A method for detecting printed circuit board defects based on skeleton extraction and distance transformation

A printed circuit board and distance transformation technology, which is applied to measuring devices, character and pattern recognition, instruments, etc., can solve problems such as loss, non-detection, and many false alarms, so as to reduce calculation deviation, reduce calculation amount, and improve defect identification efficiency effect

Active Publication Date: 2016-01-20
深圳市强华科技发展有限公司
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The advantage of the reference comparison method is that it is conceptually intuitive and the circuit implementation is simple. The disadvantage is that it requires precise alignment of the spatial positions of the PCB to be inspected and the standard PCB, otherwise there will be more false alarms; the second is the non-reference method, which is to detect whether the PCB meets the design requirements. The rules are mainly for dimensional verification, that is, to check whether the dimensions of conductors and pads meet the width and gap required by the design standards. Anything that does not meet the requirements of the design rules is considered a potential defect. Its advantage is that no reference is required. PCB, so it does not need to be aligned, the disadvantage is that it cannot detect defects that meet the design size, such as missing a wire on the PCB, etc.

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 method for detecting printed circuit board defects based on skeleton extraction and distance transformation
  • A method for detecting printed circuit board defects based on skeleton extraction and distance transformation
  • A method for detecting printed circuit board defects based on skeleton extraction and distance transformation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] In order to express the present invention more clearly, the present invention will be further described below in conjunction with the accompanying drawings.

[0029] see figure 1 , the method for detecting printed circuit board defects based on skeleton extraction and distance transformation provided by the invention comprises the following steps:

[0030] S1. Extract the single-pixel skeleton by looking up the index table;

[0031] S2, delete the skeleton branch;

[0032] S3. Search for abnormalities in the distance value range, and classify PCB board defects according to abnormal conditions.

[0033] see Figure 3-Figure 5 , in step S1, including by judging the eight connected domains around the pixel point, under the premise of ensuring that the number of connected domains is not affected, the index table method of deleting useless points, in the index table method, internal points, breakpoints, Isolated points and boundary points cannot be deleted. The method of...

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 method for detecting defects of a printed circuit board (PCB) based on skeleton extraction and range conversion. The method comprises the following steps of: checking an index table to extract a single-pixel skeleton; deleting skeleton branches; and searching for range value domain abnormity, and classifying PCB defects according to abnormal conditions. According to the method for detecting defects of the PCB based on skeleton extraction and range conversion, useless points can be deleted on the premise of not influencing the quantity of connected domains by extracting the single-pixel skeleton in a way of checking the index table, and the extracted skeleton is of a single pixel and has high generality and high practicability; skeleton branches are deleted, and range value domain abnormity is searched, so that calculation deviations can be reduced without influencing the speed and accuracy of skeleton tracking; and branches can be deleted, so that the calculation amount of skeleton search is reduced, and the efficiency of defect identification is increased.

Description

technical field [0001] The invention relates to the field of detecting printed circuit board defects, in particular to a method for detecting printed circuit board defects based on skeleton extraction and distance transformation. Background technique [0002] The printed circuit board is the main component of various electronic products, known as the "mother of electronic products", it is required for any electronic equipment and products, and its performance greatly affects the quality of electronic products . Almost every kind of electronic equipment is inseparable from PCB, ranging from electronic watches and calculators to aerospace, military weapon systems, etc., all of which contain PCB boards of various sizes. In recent years, with the continuous improvement of production technology, PCB is developing rapidly in the direction of ultra-thin, small components, high density, and fine pitch. This trend has brought many challenges and difficulties to quality inspection wo...

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): G06K9/46G01N21/956
Inventor 彭小波冯平徐刚程涛梁婧刘树成
Owner 深圳市强华科技发展有限公司
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