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

Data enhancement method and system for solving problem of sample imbalance

A sample data and enhancement system technology, applied in image enhancement, image data processing, instruments, etc., can solve the problems of increasing dirty data, model logic confusion, and reducing the accuracy of defect detection, so as to enhance training sample data and ensure accuracy Effect

Inactive Publication Date: 2020-04-10
CHENGDU UNION BIG DATA TECH CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The invention provides a data enhancement method for solving the problem of unbalanced samples, which solves the problem that when using the existing data enhancement method for automatic panel defect detection, a lot of dirty data will be added, the model logic will be confused, and the accuracy of defect detection will be greatly reduced. technical issues

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
  • Data enhancement method and system for solving problem of sample imbalance
  • Data enhancement method and system for solving problem of sample imbalance

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] In order to understand the above-mentioned purpose, features and advantages of the present invention more clearly, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, under the condition of not conflicting with each other, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0041] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from the scope of this description. Therefore, the protection scope of the present invention is not limited by the following disclosure. limitations of specific examples.

[0042] Please refer to figure 1 , an embodiment of the present invention provides a data enhancement method for solving the sample imbalance problem, the method...

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 discloses a data enhancement method and system for solving the problem of sample imbalance, and the method is used for panel defect detection. The method comprises the steps: capturing and collecting a plurality of original canvas images of a panel through an industrial camera; cutting the original canvas images to obtain cut canvas images; and obtaining sample data after data enhancement processing based on the plurality of cut canvas images. According to the invention, the sample imbalance phenomenon of the panel automatic defect detection application scene, the industrial camera shooting characteristics and various defect characteristics are comprehensively considered in the defect judgment process, and the data enhancement method and system applied to panel defect detection are proposed; data enhancement is carried out through edge random clipping and fixed angle rotation, training sample data of a panel can be enhanced, dirty data cannot be increased, and the accuracy of panel defect detection is guaranteed.

Description

technical field [0001] The invention relates to the technical fields of intelligent manufacturing and artificial intelligence, in particular to a data enhancement method and system for solving the problem of sample imbalance. Background technique [0002] Due to the influence of factors such as the production environment, the existing panel defect detection is generally restricted by the extreme imbalance in the number of samples of each defect category. The model trained by samples with unbalanced distribution has serious data bias, which will greatly affect the accuracy of defect detection. [0003] Commonly used data enhancement methods include geometric space transformation, pixel color transformation and multi-sample synthesis transformation. Using the above data enhancement methods in automatic panel defect detection will add a lot of dirty data to the training samples, which will cause serious model logic confusion and greatly reduce Accuracy of defect detection. 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 Applications(China)
IPC IPC(8): G06T5/00G06T7/00G06T3/60
CPCG06T5/00G06T7/0004G06T3/60G06T2207/10004G06T2207/20132G06T2207/30164
Inventor 不公告发明人
Owner CHENGDU UNION BIG DATA TECH CO LTD
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