion features of the grayscale image into an image coloring module constructed based on amulti-residual network for coloring to obtain a new color image. According to the invention, the image feature extraction module and the image coloring module are constructed based on the multi-residual network, so that the network performance is improved; an image semantic feature extraction module is trained based on a regularization transfer learning framework, image semantic features are extracted, and the accuracy of semantic feature extraction and the accuracy of image coloring are improved.

Description

technical field [0001] The invention relates to the technical field of image coloring, in particular to an image coloring method based on multiple residual networks and regularized transfer learning. Background technique [0002] The research and application of coloring technology has been carried out as early as the 1980s. From the beginning, people painted their favorite colors on black and white images by hand, to the earliest black and white film evolved into color images, images Coloring technology is becoming more and more mature and widely used. For example, in remote sensing and satellite fields, coloring technology plays a very important role; in the medical field, image coloring is also widely used in X-ray, CT, MR and other medical image processing. [0003] In recent years, deep learning methods have been introduced into the field of image coloring, which has greatly improved data-driven image coloring algorithms, and gradually formed a series of image coloring ...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06T11/40
CPCG06T11/40G06T2207/20081G06T2207/10024G06T2207/20221G06T2207/20084
Inventor 徐洪珍章权周梁琦付亮
Owner EAST CHINA UNIV OF TECH
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