Data enhancement method and device for micro defect detection rate

A technology of defect detection rate and data, which is applied in the field of image processing, can solve the problems of increasing calculation overhead and unbalanced size objects, so as to increase diversity, improve the detection rate of small defects, and keep the same size and pixel density sexual effect

Inactive Publication Date: 2020-10-30
CHANGZHOU MICROINTELLIGENCE CO LTD
View PDF2 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this approach of using higher resolutions adds computational overhead and does not address the imbalance between large and small objects

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 device for micro defect detection rate
  • Data enhancement method and device for micro defect detection rate

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. 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.

[0020] figure 1 It is a flow chart of the data enhancement method for the detection rate of small defects according to the embodiment of the present invention.

[0021] Such as figure 1 As shown, the data enhancement method for the detection rate of small defects in the embodiment of the present invention may include the following steps:

[0022] S1, acquire product images.

[0023] In one embodiment of the present invention, obtaining the product image inc...

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 data enhancement method and device for a micro defect detection rate. The method comprises the following steps: acquiring a product image; preprocessing the product image to obtain a product image meeting a preset condition; acquiring defect type information of the processed product image; analyzing the defect type information of the product image to obtain the type information of the target defect; copying the target defect, and pasting the target defect at any position in the product image to complete data enhancement of the product image. The invention discloses a data enhancement method. The number of samples is increased by copying and pasting defect targets, the diversity of the samples randomly appearing in the images is increased on the premise that the authenticity of the samples is increased, the consistency of the sizes and the pixel density of the training images and the test images is reserved, and the detection rate of tiny defects of the mobile phone backboard is effectively increased.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a data enhancement method for detection rate of micro-defects, a data enhancement device for detection rate of micro-defects, a computer device and a non-transitory computer-readable storage medium. Background technique [0002] At present, industrial defect detection generally has the problem of few defect samples and a small proportion of defective pixels. In order to solve the above-mentioned difficulties that have existed in the industrial field for a long time, related technologies have proposed to increase the resolution of the input image or combine high-resolution features with low-resolution features. A technical solution for high-dimensional feature fusion in high-rate images. However, this approach of using higher resolutions increases computational overhead and does not address the imbalance between large and small objects. Contents of the invention...

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): G06T7/00G06K9/46G06K9/62
CPCG06T7/0004G06V10/44G06F18/214
Inventor 陈红星马元巍李建清顾徐波
Owner CHANGZHOU MICROINTELLIGENCE 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