CN108053414A - A kind of machine vision edge detecting technology - Google Patents

A kind of machine vision edge detecting technology Download PDF

Info

Publication number
CN108053414A
CN108053414A CN201711327813.1A CN201711327813A CN108053414A CN 108053414 A CN108053414 A CN 108053414A CN 201711327813 A CN201711327813 A CN 201711327813A CN 108053414 A CN108053414 A CN 108053414A
Authority
CN
China
Prior art keywords
image
edge
detection
machine vision
detecting technology
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201711327813.1A
Other languages
Chinese (zh)
Inventor
陈哲
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Taicang Dingcheng Electronic Technology Co Ltd
Original Assignee
Taicang Dingcheng Electronic Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Taicang Dingcheng Electronic Technology Co Ltd filed Critical Taicang Dingcheng Electronic Technology Co Ltd
Priority to CN201711327813.1A priority Critical patent/CN108053414A/en
Publication of CN108053414A publication Critical patent/CN108053414A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/13Edge detection
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00Image enhancement or restoration
    • G06T5/001Image restoration
    • G06T5/002Denoising; Smoothing
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00Image enhancement or restoration
    • G06T5/20Image enhancement or restoration by the use of local operators
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/11Region-based segmentation
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/136Segmentation; Edge detection involving thresholding

Abstract

The present invention discloses a kind of machine vision edge detecting technology, includes the following steps:First step testee forms original image by video camera, original image obtains smoothed image by the single order and second dervative for filtering enhancing image, second step smoothed image is by enhancing edge basis come preliminary treatment image, which side is edge to 3rd step detection image, pass through the gradient magnitude of detection, threshold value is into row threshold division, 4th step, it is the position that numerical value determines definite image border according to Threshold segmentation, the binary image at edge is finally made, which to generate the present invention, improves the working environment of effect personnel, shorten the check test work period, improve automation and the modernization level of effect work, it is quick in the production system of high speed, accurately, comprehensively the geometric properties of product are assessed and measured, so as to strengthen the control of quality and improve logistic efficiency.

Description

A kind of machine vision edge detecting technology
Technical field
The present invention relates to a kind of machine vision edge detecting technology, belong to the technical field of machine vision edge detection.
Background technology
Machine vision processing can be regarded as realizing that a certain task is extracted from comprising substantial amounts of incoherent variable Invariant is exactly to simplify information in a word, this mean that throw away some unnecessary information and as far as possible.Using object not Change nature, and edge is exactly important invariance, the variation of light influences the appearance in a region, but not changes its side Edge.
The edge detection of digital picture is the graphical analyses necks such as image segmentation, the identification of target area, region shape extraction The first step of the highly important basis in domain, image understanding and analysis is exactly often edge detection, it has become machine vision at present One of most active problem of research field, occupies highly important status in engineer application.
The feature of image refers to the attribute that can be used as mark in picture field, and the edge of image is the most basic feature of image.In number In word image, so-called edge refers to that its surrounding pixel gray scale has the set of Spline smoothing or those pixels of roof variation.Due to The edge of object is reflected by gray scale discontinuity, therefore generally edge detection method is that each pixel of image under consideration exists The variation of gray scale in some field detects edge, this side using edge adjacent to single order or Second order directional changing rule Method is commonly referred to as Edge Detection Local Operator method.
The content of the invention
Goal of the invention:In order to overcome the specific aim of calling poor, it is impossible to called family is accurately found, and it is non-called to other User leads to the problem of interference, and the present invention provides the off host with dial feature and amplifies intercommunication telephone communication system.
Process program:The present invention discloses a kind of machine vision edge detecting technology, includes the following steps:
The first step:Filtering, testee form original image by video camera, and original image enhances the single order of image by filtering Smoothed image is obtained with second dervative, the calculating of numerical value is very sensitive to noise, it is therefore necessary to improve and noise using wave filter The performance of related edge detector may be noted that most wavenumber filter also results in edge strength while noise is reduced Loss;
Second step:Enhancing, for smoothed image by enhancing edge basis come preliminary treatment image, enhancing algorithm can be by neighborhood or office The point that portion's intensity value has significant change highlights what the enhancing of edges was completed generally by gradient magnitude is calculated;
3rd step:Detection, which side is edge to detection image, by the gradient magnitude of detection, threshold value into row threshold division, in image Many of point gradient magnitude it is bigger, and these points are not necessarily all edge in specific application field, so should use Some way come determine which point be that the simplest edge detection criterions of marginal point are gradient magnitude threshold criterions, directly utilization Threshold value, this method is easy, quickly;
4th step, positioning are the positions that numerical value determines definite image border according to Threshold segmentation, finally make the binary picture at edge As generation;
Further, the amplitude and threshold value will carry out denoising, and the generation of noise is had in measured value, so will be to measurement Good numerical value is handled into progressive step, it is ensured that the accuracy of numerical value,.
Further, the edge detection uses Edge Detection Local Operator method.
The present invention improves the working environment of effect personnel, shortens the check test work period, improves the automatic of effect work Change and modernization level, the geometric properties of product are assessed and surveyed fast, accurately and comprehensively in the production system of high speed Amount, so as to strengthen the control of quality and improve logistic efficiency.
Description of the drawings
Fig. 1:A kind of structure diagram of machine vision edge detecting technology of the present embodiment.
Specific embodiment
Below in conjunction with attached drawing and pass through specific embodiment the present invention be further elaborated, it should be pointed out that:For this technique For the common process personnel in field, without departing from the principle of the present invention, to repairing for various equivalent forms of the invention Change and fall within the application scope as defined in the appended claims.
Embodiment 1:
A kind of machine vision edge detecting technology as shown in Figure 1, includes the following steps:
The first step:Filtering, testee form original image by video camera, and original image enhances the single order of image by filtering Smoothed image is obtained with second dervative, the calculating of numerical value is very sensitive to noise, it is therefore necessary to improve and noise using wave filter The performance of related edge detector may be noted that most wavenumber filter also results in edge strength while noise is reduced Loss;
Second step:Enhancing, for smoothed image by enhancing edge basis come preliminary treatment image, enhancing algorithm can be by neighborhood or office The point that portion's intensity value has significant change highlights what the enhancing of edges was completed generally by gradient magnitude is calculated;
3rd step:Detection, which side is edge to detection image, by the gradient magnitude of detection, threshold value into row threshold division, in image Many of point gradient magnitude it is bigger, and these points are not necessarily all edge in specific application field, so should use Some way come determine which point be that the simplest edge detection criterions of marginal point are gradient magnitude threshold criterions, directly utilization Threshold value, this method is easy, quickly;
4th step, positioning are the positions that numerical value determines definite image border according to Threshold segmentation, finally make the binary picture at edge As generation;
Further, the amplitude and threshold value will carry out denoising, and the generation of noise is had in measured value, so will be to measurement Good numerical value is handled into progressive step, it is ensured that the accuracy of numerical value.
Further, the edge detection uses Edge Detection Local Operator method.
The present invention improves the working environment of effect personnel, shortens the check test work period, improves the automatic of effect work Change and modernization level, the geometric properties of product are assessed and surveyed fast, accurately and comprehensively in the production system of high speed Amount, so as to strengthen the control of quality and improve logistic efficiency.

Claims (3)

1. a kind of machine vision edge detecting technology, which is characterized in that include the following steps:
The first step:Filtering, testee form original image by video camera, and original image enhances the single order of image by filtering Smoothed image is obtained with second dervative;
Second step:Enhancing, smoothed image is by enhancing edge basis come preliminary treatment image;
3rd step:Detection, which side is edge to detection image, by the gradient magnitude of detection, threshold value into row threshold division;
4th step, positioning are the positions that numerical value determines definite image border according to Threshold segmentation, finally make the binary picture at edge As generation.
2. a kind of machine vision edge detecting technology according to claim 1, which is characterized in that the amplitude and threshold value will be into Row denoising.
3. a kind of machine vision edge detecting technology according to claim 1, which is characterized in that the edge detection uses side Edge detects Local Operator method.
CN201711327813.1A 2017-12-13 2017-12-13 A kind of machine vision edge detecting technology Pending CN108053414A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711327813.1A CN108053414A (en) 2017-12-13 2017-12-13 A kind of machine vision edge detecting technology

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711327813.1A CN108053414A (en) 2017-12-13 2017-12-13 A kind of machine vision edge detecting technology

Publications (1)

Publication Number Publication Date
CN108053414A true CN108053414A (en) 2018-05-18

Family

ID=62132154

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711327813.1A Pending CN108053414A (en) 2017-12-13 2017-12-13 A kind of machine vision edge detecting technology

Country Status (1)

Country Link
CN (1) CN108053414A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110060270A (en) * 2019-04-25 2019-07-26 宁锐慧创信息科技南京有限公司 A kind of edge detection method suitable for low image quality multiangular tubular object

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
王丹: "《基于各向异性高斯滤波的图像边缘检测方法》", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110060270A (en) * 2019-04-25 2019-07-26 宁锐慧创信息科技南京有限公司 A kind of edge detection method suitable for low image quality multiangular tubular object
CN110060270B (en) * 2019-04-25 2021-05-04 宁锐慧创信息科技南京有限公司 Edge detection method suitable for polygonal tubular object with low imaging quality

Similar Documents

Publication Publication Date Title
JP5699788B2 (en) Screen area detection method and system
EP3176751B1 (en) Information processing device, information processing method, computer-readable recording medium, and inspection system
CN105865329B (en) The acquisition system and method for the bundled round steel end face center coordinate of view-based access control model
CN104966089B (en) A kind of method and device of image in 2 D code edge detection
CN107256406B (en) Method and device for segmenting overlapped fiber image, storage medium and computer equipment
CN108921176B (en) Pointer instrument positioning and identifying method based on machine vision
CN105718931B (en) System and method for determining clutter in acquired images
US9792507B2 (en) Method and system for ground truth determination in lane departure warning
Yu et al. Image edge detection based tool condition monitoring with morphological component analysis
CN102005051A (en) Edge detection method and related device
CN110070523B (en) Foreign matter detection method for bottle bottom
TWI543117B (en) Method for recognizing and locating object
CN108053414A (en) A kind of machine vision edge detecting technology
CN104732530A (en) Image edge detection method
CN105447489B (en) A kind of character of picture OCR identifying system and background adhesion noise cancellation method
KR101977647B1 (en) Apparatus and Method for Detection MURA in Display Device
CN109211919B (en) Method and device for identifying magnetic tile defect area
CN108629775B (en) Thermal state high-speed wire rod surface image processing method
CN109087347B (en) Image processing method and device
CN107345916B (en) Plane appearance detection method based on fixed contour
JP6114559B2 (en) Automatic unevenness detector for flat panel display
JP2019526865A (en) Particle boundary identification
CN107194939A (en) A kind of edge detection method and system based on improved edge focusing
Soumya et al. Enhancement and Segmentation of Historical Records
Chiang et al. Automated surface defect inspection system for capacitive touch sensor

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination