Gray level image colorization method based on generative adversarial network
A grayscale image and colorization technology, which is applied in the field of deep learning and image generation, can solve the problems of poor flexibility and long time consumption, and achieve the effect of shortening the training time, enriching the color of the image, and reducing the work of fine coloring
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0019] In order to make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the invention will be clearly described and fully described below. Example.
[0020] The present invention provides a technical solution: based on the gray image of the network against the network, including the following steps:
A. Select the quantitative color picture set of the COCO image data set to perform coloring processing and make a training set;
B. Construct a confrontation network architecture, including the generator model and the discriminator model, which completes pre -training in the generator model;
C. Enter the training set obtained by step A in order to generate model training in the network architecture, adjust the parameters, and achieve convergence;
D. Prepare the image to be processed, and the input step C obtains the confrontation model can automatically color the gray image.
[0021]...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com