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

A Mark Point Visual Recognition and Positioning Method Based on Invariant Moments

A positioning method and visual recognition technology, applied in character and pattern recognition, image analysis, image enhancement and other directions, can solve the problems of scaling invariance, rotation invariance and poor real-time performance, and achieve scaling invariance and rotation invariance. problems, improved real-time performance, the effect of ensuring accuracy and reliability

Active Publication Date: 2020-09-18
HUAZHONG UNIV OF SCI & TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the above defects or improvement needs of the prior art, the present invention provides a Mark point visual recognition and positioning method based on invariant moments, thereby solving the problems of scaling invariance, rotation invariance, and poor real-time performance in the prior art. technical problem

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 Mark Point Visual Recognition and Positioning Method Based on Invariant Moments
  • A Mark Point Visual Recognition and Positioning Method Based on Invariant Moments
  • A Mark Point Visual Recognition and Positioning Method Based on Invariant Moments

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] Step 1. For figure 2 As shown in the PCB diagram, the Mark points include a white solid circle in the center, two regular octagons, and the outermost large circle outline features, such as image 3 shown. Since the outline of the outer great circle is mainly used to segment Mark points and external interference information, the present invention only uses solid circles and two regular octagons as geometric features that need to be extracted, such as Figure 4 shown. According to the geometric relationship, get as figure 2 The target area in the picture to be tested is similar to the geometric features of the real Mark point.

[0030] The specific method is: for the circle and the regular octagon in the present invention, in order to simplify the algorithm, the unified search interval is That is: first search for white gray blocks in the image to be detected, and obtain the center coordinates of the gray blocks. Then start from any angle, search the edge of the c...

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 visual recognition and positioning method of Mark points based on invariant moments, which includes performing rough screening in PCB diagrams according to the geometric characteristics of Mark points, obtaining suspected Mark points, and forming a result set; using standard Mark points as references Template, use the Hu invariant moment to match the suspected Mark points in the result set with the reference template in turn to obtain the Hu invariant moment matching value; sort the Hu invariant moment matching value, and the smallest Hu invariant moment matching value is the best Matching value. At this time, the suspected Mark point in the result set corresponding to the best matching value is the correct Mark point target. The invention solves the problems of scale invariance and rotation invariance in Mark point recognition, and at the same time, the real-time performance of Mark point recognition and positioning algorithms is greatly improved.

Description

technical field [0001] The invention belongs to the technical field of digital image processing and pattern recognition, and more specifically relates to a moment-invariant visual recognition and positioning method for Mark points. Background technique [0002] In recent years, in the automated manufacturing of printed circuit boards (PCBs) in the 3C industry, robot vision systems generally achieve target positioning with the assistance of Mark points. The visual positioning results of Mark points directly affect the execution accuracy of robots. At present, some Mark point recognition algorithms have been applied to industrial production, such as improved template matching, Huffman element transformation, Surf operator and other recognition algorithms. These algorithms can basically meet the current production requirements, but template matching needs to be processed separately for scaling, rotation, etc.; Huffman transform needs to be combined with other algorithms to ensu...

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): G06K9/62
CPCG06T7/0002G06T2207/30141G06F18/22
Inventor 彭刚熊超
Owner HUAZHONG UNIV OF SCI & TECH
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com