Mobile phone shell rear cover defect detection method and system based on deep learning

A mobile phone case, deep learning technology, applied in the field of visual detection, to achieve the effect of high detection accuracy, fast speed and strong robustness

Pending Publication Date: 2021-08-10
HARBIN INST OF TECH SHENZHEN GRADUATE SCHOOL
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Through the image of the back cover of the mobile phone case collected by the machine vision system, using traditional image processing algorithms to detect the defects of the back cover of the mobile phone case will face a huge challenge

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
  • Mobile phone shell rear cover defect detection method and system based on deep learning
  • Mobile phone shell rear cover defect detection method and system based on deep learning
  • Mobile phone shell rear cover defect detection method and system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0063] refer to Figure 1-2 as shown,

[0064] A method for detecting defects of a mobile phone case back cover based on deep learning, comprising the following steps:

[0065] Step 1: the image acquisition module acquires images;

[0066] Step 2: Select different types of defective image blocks and non-defective image blocks as training sample sets;

[0067] Step 3: Build a deep learning neural network for learning training and prediction;

[0068] Step 4: Use the training sample offline set to train the deep learning algorithm;

[0069] Step 5: Use the trained deep learning algorithm to detect and identify defects in the surface shell image of the mobile phone online.

[0070] Said step 3 includes:

[0071] Step 3.1: Use the selective search algorithm Selective Search for region selection to find out the Region Proposal of the candidate region where the target may exist in the picture;

[0072] Step 3.2: Adjust the size of the image to suit the input of the subsequent ...

specific Embodiment approach 2

[0105] refer to Figure 1-3 as shown,

[0106] A method for detecting defects of the back cover of a mobile phone case based on deep learning, and a defect detection system for the back cover of a mobile phone case based on deep learning, including: a mobile phone carrying platform, an image acquisition module, an image processing module, and a control feedback module;

[0107] The mobile phone bearing platform is an automatic translation device for carrying the mobile phone and realizing two-degree-of-freedom plane movement, and realizes plane positioning, bearing and two-degree-of-freedom movement of the mobile phone;

[0108] The mobile phone carrying platform includes a custom positioning fixture 1, a sliding assembly I2 and a sliding assembly II3, the custom positioning fixture 1 is used to place the mobile phone, and the sliding assembly I2 and the sliding assembly II3 drive the custom positioning fixture 1 in a manner that the motor drives the slider to move. The X-axi...

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 relates to the technical field of visual inspection, in particular to a mobile phone shell rear cover defect detection method and system based on deep learning. The invention discloses a mobile phone shell rear cover defect detection method based on deep learning. The method comprises the following steps: 1, enabling an image acquisition module to acquire an image; 2, selecting different types of defective image blocks and defect-free image blocks as a training sample set; 3, building a deep learning neural network for learning training and prediction; 4, training a deep learning algorithm by using the training sample offline set; and 5, detecting and identifying the defects of the mobile phone surface shell image on line by using the trained deep learning algorithm. A mobile phone shell rear cover defect detection system based on deep learning comprises a mobile phone bearing platform, an image acquisition module, an image processing module and a control feedback module.

Description

technical field [0001] The invention relates to the technical field of visual inspection, and more specifically to a method and system for detecting defects of the back cover of a mobile phone shell based on deep learning. Background technique [0002] With the vigorous development of the smart phone industry, the production of mobile phone accessories and their peripheral products continues to increase significantly. At present, in the assembly line production, the quality inspection of the surface defects of mobile phones is mainly realized by manual observation one by one with the help of certain auxiliary tools. As for the back cover of the mobile phone case, which has the characteristics of imaging and reflection of different colors, different patterns or even different textures according to different viewing angles under the illumination of the light source, this method will face the problem of small visual range and defects caused by light. It is not easy to find or ...

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): G06T7/00G06K9/32G06K9/62G06N3/04
CPCG06T7/0004G06V10/25G06N3/045G06F18/214G06F18/2411
Inventor 赵晨阳张大山李洋姚英学杜建军邓大祥
Owner HARBIN INST OF TECH SHENZHEN GRADUATE SCHOOL
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