Construction method of automobile paint film defect recognition system based on deep learning

A defect recognition and deep learning technology, applied in character and pattern recognition, image analysis, image enhancement, etc., to make up for manual visual inspection, improve detection accuracy, and assist in recognition.

Pending Publication Date: 2019-10-15
JILIN UNIV
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Aiming at the deficiencies of the prior art, the present invention aims to provide a method for constructing a car paint film defect recognition system based on deep learning, which can effectively assist the recognition of car paint film defects, make up for the shortcomings of manual visual inspection, and improve the quality of car body paint film

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
  • Construction method of automobile paint film defect recognition system based on deep learning
  • Construction method of automobile paint film defect recognition system based on deep learning
  • Construction method of automobile paint film defect recognition system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The present invention will be further described below. It should be noted that this embodiment takes the technical solution as the premise, and provides a detailed implementation manner and a specific operation process, but the protection scope of the present invention is not limited to this embodiment.

[0032] The present embodiment provides a deep learning method for constructing a vehicle paint film defect recognition system, comprising the following steps:

[0033] S1. Collect a number of original images of the car body paint film to be detected to obtain the original sample set, and mark the original sample set, and the labeling includes marking the defect area and category in the original image of the car body paint film; use the 1abelImg tool when labeling. The original image of the film is selected and marked for the defect area, and then an xml format file is generated for each marked image for data sorting and unified specification operation to form a marked s...

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 construction method of an automobile paint film defect recognition system based on deep learning. The method comprises the following steps: collecting and labeling a plurality of to-be-detected vehicle body paint film original images, labeling comprising labeling defect areas and categories in the vehicle body paint film original images, after labeling, generating an xmlformat file for each labeled picture, and forming a labeled sample set; performing multiple times of multi-angle clipping sampling on each defect area marked in each picture of the marked sample set by utilizing a sampling block to obtain a defect area sampling set; the sampling block being square; training and testing the defect area sampling set by using a deep learning algorithm, and constructing an automobile paint film defect recognition model based on deep learning; and constructing an automobile paint film defect identification system based on deep learning. The method can effectively assist the recognition of the defects of the automobile paint film, makes up the defects of manual visual detection, and improves the quality of the automobile body paint film.

Description

technical field [0001] The invention relates to the technical field of deep learning, in particular to a deep learning method for constructing a vehicle paint film defect identification system. Background technique [0002] Automobile painting is a crucial link in the automobile manufacturing process. The painted body needs to be inspected and modified for surface paint film defects. The traditional industrial line defect detection system adopts human eye initial inspection and manual re-inspection. Due to the influence of human eye resolution, resolution speed and subjective consciousness of inspection workers, and long-term intensive work and reflection of white light will lead to workers' vision Fatigue, the efficiency of manual inspection is not high, and missed inspections often occur. SUMMARY OF THE INVENTION [0003] In view of the deficiencies of the prior art, the present invention aims to provide a deep learning method for constructing a vehicle paint film defec...

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): G06T7/00G06K9/62
CPCG06T7/0004G06T2207/30156G06F18/23213G06F18/241
Inventor 张晋东徐嘉斌朱琳瑶孙宛路刘通王雪张坤鹏王栋辉
Owner JILIN 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
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