Unlock instant, AI-driven research and patent intelligence for your innovation.

Shape modeling method based on convolutional restricted Boltzmann machine and related devices

A technology of limited Boltzmann machine and modeling method, applied in the field of image processing, which can solve the problems of blurred shape and easy to ignore details.

Active Publication Date: 2017-11-07
SHAANXI NORMAL UNIV
View PDF2 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since the model pulls the input image into a one-dimensional vector as input and ignores the two-dimensional structural information between images, when using this model to sample and generate shapes, it is easy to ignore details and make the sampled shapes blurred

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
  • Shape modeling method based on convolutional restricted Boltzmann machine and related devices
  • Shape modeling method based on convolutional restricted Boltzmann machine and related devices
  • Shape modeling method based on convolutional restricted Boltzmann machine and related devices

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] Embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0038] It should be clear that the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0039] The purpose of the present invention is to propose a method for establishing a shape model for a target in an image, and proposes to establish a shape model through a deep learning method, use the same type of target training model but with different postures, and express the probability distribution of this type of target through the model, In this way, various forms of expression and generation of the target can be realized.

[0040] The modeling method proposed by the present invention is a shape model...

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

Embodiments of the invention disclose a shape modeling method based on a convolutional restricted Boltzmann machine and related devices, and relate to the field of image processing. The method according to the embodiment of the invention includes the steps of adding a convolutional operation on the basis of a restricted Boltzmann machine to obtain a model structure of a convolutional restricted Boltzmann machine; based on the convolutional restricted Boltzmann machine, obtaining a mathematical expression of the model of the convolutional restricted Boltzmann machine and a training mode of the model; and determining the structure of the model used in an experiment, training the model with a training set, and carrying out the experiment of modeling the shape by using the model. In addition, the embodiments of the invention also disclose a shape modeling device based on the convolutional restricted Boltzmann machine and an electronic device. Through the schemes of the embodiments of the invention, multiple morphological expressions of the target can be achieved.

Description

technical field [0001] The invention relates to the field of image processing, in particular to the modeling of similar but different target shapes by using a convolutional restricted Boltzmann machine. Background technique [0002] Model the target shape in the image, and the obtained shape can completely express the outline of the target, laying the foundation for subsequent tasks such as image segmentation, classification, and target detection. For example, when the shape is applied to the field of image segmentation, since the shape can express the outline of the target, after the shape is aligned with the target, the target can be well separated from the background and the ideal segmentation result can be achieved. [0003] The Restricted Boltzmann Machine (RBM) was proposed by Smolensky. It is a generative model that contains two layers of structure, namely the visible layer and the hidden layer. The nodes between the two layers are fully connected, and the nodes of th...

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): G06T7/194
CPCG06T7/194G06T2207/20081
Inventor 汪西莉陈粉刘侍刚洪灵刘明
Owner SHAANXI NORMAL UNIV