Multi-attribute editing method, system and device for high-resolution face image

A face image, high-resolution technology, applied in image coding, image enhancement, image analysis and other directions, can solve the problem of inability to achieve high-resolution multi-attribute face image editing, and achieve high-resolution image editing and scalability. Controlled multi-attribute editing, accurate and controllable multi-attribute editing, the effect of improving the quality and accuracy of editing

Active Publication Date: 2021-11-26
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the above-mentioned problems in the prior art, that is, the problem that the prior art cannot realize high-resolution, controllable multi-attribute face image editing, the present invention provides a multi-attribute editing method for high-resolution face images, The multi-attribute editing method of the face image comprises:

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
  • Multi-attribute editing method, system and device for high-resolution face image
  • Multi-attribute editing method, system and device for high-resolution face image
  • Multi-attribute editing method, system and device for high-resolution face image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The following detailed description will be further described below with reference to the accompanying drawings and examples. It will be appreciated that the specific embodiments described herein are only relevant for explaining the invention, not limitation of the invention. It will also be noted that only portions associated with the relevant invention are shown in the drawings for ease of description.

[0047] It should be noted that the features of the present application and the features in the embodiments in the present application can be combined with each other in the case of an unable conflict. The present application will be described in detail below with reference to the accompanying drawings.

[0048] The present invention provides a high-resolution multi-attribute face image editing method, the method introduced in the image generation wavelet transform, wavelet decomposition acquiring high and low frequency wavelet coefficients, which can recover the global and...

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 fields of pattern recognition, computer vision and digital image processing, and specifically relates to a multi-attribute editing method, system and device for high-resolution face images, aiming to solve the problem that the prior art cannot realize high-resolution and controllable The problem of multi-attribute face image editing. The present invention includes: obtaining the feature expression of the input image through the encoder of the multi-attribute editing network; adjusting the tags to be edited in the original tag set to preset target tags; and expanding the adjusted tag set to image feature space resolution After the size is combined with the image feature expression; based on the combined feature expression, the attribute-edited image corresponding to the input image is obtained through the decoder of the multi-attribute editing network. The present invention uses wavelet transform to obtain high-frequency and low-frequency information of images, and combines the strategy of weighted and constrained attribute categories and reconstruction learning based on attribute mapping, so that high-resolution face images can be edited, and at the same time, controllable multi-attribute face image editing can be realized .

Description

Technical field [0001] The present invention belongs to the field of pattern recognition, computer vision and digital image processing, and specific to a multi-attribute editing method, system and device for high-resolution human face images. Background technique [0002] The ideal face attribute editing refers to a given property tab to change one or more attributes in a face image while maintaining the remaining properties and background. Common attribute editing has changed color, remove beard and age, and so on. [0003] Face Properties Editing gradually became a focus of research in computer visual directions due to its wide application in the fields of leisure entertainment, information security and face recognition. Face recognition technology has been deployed in a large scale of airport security, access control attendance, and public security criminal investigation, but there is still certain limitations for large human face age changes and large-scale face blindness. Fa...

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 Patents(China)
IPC IPC(8): G06T11/60G06K9/00G06T9/00G06K9/62
CPCG06T11/60G06T9/002G06T2207/20064G06V40/168G06F18/2431
Inventor 孙哲南李琦邓琪瑶
Owner INST OF AUTOMATION CHINESE ACAD OF SCI
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