Low-resolution face image super-resolution reconstruction method based on three-dimensional face model

A technology of super-resolution reconstruction and face image, which is applied in the field of super-resolution reconstruction of low-resolution face images based on 3D face models, can solve problems such as face angle inclination, reduce the amount of computation, and overcome the face angle Problems and solve the unsatisfactory effect of reconstructing the face model

Pending Publication Date: 2020-01-31
智慧视通(杭州)科技发展有限公司
View PDF9 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a method for super-resolution reconstruction of a low-resolution face image based on a three-dimensional face model, which overcomes the problem of face angle inclination in normal surveillance videos

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
  • Low-resolution face image super-resolution reconstruction method based on three-dimensional face model
  • Low-resolution face image super-resolution reconstruction method based on three-dimensional face model
  • Low-resolution face image super-resolution reconstruction method based on three-dimensional face model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The following describes the technical solutions in the embodiments of the present invention clearly and completely. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

[0045] See figure 1 The present invention provides a low-resolution face image super-resolution reconstruction method based on a three-dimensional face model, which is characterized in that it includes the following steps:

[0046] S1, locate the feature points of the low-resolution face image;

[0047] Using the facial feature point positioning method, for the low-resolution face image LRFace captured in the video or in the ordinary image, locate the key parts of the face, from the eyebrows to the chin, and the rectangular area...

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 low-resolution face image super-resolution reconstruction method based on a three-dimensional face model, and relates to the technical field of image and video processing. The low-resolution face image super-resolution reconstruction method comprises the following steps: positioning feature points of a low-resolution face image; straightening the low-resolution face image: checking a reconstruction area of the straightened low-resolution face image; performing super-resolution reconstruction, wherein the super-resolution reconstruction further comprises the followingsteps: partitioning a reconstruction region; performing fuzzy processing on the high-resolution face image in the database to obtain a fuzzy face image; performing the same blocking operation on the high-resolution face image and the blurred face image; solving the weight of each blurred face image block at the same position; performing weighted summation according to the weight and the corresponding high-resolution face image block to obtain a reconstructed block; and splicing the reconstructed blocks according to the position relationship. According to the low-resolution face image super-resolution reconstruction method, the problem of face angle inclination in a normal monitoring video is overcome.

Description

Technical field [0001] The invention relates to the technical field of image and video processing, in particular to a low-resolution face image super-resolution reconstruction method based on a three-dimensional face model. Background technique [0002] The video surveillance system has been developed in just over 20 years. From analog surveillance to fiery digital surveillance to the ascendant network video surveillance, earth-shaking changes have taken place. Video surveillance plays an increasingly important role in daily work and life, especially in the field of public security systems and criminal investigations. Through the monitoring system, the status of the scene can be seen in the control center in real time, especially the behavior of people and vehicles in the surveillance video; however, affected by many factors such as imaging equipment, shooting distance, environmental interference, etc., the corresponding people in the video surveillance Because of the quality pr...

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): G06T3/40G06T17/00G06T15/20
CPCG06T3/4053G06T17/00G06T15/205
Inventor 满庆奎徐晓刚
Owner 智慧视通(杭州)科技发展有限公司
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