Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Face image compression method and device based on deep learning

A face image and deep learning technology, applied in the field of face image compression based on deep learning, can solve the problems of low face image compression efficiency and high compression complexity, reduce redundancy, ensure reconstruction quality, and improve compression. The effect of efficiency

Active Publication Date: 2020-12-08
TSINGHUA UNIV
View PDF10 Cites 1 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 face image compression method and device based on deep learning to alleviate the technical problems of high compression complexity and low face image compression efficiency in the prior art

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
  • Face image compression method and device based on deep learning
  • Face image compression method and device based on deep learning
  • Face image compression method and device based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] According to an embodiment of the present invention, an embodiment of a face image compression method based on deep learning is provided. It should be noted that the steps shown in the flow chart of the accompanying drawings can be implemented in a computer system such as a set of computer-executable instructions and, although a logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in an order different from that shown or described herein.

[0043] figure 1 A flow chart of a face image compression method based on deep learning provided by the embodiment of the present invention, such as figure 1 As shown, the method includes the following steps:

[0044] Step S101, decomposing the test face image into shape components and texture components based on the average face image and the active appearance model;

[0045] In the embodiment of the present invention, the texture component includes the edge and contour of the test f...

Embodiment 2

[0108] According to the method provided in the above-mentioned embodiment 1, it can be seen that the average face image and the active appearance model are used to decompose the face image, and different compression methods are used for the shape component and the texture component, so that the shape component of the face image can be Better reconstruction, compared with the deep learning compression method without face image decomposition, the method provided in this embodiment can obtain a clearer face outline. Such as Figure 6(a) ~ Figure 6(c) As shown, Fig. 6(a) is the original image of a certain face image, and Fig. 6(b) is the face image reconstruction result obtained by using the deep learning method without face image decomposition. It can be seen from the figure that If the average face image and active appearance model are not used to decompose the face image, the shape and outline are not clear, and the recognition of the face is reduced. Fig. 6 (c) is the face im...

Embodiment 3

[0110] According to the method provided in Embodiment 1 above, the embodiment of the present invention uses the average face image and the active appearance model to decompose the texture component of the face image, and compresses it using the convolutional neural network method. When compressing the texture component of the test face image, the texture component includes the edge, contour and facial features including eyes, nose, mouth, etc. of the test face image. According to the importance of different features, different convolutional neural networks can be selected The network compresses the features. Therefore, the implementation process of the embodiment of the present invention may include two paths: the general compression process of texture components and the compression process of facial key features. Specifically, such as Figure 7 as shown, Figure 7 Another face image compression method based on deep learning is provided, which is a method for compressing 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 provides a face image compression method and device based on deep learning, and relates to the technical field of image processing, and the method comprises the steps: decomposing a testface image into a shape component and a texture component based on an average face image and an active appearance model; then, using a quantization entropy encoder for encoding and compressing the shape component to obtain a first compression result; using a trained convolutional neural network encoder for encoding and compressing the texture component to obtain a second compression result; and finally, determining the first compression result and the second compression result as a face image compression result. According to the method, the average face image and the active appearance model are used as priori knowledge, and the trained convolutional neural network encoder is used to encode and compress the texture component, so that the second compression result represented by a low-dimensional feature can be obtained, therefore, the redundancy of the texture component is reduced, and the compression efficiency of the face image is improved.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a face image compression method and device based on deep learning. Background technique [0002] With the development of Internet technology, video-based mobile multimedia data has grown rapidly, exceeding the growth rate of 5G bandwidth, leading to research challenges for ultra-high-definition video services. At present or in the foreseeable future, there will be a certain degree of disconnection in the growth rate of the volume of information generation and the corresponding transmission technology. With the continuous expansion of data scale, the contradiction between it and wireless bandwidth resources has become increasingly prominent. During the global COVID-19 epidemic, remote diagnosis and treatment, remote visitation, remote meetings, and remote office have quietly become the norm, and face images are the main carrier of related businesses. At present, ...

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
IPC IPC(8): G06T9/00G06T7/529G06K9/62G06N3/04G06N3/08
CPCG06T9/002G06T7/529G06N3/08G06T2207/30201G06T2207/30168G06N3/045G06F18/253
Inventor 段一平陶晓明胡舒展刘永嘉张栩铭陆建华
Owner TSINGHUA UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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