Method, device, storage medium and terminal device for product defect detections and locations

A technology for product defect and position prediction, applied in the computer field, to achieve the effect of improving accuracy and high robustness

Active Publication Date: 2018-06-12
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF8 Cites 31 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Embodiments of the present invention provide a method, device, storage medium and terminal equipment for detecting and locating product defects, so as to solve or alleviate the above technical problems in the prior art

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
  • Method, device, storage medium and terminal device for product defect detections and locations
  • Method, device, storage medium and terminal device for product defect detections and locations
  • Method, device, storage medium and terminal device for product defect detections and locations

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] see figure 1 , the embodiment of the present invention provides a method for detecting and locating product defects, executed by the training engine, including steps S10 to S40, specifically as follows:

[0059] S10. Select the neural network structure of the detection model to be trained according to the image data characteristics of the product to be tested and the complexity of product defects.

[0060] In the embodiment of the present invention, when the surface state of the product to be tested is detected, the product picture collection of the product to be tested can be collected by a camera and other equipment. Due to the influence of the camera equipment, camera technology and camera environment, the picture data features of the pictures exist. For example, when the picture is high-definition, the number of neurons in the convolutional layer of the neural network structure selected by the detection model can be reduced. And different types of products contain ...

Embodiment 2

[0076] see Figure 5 , an embodiment of the present invention provides a device for detecting and locating product defects, including:

[0077] The structure selection module 10 is used to select the neural network structure of the detection model to be trained according to the picture data characteristics and product defect complexity of the product to be tested;

[0078] The data acquisition module 20 is used to acquire training data; wherein, the training data includes training product pictures and standard categories and standard positions of product defects in the training product pictures;

[0079] The detection model training module 30 is used to train the detection model of each neural network structure selected according to the training data;

[0080] The detection model selection module 40 is used to select the detection model with the best fitting degree from the trained detection models to provide to the detection server for product defect detection; wherein, the ...

Embodiment 3

[0089] see Figure 6 , the embodiment of the present invention provides a method for detecting and locating product defects, which can be executed by a detection server, including:

[0090] S210, receiving a product picture of the product to be tested;

[0091] S220, calculate the product picture according to the currently stored detection model, and obtain the predicted category and predicted position of the product defect in the product picture; wherein, the detection model is all selected neural networks generated according to training data training In the detection model of the structure, select the detection model with the best fitting degree, the neural network structure selected is selected according to the picture data characteristics and product defect complexity of the product to be tested, and the training data includes training product pictures and Standard categories and standard locations of product defects in the training product images.

[0092] Furthermore, ...

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 method, device, storage medium and terminal device for product defect detections and locations, wherein the method includes: according to the image data characteristics of products to be tested and the product defect complexity, selecting the neural network structure of detection models to be trained; obtaining training data, wherein the training data include training product pictures and standard categories and standard positions of product defects in the training product pictures; according to the training data, training the selected detection models of each neuralnetwork structure; selecting a best fitting detection model from the detection models after training to provide a detection server with the product defect detection, wherein the detection models are used for calculating according to the received product pictures to obtain predicted categories and predicted locations of the product defects in the received product pictures. Adopting the method, device, storage medium and terminal device for product defect detections and locations is capable of improving the accuracy of detecting the product defects.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a method, device, storage medium and terminal equipment for detecting and locating product defects. Background technique [0002] In the production scenario of traditional industrial manufacturing, quality inspection is a key link in the production process. In the fields of steel production, automobile manufacturing, paper making, battery manufacturing, solar panel manufacturing, etc., an important means of product quality control is to inspect the surface state of the product to determine whether the product has flaws and defects, and according to the inspection As a result, the product is processed accordingly. In the production scenario of traditional industrial manufacturing, quality inspection is a key link in the production process. In the fields of steel production, automobile manufacturing, paper making, battery manufacturing, solar panel manufacturing, etc., ...

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): G06T7/00G06T7/73G06N3/04G06N3/08G06K9/62G01N21/88
CPCG06N3/084G06T7/0008G06T7/73G01N21/8851G06T2207/30108G06T2207/20081G06T2207/20084G01N2021/8887G01N2021/8861G06N3/045G06F18/213
Inventor 冷家冰刘明浩梁阳文亚伟张发恩郭江亮唐进尹世明
Owner BEIJING BAIDU NETCOM SCI & 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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap