DCNN (Deep Convolutional Neural Network) based 3D shape classification method

A convolutional neural network and neural network technology, applied in the field of three-dimensional shape classification based on deep convolutional neural network, can solve the problems of small three-dimensional shape data set and time-consuming images.

Inactive Publication Date: 2017-06-20
SHENZHEN WEITESHI TECH
View PDF0 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problem that the 3D shape data set is too small and the existing classification model takes time to process images, the purpose of the present invention is to provide a 3D shape classification method based on deep convolutional 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
  • DCNN (Deep Convolutional Neural Network) based 3D shape classification method
  • DCNN (Deep Convolutional Neural Network) based 3D shape classification method
  • DCNN (Deep Convolutional Neural Network) based 3D shape classification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present invention will be further described in detail below in conjunction with the drawings and specific embodiments.

[0033] figure 1 It is a system flowchart of a three-dimensional shape classification method based on a deep convolutional neural network in the present invention. It mainly includes data input; initial convolutional neural network; beam search; knowledge transfer.

[0034] Wherein, the data input uses a three-dimensional entity set as a data set, which includes 40 various types of physical object classes, such as chairs, tables, toilets, sofas, etc.; each class has 100 unique CAD models, representing The most common 3D shapes, there are a total of 151,128 voxelized models in the entire dataset.

[0035] Wherein, the initial convolutional neural network is a relatively simple initial ...

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 DCNN based 3D shape classification method. The method mainly comprises data input, initialization of convolutional neural network, clustering searching and knowledge migration. The convolutional neural network is used, a relatively simple structure of the convolutional neural network serves as a root node of a searching tree, and a cluster searching method is used to explore a candidate more-complex model from the root node; and when a new candidate convolutional neural network is generated, a mother convolutional neural network transmits a proper parameter value to a later generation, a cluster searching result is valid, and an optimal convolutional neural network is obtained finally. Compared with the prior art, performance of a popular 3D shape data set is higher, and the total number of parameters is reduced by about 98%; and knowledge migration is carried out after the cluster searching method, and the method of the invention is can be easily applied to deep robustness learning and the like needed in a mini training data set.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a three-dimensional shape classification method based on a deep convolutional neural network. Background technique [0002] With the rapid development of technology, convolutional neural networks have been widely used to classify 3D shapes. Predicting the object class given a 3D shape is a fundamental problem in computer vision because 3D shape is an important visual cue for image understanding. However, currently available 3D shape datasets are an order of magnitude smaller than other commonly used datasets and are not sufficient for training models. Even with a lot of fine-tuning on this small dataset, it takes a very long time. However, if the 3D shape classification method based on the deep convolutional neural network is adopted, the optimal convolutional neural network architecture and parameters can be obtained through beam search, so as to better predict the 3D shape. At...

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): G06K9/62G06N3/04
CPCG06N3/04G06F18/241
Inventor 夏春秋
Owner SHENZHEN WEITESHI TECH
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap