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

A method and system for training a recognition classification model

A technology of recognition classification and model training, applied in the field of deep learning, can solve the problem of low accuracy, achieve the effect of reducing influence and improving accuracy

Inactive Publication Date: 2019-01-18
GUANGDONG INST OF INTELLIGENT MFG
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Based on this, it is necessary to provide a recognition and classification model training method and system for the above-mentioned problem that the convolutional neural network model used for classification and recognition has low accuracy in recognizing pictures with noise or inconspicuous features

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 method and system for training a recognition classification model
  • A method and system for training a recognition classification model
  • A method and system for training a recognition classification model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

[0031] In one embodiment, such as figure 1 as shown, figure 1 It is a flowchart of a method for training a recognition and classification model in an embodiment, and provides a method for training a recognition and classification model. The method for training a recognition and classification model in this embodiment includes the following steps:

[0032] Step S100: Obtain lossy image sample data according to the damage rate and the initial image sample data.

[0033] The damage rate is used to indicate a certain degree of damage. In this step, the initial image sample d...

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

A method and system for training an identification classification model are disclosed. The method comprises: based on the destruction rate and the initial image sample data, the lossy picture sample data is obtained, a lossy picture sample data is input into a de-noising model for train, the recovered image sample data is input into the recognition classification model for training, the sample label value and recognition loss value are obtained, and the denoising model and recognition classification model are calculated by the reverse conduction algorithm, so that the trained denoising model and the trained recognition classification model are obtained. The denoising model trained by this method can match the recognition model effectively, The recognition and classification model can effectively and accurately identify and classify the lossy data, reduce the impact of noise on recognition and classification in practical application, and improve the accuracy of recognition and classification of pictures with noise or features not obvious.

Description

technical field [0001] The present application relates to the technical field of deep learning, in particular to a training method for a recognition classification model and a training system for a recognition classification model. Background technique [0002] Artificial intelligence is developing rapidly. Among them, the convolutional neural network model is an important model in deep learning. It is mainly used in image processing, and it has remarkable effects in image processing and classification. [0003] Under the traditional technology, the pictures classified during the training process of the convolutional neural network model for classification and recognition are generally lossless and characteristic pictures, and the trained convolutional neural network model is suitable for processing lossless and characteristic pictures. [0004] However, in the actual application environment, due to the interference of the signal or the quality problems of the equipment, the...

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): G06K9/62
CPCG06F18/24G06F18/214
Inventor 徐智浩王达周雪峰苏泽荣鄢武
Owner GUANGDONG INST OF INTELLIGENT MFG
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