Training method and device suitable for industrial part recognition model and storage medium

A technology for identifying models and training methods, applied in the field of model training, which can solve problems such as poor recognition accuracy, poor model applicability, and finding industrial parts

Active Publication Date: 2021-06-08
HANGZHOU YOUGONGPIN TECH CO LTD
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, after the database is formed, the applicability of the model for parts identification and query based on the database is poor, and the corresponding industrial parts and their corresponding information cannot be found in the database, and the recognition accuracy is poor.

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
  • Training method and device suitable for industrial part recognition model and storage medium
  • Training method and device suitable for industrial part recognition model and storage medium
  • Training method and device suitable for industrial part recognition model and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is only some embodiments of the present invention, but not all embodiments. 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.

[0042] The terms "first", "second", "third", "fourth", etc. (if any) in the description and claims of the present invention and the above drawings are used to distinguish similar objects and not necessarily Describe a specific order or sequence. It is to be understood that the data so used are interchangeable under appropriate circumstances ...

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 training method and device suitable for an industrial part recognition model and a storage medium. The training method comprises the steps that a preset industrial part three-dimensional image in an industrial part database is acquired; performing two-dimensional processing on the three-dimensional image of the preset industrial part to generate a plurality of two-dimensional images of the preset industrial part, wherein each two-dimensional image of the preset industrial part is an image of the same industrial part at different angles; and training the industrial part recognition model by taking the preset industrial part two-dimensional images of all the same industrial part at different angles as training samples. Obtaining a customized industrial part three-dimensional image customized by a user at the current moment; performing two-dimensional processing on the three-dimensional image of the customized industrial part to generate a plurality of two-dimensional images of the customized industrial part, wherein each two-dimensional image of the customized industrial part is an image of the same industrial part at different angles; and training the industrial part recognition model again by taking the customized industrial part two-dimensional images of all the same industrial part at different angles as training samples.

Description

technical field [0001] The invention relates to model training technology, in particular to a training method, device and storage medium suitable for industrial component recognition models. Background technique [0002] Industrial components are a very important pillar industry in my country's national economy, with an output value of over one trillion yuan. Among them, fasteners (commonly known as screws) are the most widely used and involve industries, ranging from mobile phones to airplanes. Fasteners are required for connection. As an industrial basic supporting industry, fasteners are also dubbed the title of "industrial rice". Each country, region and industry has its own standards for fastener products (standard content includes information such as technology, performance, application, drawings, etc.), my country is a big industrial manufacturing country, which gathers global fastener product data. There are more than 8,000 fastener standards in the world, and the comm...

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): G06K9/00G06K9/62G06Q50/04G06T3/00
CPCG06T3/0037G06Q50/04G06V20/64G06F18/214Y02P90/30
Inventor 林振峰
Owner HANGZHOU YOUGONGPIN TECH CO LTD
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