Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Mobile phone clapboard sand detection method based on line scanning local peak analysis

A local peak and detection method technology, which is applied in image analysis, image data processing, instruments, etc., can solve problems such as the detection method of the quality of mobile phone partition accessories that have not been reported in relevant literature

Inactive Publication Date: 2014-04-23
XIANGTAN UNIV
View PDF0 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] To sum up, although many scholars at home and abroad have conducted a lot of research on the quality inspection of various mobile phone accessories in recent years, there is no relevant literature reporting the quality inspection method of mobile phone partition accessories, so the defect detection related to the partition is studied. method matters

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 clapboard sand detection method based on line scanning local peak analysis
  • Mobile phone clapboard sand detection method based on line scanning local peak analysis
  • Mobile phone clapboard sand detection method based on line scanning local peak analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] The present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments.

[0063] Such as figure 1 Shown, mobile phone clapboard residual sand particle detection method of the present invention, its specific process is:

[0064] 1. Calibration of the area to be detected. It was observed that sand particles are usually located in specific grooves on the edge of the partition, such as figure 2 As shown in the black box, it is necessary to extract the image of the area to be detected through mask operation before detection.

[0065] 2. Image preprocessing. Due to the little difference in the size of the residual sand grains, it appears as a bright dot structure of a certain size on the image, such as figure 2 Boxes pointed by black arrows. The top-hat transformation is often used to suppress the background, enhance the image details, and also realize the detection of small target objects whose size is smaller tha...

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 mobile phone clapboard sand detection method based on line scanning local peak analysis. The method comprises the following steps: (1) masking a mobile phone clapboard image to obtain an area to be detected; (2) preprocessing the clapboard image by adopting top-hat transformation; (3) analyzing the cross section features of pixel points in different directions in the area to be detected by adopting line segments by means of rotational scanning, and performing binary encoding according to gray level relative strength relationship between the internal pixel points and peripheral pixel points of line scanning adjacent domains to obtain a line scanning response values of the points; (4) calculating the probability measure P<t>m belonging to a local peak value of each point in each direction to obtain a local peak value evaluation map; (5) combining local peak values and pixel gray level information, calculating a matching fraction S<t>(x,y) indicating that a point to be detected belonging to sand to obtain a matching fractional image, and extracting and segmenting mobile phone clapboard residual sands by adopting a dual-threshold processing technology. The mobile phone clapboard sand detection method is insensitive to contrast change, highly sensitive to sand detection, and low in missing detection and error detection rates.

Description

technical field [0001] The invention relates to a method for detecting the appearance quality of mobile phone accessories, in particular to a method for detecting sand grains on a mobile phone partition based on line scanning local peak analysis. Background technique [0002] Mobile phones are currently the most influential consumer electronics products. During the mass production process of mobile phones, the appearance quality is extremely high. Traditional mobile phone accessories are usually inspected manually. Manual visual inspection is convenient, practical and adaptable, but labor The strength is high, the efficiency is low, the inspectors are prone to fatigue, and there are problems such as false detection and missed detection. At present, researchers at home and abroad mainly focus on the development of fast, reliable and accurate robust machine vision detection technology for mobile phone accessories. Improve product quality, reduce inspection costs, and increase ...

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
IPC IPC(8): G06T7/00
Inventor 张东波刘霞宋迪张莹张东晖
Owner XIANGTAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products