Wine bottle defect automatic detection method based on YOLOv3

An automatic detection and defect technology, which is applied in image data processing, image enhancement, instruments, etc., can solve the problems of large detection tasks, prone to missed detection, and large number of wine bottles, and achieves fast detection speed and convenient operation , Improving detection efficiency and accuracy

Pending Publication Date: 2021-01-05
FOSHAN NANHAI GUANGDONG TECH UNIV CNC EQUIP COOP INNOVATION INST +1
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, in the production process of wine bottle manufacturers, the quality inspection of wine bottles was mainly done manually in the past. Due to the huge number of wine bottles manufactured, the detection task is huge, and it is easy to miss inspection.

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
  • Wine bottle defect automatic detection method based on YOLOv3
  • Wine bottle defect automatic detection method based on YOLOv3
  • Wine bottle defect automatic detection method based on YOLOv3

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] Such as Figure 1 to Figure 6 As shown, this embodiment discloses a wine bottle defect detection method based on deep learning target detection, which is characterized in that the one-stage YOLOv3 multi-scale feature extraction detection network is used to realize the accurate detection of multi-category and large-scale defect targets. Positioning and classification, specifically including the following implementation steps:

[0034] Step 1. Collect image data of abundant defective wine bottles on the production site for model learning.

[0035] (1) Since the bottle cap and bottle body may have flaws, pictures of the bottle body and bottle cap will be collected separately.

[0036] (2) Use a high-precision industrial camera to take pictures of defective wine bottles in the production environment. Cameras need to be arranged in two places, one for collecting bottle cap pictures, and the other for collecting bottle body pictures, such as figure 1 and figure 2 .

[00...

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 wine bottle defect automatic detection method based on YOLOv3. The method comprises the steps: learning defect features in wine bottle defect image data which is marked through manual collection through a YOLOv3 network structure to obtain a model which can automatically recognize whether a wine bottle in production contains a defect; and loading the model into a real-time wine bottle identification system, carrying out real-time shooting, and returning an identification result in real time, so that the problems of low efficiency and low precision of a manual detection belt can be solved, the automation degree of a production process can be improved, the detection speed is very high, multiple images can be detected in one second, the requirement of large-batch detection tasks is met, the defect that the previous version is not high in recognition precision of small-size targets is overcome, and the detection precision is remarkably improved. The method has theadvantages of being convenient to operate and easy to implement.

Description

technical field [0001] The invention relates to the technical field of deep learning computer vision, in particular to a method for automatic detection of wine bottle defects based on YOLOv3. Background technique [0002] As my country's production and manufacturing industry continues to transform into automated production, it is gradually transforming from a manual-dominated production line to a machine-dominated production line, and artificial intelligence algorithms play a vital role. For example, in the production process of wine bottle manufacturers, the quality inspection of wine bottles was mainly done manually in the past. Due to the huge number of wine bottles manufactured, the detection task is huge, and it is easy to miss inspection. But now using computer vision algorithms, using a camera to shoot a wine bottle can immediately determine whether the wine bottle contains flaws and liberate manpower. Therefore, the existing technology needs to be further improved an...

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): G06T7/00G06T7/73G06N3/04
CPCG06T7/0004G06T7/73G06T2207/20081G06N3/045
Inventor 关洁杨海东李俊宇李淑芬
Owner FOSHAN NANHAI GUANGDONG TECH UNIV CNC EQUIP COOP INNOVATION INST
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