Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Injection molding product surface image defect identification method based on transfer learning

A technology for injection molding products and transfer learning, applied in image enhancement, image analysis, image data processing, etc., can solve the problems of missing image details, high hardware requirements, overfitting, etc., to solve the dependence of training data, solve Lack of image samples and the effect of improving accuracy

Active Publication Date: 2019-08-09
ZHEJIANG UNIV
View PDF9 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, the methods for identifying surface defects of injection molded products are mainly divided into two categories: one is to perform operations such as noise reduction filtering, edge extraction, and feature matching on images through digital image processing technology, and to identify defects according to the feature description of images. The advantage of this method is that it is convenient to calculate and easy to implement. The disadvantage is that using simple features to describe the image will lose the details of the image, making it difficult for the classification accuracy of defects to reach a high standard; the second is to use a large amount of training data and GPU computing power. , use the method of deep learning to recognize the surface image of injection molded products. The advantage of this method is that it has high classification accuracy and many types of defects that can be processed. The disadvantage is that it requires high hardware and relies heavily on a large amount of data for training. set, otherwise it is easy to cause overfitting phenomenon

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
  • Injection molding product surface image defect identification method based on transfer learning
  • Injection molding product surface image defect identification method based on transfer learning
  • Injection molding product surface image defect identification method based on transfer learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The present invention will be further described below in conjunction with drawings and embodiments.

[0039] Such as figure 1As shown, the CNN (Convolutional Neural Network) model is mainly composed of convolutional layer 1, pooling layer 1, convolutional layer 2, pooling layer 2, convolutional layer 3, convolutional layer 4, convolutional layer 5, pooling Layer 3, convolutional layer 6, pooling layer 4, convolutional layer 7, fully connected layer 1, fully connected layer 2, and fully connected layer 3 are connected in sequence, and samples are input to convolutional layer 1 and extracted by convolutional layer 5 And output the first feature map, the first feature map is used as the input of the pooling layer 3 and the predicted defect classification result corresponding to the sample is output through the fully connected layer 3.

[0040] In the CNN (Convolutional Neural Network) model, the convolutional layer 1 to the convolutional layer 5 are used as the feature ex...

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 an injection molding product surface image defect identification method based on transfer learning. The surface defect image of the non-injection molding product is used as a source domain data set; the surface defect image of the injection molding product is used as a target domain data set; carrying out defect category marking on the source domain data set, carrying out domain information marking on all images, establishing a CNN model, inputting the two data sets into the CNN model for training, obtaining a first feature map of a sample through extraction of a plurality of convolutional layers by the CNN model, and outputting a predicted defect classification result through a full connection layer; establishing a migration learning model, constructing a migrationloss function, migrating the source domain data set as knowledge to the CNN model according to the migration loss function, and performing optimization iteration to obtain a target CNN model; and collecting an injection molding product image with surface defects, and inputting the injection molding product image into the target CNN model for testing to obtain a predicted defect classification result. The method is high in identification accuracy, and solves the problem that samples for identifying the surface defects of the injection molding product are lack.

Description

technical field [0001] The invention relates to the technical fields of computer vision and industrial automation, in particular to a method for identifying surface image defects of injection molded products based on migration learning. Background technique [0002] The surface of injection molded products is affected by many factors such as molds and raw material characteristics, and is closely related to the processing environment, product cooling time, and post-processing technology. It is prone to various defects and seriously affects product quality; its characteristics can reflect the quality of injection molded products. The formation mechanism of surface defects of injection molded products is complex and manifests in various forms, making it difficult to quantify. The identification of surface defects has always been a difficult problem. Since the surface defect detection technology based on machine vision is an intuitive and non-contact quality detection method, it...

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): G06T7/00G06N3/04
CPCG06T7/0004G06T2207/20081G06N3/045
Inventor 伊国栋李琎
Owner ZHEJIANG UNIV
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
Eureka Blog
Learn More
PatSnap group products