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

Method for image processing based on matrix variable variation self-encoder

An image processing and autoencoder technology, applied in the field of computer vision and machine learning, which can solve problems such as destroying the spatial structure

Active Publication Date: 2018-12-04
BEIJING UNIV OF TECH
View PDF3 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide a method for image processing based on a matrix variable variational autoencoder (Matrix-variate Variational Autoencoder, MVVAE), which can solve the problem of image vectorization processing destroying the spatial structure, thereby benefiting the image Refactoring, denoising and completion

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
  • Method for image processing based on matrix variable variation self-encoder
  • Method for image processing based on matrix variable variation self-encoder
  • Method for image processing based on matrix variable variation self-encoder

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0009] The invention provides a method for image processing based on a matrix variable variational autoencoder (Matrix-variate VariationalAutoencoder, MVVAE),

[0010] Suppose there are N independent and identically distributed image sets Each image is represented as That is, the size of the input sample is a two-dimensional matrix of I×J. The present invention aims to model the statistical distribution logp of a set of images θ (X), and then effectively perform image reconstruction, denoising and completion. The image modeling process is based on the MVVAE network proposed by the present invention, so the core is to model the network and train to obtain the parameters of the network model.

[0011] To achieve the above object, the present invention adopts the following technical solutions:

[0012] 1. Definition of MVVAE model for image set distribution modeling

[0013] MVVAE model definition, such as figure 1 as shown,

[0014] in this model Is the input layer ma...

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 method for image processing based on a matrix variable variation self-encoder so that a problem of damaging the spatial structure by image vectorization processing can be solved and thus image reconstruction, denoising and completion can be realized. Different from the traditional VAE, the method has the following advantages: the input, hidden layer features, latent variable distribution parameters of the model are described by using an inherent expression form -2D matrix of the image; with the definition of matrix Gaussian distribution and related properties, an explicit expression of an objective function of a novel model is deduced and then model parameters are calculated by using a stochastic gradient descent algorithm. In the model, modeling of the spatial structure and statistical information of the image data is carried out well because the involved modeling process is oriented at the matrix variable, so that the image reconstruction quality is enhanced, noises are removed, and the image completion is realized.

Description

technical field [0001] The invention belongs to the field of computer vision and machine learning, and in particular relates to an image processing method based on a matrix variable variational autoencoder. Background technique [0002] Image reconstruction, denoising and completion are important contents of image processing. Variational Autoencoder (VAE) is widely used in image processing related fields because it can well model the probability distribution of image data. VAE usually consists of an inference model (encoder) and a generation model (decoder). The objective function of the model includes two items: one is the reconstruction error of the image, which is generally measured by mean square error or cross entropy; the other is The Kullback-Leibler (KL) divergence is used to measure the similarity between the posterior of the feature latent variables learned based on the inference model and the prior distribution of the feature assumptions, which is equivalent to a ...

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): G06T5/00G06T9/00
CPCG06T9/00G06T2207/10004G06T5/77G06T5/70
Inventor 李敬华闫会霞孔德慧王立春尹宝才
Owner BEIJING UNIV OF TECH
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