Supercharge Your Innovation With Domain-Expert AI Agents!

A Fast and Stable Method for Thickness Detection of Devices with Sub-pixel Precision

A sub-pixel-level, device-thick technology, applied in the fields of industrial vision and automatic inspection, can solve problems affecting corporate profits, reducing production capacity, and high complexity

Inactive Publication Date: 2020-02-18
合肥市雅视智能科技有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current common sub-pixel boundary positioning algorithm is too complex and has a high degree of redundant calculation, which leads to a decrease in the efficiency of automatic detection equipment, thereby reducing production capacity and affecting the profit of the enterprise

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
  • A Fast and Stable Method for Thickness Detection of Devices with Sub-pixel Precision
  • A Fast and Stable Method for Thickness Detection of Devices with Sub-pixel Precision
  • A Fast and Stable Method for Thickness Detection of Devices with Sub-pixel Precision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0094] Referring to the accompanying drawings, the abnormal situations handled by the present invention include: no device in the field of view, multiple devices in the field of view, overlapping devices, gaps between the device and the glass surface, interference from dust on the device, and inaccurate placement of devices caused by tail flicking. Improve the sub-pixel boundary positioning algorithm, from the three aspects of initial positioning, parameter estimation, and fast search for the best parameters. On the basis of ensuring that the positioning accuracy meets the requirements, the algorithm speed is further improved, thereby improving the sub-pixel Potential applications of boundary localization algorithms.

[0095] 1. Preliminary positioning of the boundary

[0096] Divide the image into two regions, target and air, and then get the dividing line of these two regions as the preliminary boundary positioning result. In this way, the subsequent precise positioning at...

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 a fast and stable sub-pixel-level high-precision device thickness detection method. The method comprises the following step: carrying out preliminary boundary positioning; to be specific, dividing an image into a target region and an air region and then obtaining a boundary between the two regions to obtain a preliminary boundary positioning result; carrying out sub-pixel-level precise positioning; to be specific, carrying out solution based on a particle swarm optimization algorithm by using an arc tangent curve fitting method, and then carrying out fitting on a positioning result of each column by using a bezier curve; and then dealing with an abnormal situation. According to the method provided by the invention, on the basis of improvement of a sub-pixel-level boundary positioning algorithm, the positioning accuracy can meet the requirement and the algorithm speed can be increased from aspects of initial positioning, approximate parameter estimation, and rapid optimal parameter searching, so that the application potential of the sub-pixel-level boundary positioning algorithm is improved.

Description

technical field [0001] The invention belongs to the field of automatic detection, relates to the technical field of industrial vision, in particular to a fast and stable method for detecting the thickness of a sub-pixel-level precision device. Background technique [0002] With the rapid development of my country's manufacturing industry, the emphasis on quality has become increasingly important. In the production process of various products, the use of automated equipment for quality inspection of various components can reduce the scrap rate and reduce the loss of materials. This has become a powerful means to improve corporate profits and brand influence. Industrial vision technology is the most commonly used technology in the field of automated inspection. [0003] Measuring the thickness and size of components is the most common application of industrial visual inspection. After obtaining the size parameters of the components, it can be judged whether the components ar...

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 Patents(China)
IPC IPC(8): G01B11/06G06T7/00
CPCG01B11/06G06T7/0004
Inventor 韦文波盛琦江淮李维孔园林吕政杨世举
Owner 合肥市雅视智能科技有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com