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

A 3D Model Classification Method Based on Geometric Shape and LSTM Neural Network

A three-dimensional model and neural network technology, applied in biological neural network models, neural learning methods, neural architectures, etc., can solve problems such as three-dimensional model classification, and achieve high accuracy, good rotation robustness, accurate and efficient classification results Effect

Active Publication Date: 2022-04-26
HARBIN UNIV OF SCI & TECH
View PDF13 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In order to solve the problem of 3D model classification, the present invention discloses a 3D model classification method based on geometric shape and LSTM neural network

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
  • A 3D Model Classification Method Based on Geometric Shape and LSTM Neural Network
  • A 3D Model Classification Method Based on Geometric Shape and LSTM Neural Network
  • A 3D Model Classification Method Based on Geometric Shape and LSTM Neural Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The specific implementation manner of the present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments.

[0047] The flow chart of the three-dimensional model classification method based on geometric shape and LSTM neural network implemented by the present invention, as figure 1 As shown, use figure 2 Three-dimensional model is described, the present invention comprises the following steps:

[0048] Step 1 In order to construct the geometric features of the 3D model, read the data file of the 3D model, discretize the 3D model, and make the surface of the model triangular.

[0049] Step 1-1 reads the 3D model file by using the parsing tool.

[0050] Step 1-2 Use the triangulation tool to triangulate the 3D model, use the file analysis tool to read and triangulate the 3D model sample, and store it in the list file.

[0051] Step 2 Sampling several random points on the surface of the 3D model, selectin...

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 relates to a three-dimensional model classification method based on geometric shapes and LSTM neural network. The present invention extracts the geometric shape feature vectors D1, D2, D3 and A3 of the three-dimensional model, regards these feature vectors as a vector sequence and transmits them to the LSTM neural network as input, and trains the noise reduction autoencoder. The coding part of the denoising self-encoder is the LSTM neural network. The LSTM neural network extracts and aggregates the feature vectors into global features for the identification and classification of 3D models. Use the global features and category labels of the 3D model in the training set to train the weights of the XGBoost classifier. The 3D models in the test set are classified using an optimized LSTM neural network and an XGBoost classifier. The present invention has good effect on three-dimensional model classification.

Description

Technical field: [0001] The invention relates to a three-dimensional model classification method based on geometric shape and LSTM neural network, and the method has better application in three-dimensional model classification. Background technique: [0002] In recent years, with the rapid development of 3D modeling technology, imaging technology and computer vision, the types and quantities of 3D models have experienced explosive growth. How to effectively classify and manage these 3D models has become an urgent problem to be solved. Neural networks have been widely used in many fields such as speech recognition, machine translation, language modeling, character recognition and 3D model classification. There are some deficiencies in the classification of 3D models by traditional neural networks. When the 3D models are numerous and complex, the classification effect is not ideal. Geometry information can accurately reflect the differences between different 3D models and c...

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): G06T17/00G06K9/62G06N3/04G06N3/08G06V10/764G06V10/80G06V10/82
CPCG06T17/00G06N3/049G06N3/08G06T2200/04G06N3/044G06N3/045G06F18/24G06F18/253
Inventor 高雪瑶李正杰张春祥
Owner HARBIN UNIV OF SCI & 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

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