Portrait relief data set construction method

A construction method and data set technology, applied in the field of portrait relief data set construction, to achieve the effect of a large number of samples, reasonable depth and layering, and a wide range

Pending Publication Date: 2022-03-08
QILU UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical task of the present invention is to address the above deficiencies and provide a method for constructing a portrait relief data set to solve the problem of how to construct a high-quality portrait relief data sample with complete head features

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
  • Portrait relief data set construction method
  • Portrait relief data set construction method
  • Portrait relief data set construction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0065] Portrait relief dataset construction method of the present invention, comprises the following steps:

[0066] S100. Based on the 3D portrait sculpture, obtain a portrait map, a mask map, and a line map, use the mask map and the line map as input, and use the portrait map as an output, construct and train a network model, and the network model is an encoding-decoding structure network model;

[0067] S200. Obtain a portrait image as a reference image;

[0068] S300. For the reference image, perform filtering processing, extract features and accurately locate line drawings, perform bilateral filtering and filter to extract edges, extract hair line drawings, and extract mask images through the MODNet network, merge hair line drawings and feature precise positioning The line drawing obtains the final line drawing, and the mask map and the final line drawing are input into the network model after the training, and the overall portrait method figure is output;

[0069] S400...

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 portrait relief data set construction method, belongs to the technical field of portrait relief models, and aims to solve the technical problem of how to construct a high-quality portrait relief data sample with complete head features. Comprising the following steps: acquiring a portrait method graph, a mask graph and a line graph based on a 3D portrait sculpture, and constructing and training a network model; for a reference image, extracting a line diagram with accurate feature positioning, extracting a hair line diagram, extracting a mask diagram through an MODNet network, combining the hair line diagram and the line diagram with the accurate feature positioning to obtain a final line diagram, inputting the mask diagram and the final line diagram into the trained network model, and outputting an overall portrait method diagram; for the reference image, obtaining a face normal image with fine geometric details through a ResUnet network, and fusing the whole portrait normal image and the face normal image; the texture normal is migrated to the fused overall portrait normal graph; and performing relief depth reconstruction to obtain a portrait relief model.

Description

technical field [0001] The invention relates to the technical field of portrait relief models, in particular to a method for constructing portrait relief data sets. Background technique [0002] Portrait relief is a stylized sculpture art form, which is widely used in seals, commemorative coins, architecture, handicrafts, etc. Traditional hand-carving and software modeling portrait relief require professional skills and are time-consuming and labor-intensive. With the development of artificial intelligence technology, it has become possible to realize the end-to-end modeling of portrait relief from a single image, but the construction of the data set is crucial to realize the supervised training of the deep neural network. At present, there is no portrait relief dataset with sufficient sample size in academia and industry. [0003] Based on the above analysis, how to construct high-quality portrait relief data samples with complete head features is a technical problem that...

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): G06T19/20G06T17/00G06N3/04G06N3/08
CPCG06T19/20G06T17/00G06N3/08G06N3/045
Inventor 张玉伟刘延庆罗萍周浩陈彦钊杨洪广
Owner QILU 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

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