CN107122783A - A kind of assembling connecting piece method for quickly identifying based on Corner Detection - Google Patents
A kind of assembling connecting piece method for quickly identifying based on Corner Detection Download PDFInfo
- Publication number
- CN107122783A CN107122783A CN201710256335.3A CN201710256335A CN107122783A CN 107122783 A CN107122783 A CN 107122783A CN 201710256335 A CN201710256335 A CN 201710256335A CN 107122783 A CN107122783 A CN 107122783A
- Authority
- CN
- China
- Prior art keywords
- mrow
- msubsup
- mtd
- msub
- munderover
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/06—Recognition of objects for industrial automation
Abstract
The invention discloses a kind of assembling connecting piece method for quickly identifying based on Corner Detection, including sample angle point study statistics：Harris angle points, Shi Tomasi angle points, FAST angle points including gathering and detecting sample, and count the average value and standard deviation of various angle point quantity in the sample；High robust Corner Detection is quickly recognized：Including setting reliability requirement, the calculation formula of connector possible position numerical lower limits is set up automatically；Select the maximum Corner Detection Algorithm of the number average Corner Detection Algorithm minimum with standard deviation in angle point learns statistics, the method for meeting condition is set to detect image angle point to be checked, if image local area angle point quantity is higher than threshold requirement, it is probably greatly connector then to think to have, and extracts image and inputs to the detection of grader kind；Full Corner Detection is quickly recognized：Including the use of Harris angle points, Shi Tomasi angle points, three kinds of angular-point detection methods of FAST angle points, for the position with angle point, that is, think to be likely to be connector, extract image and input to the detection of grader kind.
Description
Technical field
The present invention relates to assembling connecting piece method for quickly identifying, more particularly to a kind of assembling connecting piece based on Corner Detection
Method for quickly identifying.
Background technology
Assembling refers to by defined technical requirements, and part or part are connected, semifinished or finished goods are made
Technical process.Assembling is the important procedure of product manufacture, and the quality of assembling, the quality to product plays a decisive role.
Assembling quality is discussed, carried out in the case where all Assembly parts are certified products, install correct precondition, therefore in detection production
Before product assembling quality, it is necessary to check for misloading and the part of neglected loading.Because Assembly part, connector are more, assembling detection pair
As variation, accuracy, uniformity and real-time to detection technique propose higher requirement and challenge.Relative to whole dress
With product, its connector size is smaller, often complete in the picture, therefore the geometric figure that standard connector can be closed is retouched
State, and the geometric figure closed certainly exists angle point.
The general recognition methods having to the method that objects in images is identified based on classification with based on the identification side matched
Method.It is computationally intensive using the method for classification, but precision it is high, with generalization ability, also have in the case of to provide sample compared with
Good recognition accuracy, such as piston of automobile assembling quality visual detecting system (ZL201010543006.5) can be disposably automatic right
Piston of automobile top surface character, piston ring is assembled, and the content such as graphite linings integrality carries out the vision-based detection based on digital picture；Vision
Detection method (201610496560.X) allows the bowlder on the image for detecting product to be checked to improve the center of circle and radius is extracted
The degree of accuracy and speed, and then improve extraction efficiency；Braking automobile master cylinder piston surface quality machine vision detection device
(201210348279.3) quick detection for being automatically performed piston face mass defect can be realized, the detection knot of surface quality is provided
Really.Recognition methods based on inherent feature is good to specific parts Detection results, if object variation, must be by professional vision
Testing staff detects feature again, and flexibility is poor.Recognition methods flexibility based on matching is stronger, for not setting in advance
Situation can not then detect, it is narrower using scope.Patent of the present invention for connector size it is smaller, be in the picture it is complete,
It can be described with the geometric figure of closing, the characteristics of certainly existing angle point.Realize that assembling connecting piece is quickly known based on Corner Detection
Not, the efficiency of the recognition methods based on classification can be effectively improved.
The content of the invention
In order to solve the above technical problems, it is an object of the invention to provide a kind of assembling connecting piece based on Corner Detection is quick
Recognition methods.
The purpose of the present invention is realized by following technical scheme：
A kind of assembling connecting piece method for quickly identifying based on Corner Detection, comprises the following steps：
Step A samples angle point study statistics；Including gather and detect the Harris angle points of sample, Shi-Tomasi angle points,
FAST angle points, and count the average value and standard deviation of various angle point quantity in the sample；
Step B high robust Corner Detections are quickly recognized；Including setting reliability requirement, connector possible position is set up automatically
The calculation formula of numerical lower limits；Select the Corner Detection Algorithm and standard deviation of the number average maximum in angle point learns statistics most
Small Corner Detection Algorithm, makes the method for meeting condition detect image angle point to be checked, if image local area angle point quantity is higher than
Threshold requirement, then it is assumed that with being probably greatly connector, extracts image and inputs to the detection of grader kind；
Step C is complete, and Corner Detection is quickly recognized；Including the use of Harris angle points, Shi-Tomasi angle points, FAST angle points three
Angular-point detection method is planted, for the position with angle point, that is, thinks to be likely to be connector, extracts image and input to grader kind
Detection.
Compared with prior art, one or more embodiments of the invention can have the following advantages that：
Relative to whole assembling product, the size of connector is smaller, often complete in the picture, can be several with closing
What figure description, certainly exists angle point, and invention is based on this hypothesis, it is possible to achieve the various connectors of assembly process are quickly known
Not, for do not have sample set detection means, it is probably connector image that can quickly filter out, so as to improve
Test equipment detection efficiency and real-time.
Brief description of the drawings
Fig. 1 is the assembling connecting piece method for quickly identifying flow chart based on Corner Detection；
Fig. 2 is assembling connecting piece model top view；
Fig. 3 is the quick recognition effect figure of assembling connecting piece based on Corner Detection.
Embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with embodiment and accompanying drawing to this hair
It is bright to be described in further detail.
As shown in figure 1, being the assembling connecting piece method for quickly identifying flow based on Corner Detection, comprise the following steps：
Step 1 sample angle point study statistics：Including gather and detect the Harris angle points of sample, Shi-Tomasi angle points,
FAST angle points, and count the average value and standard deviation of various angle point quantity in the sample；
Step 2 high robust Corner Detection is quickly recognized：Including setting reliability requirement, connector possible position is set up automatically
The calculation formula of numerical lower limits；Select the Corner Detection Algorithm and standard deviation of the number average maximum in angle point learns statistics most
Small Corner Detection Algorithm, makes the method for meeting condition detect image angle point to be checked, if image local area angle point quantity is higher than
Threshold requirement, then it is assumed that with being probably greatly connector, extracts image and inputs to the detection of grader kind；
The full Corner Detection of step 3 is quickly recognized：Including the use of Harris angle points, Shi-Tomasi angle points, FAST angle points three
Angular-point detection method is planted, for the position with angle point, that is, thinks to be likely to be connector, extracts image and input to grader kind
Detection.
The sample collection stage of above-mentioned steps 1 specifically includes：
If sample set is { R1,R2…Ri…RI, if with RX、RYImage R is represented respectivelyiHorizontal stroke, ordinate scope, for
Arbitrary sample image Ri, point p (x, y) set can be expressed as；
Ri=p (x, y) | x ∈ RX∧y∈RY}
If along direction w on image midpoint p (x, y)u,vGrey scale change value be Ex,yFor：
And the detection method such as Harris angle points, Shi-Tomasi angle points, FAST angle points is then to select different to point P (x, y)
Wu,v, according to different Ex,yJudge P (x, y) whether as angle point；
Use Harris angle points, Shi-Tomasi angle points, 3 kinds of method detection sample set { R of FAST angle points1,R2…Ri…RI}
It is respectively N to detect angle point quantity vectorH、NST、NF：
N is calculated respectivelyHDesired value and variance E (NH)、D(NH)；NSTDesired value and variance E (NST)、D(NST)；NF's
Desired value and variance E (NF)、D(NF)。
The high robust Corner Detection of above-mentioned steps 2 is quickly in identification, and setting confidence level requirement sets up connector possible automatically
The calculation formula of number of positions lower limit；
The confidence level can divide multiple stage (c1,c2...) choose, then under different confidence levels, Harris angle point quantity
Lower limit nTHCalculation formula is：
Shi-Tomasi angle point numerical lower limits nTSCalculation formula is：
FAST angle point numerical lower limits nTFCalculation formula is：
The full Corner Detection of above-mentioned steps 3 directly sets angle point numerical lower limits n in quickly recognizingT=1, use Harris angles
Point, Shi-Tomasi angle points, 3 kinds of angular-point detection methods of FAST angle points, for the position with angle point, that is, think the company of being likely to be
Fitting, extracts image and inputs to the detection of grader kind.
Fig. 2 is assembling connecting piece model top view；Fig. 3 is the quick recognition effect of assembling connecting piece based on Corner Detection
Figure.
Although disclosed herein embodiment as above, described content is only to facilitate understanding the present invention and adopting
Embodiment, is not limited to the present invention.Any those skilled in the art to which this invention pertains, are not departing from this
On the premise of the disclosed spirit and scope of invention, any modification and change can be made in the implementing form and in details,
But the scope of patent protection of the present invention, still should be subject to the scope of the claims as defined in the appended claims.
Claims (4)
1. a kind of assembling connecting piece method for quickly identifying based on Corner Detection, it is characterised in that methods described includes following step
Suddenly：
Step A samples angle point study statistics：Harris angle points, Shi-Tomasi angle points, FAST including gathering and detecting sample
Angle point, and count the average value and standard deviation of various angle point quantity in the sample；
Step B high robust Corner Detections are quickly recognized：Including setting reliability requirement, connector possible position quantity is set up automatically
The calculation formula of lower limit；The selection maximum Corner Detection Algorithm of number average and standard deviation minimum in angle point learns statistics
Corner Detection Algorithm, makes the method for meeting condition detect image angle point to be checked, if image local area angle point quantity is higher than threshold value
It is required that, then it is assumed that with being probably greatly connector, extract image and input to the detection of grader kind；
Step C is complete, and Corner Detection is quickly recognized：Including the use of Harris angle points, Shi-Tomasi angle points, three kinds of angles of FAST angle points
Point detecting method, for the position with angle point, that is, thinks to be likely to be connector, extracts image and inputs to the inspection of grader kind
Survey.
2. the assembling connecting piece method for quickly identifying as claimed in claim 1 based on Corner Detection, it is characterised in that the step
Sample collection is specifically included in rapid A：
If sample set is { R1,R2…Ri…RI, if with RX、RYImage R is represented respectivelyiHorizontal stroke, ordinate scope, for any
Sample image Ri, point p (x, y) set can be expressed as；
Ri=p (x, y) | x ∈ RX∧y∈RY}
If along direction w on image midpoint p (x, y)u,vGrey scale change value be Ex,yFor：
<mrow>
<msub>
<mi>E</mi>
<mrow>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
</mrow>
</msub>
<mo>=</mo>
<munder>
<mo>&Sigma;</mo>
<mrow>
<mi>u</mi>
<mo>,</mo>
<mi>v</mi>
</mrow>
</munder>
<msub>
<mi>w</mi>
<mrow>
<mi>u</mi>
<mo>,</mo>
<mi>v</mi>
</mrow>
</msub>
<msup>
<mrow>
<mo>|</mo>
<mrow>
<msub>
<mi>I</mi>
<mrow>
<mi>x</mi>
<mo>+</mo>
<mi>u</mi>
<mo>,</mo>
<mi>y</mi>
<mo>+</mo>
<mi>v</mi>
</mrow>
</msub>
<mo>-</mo>
<msub>
<mi>I</mi>
<mrow>
<mi>u</mi>
<mo>,</mo>
<mi>v</mi>
</mrow>
</msub>
</mrow>
<mo>|</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
And the detection method such as Harris angle points, Shi-Tomasi angle points, FAST angle points is then to select different to point P (x, y)
wu,v, according to different Ex,yJudge P (x, y) whether as angle point；
Use Harris angle points, Shi-Tomasi angle points, three kinds of method detection sample set { R of FAST angle points1,R2…Ri…RIDetection
Angle point quantity vector is respectively NH、NS、NF：
<mrow>
<msub>
<mi>N</mi>
<mi>H</mi>
</msub>
<mo>=</mo>
<mrow>
<mo>(</mo>
<msubsup>
<mi>n</mi>
<mi>H</mi>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</msubsup>
<mo>,</mo>
<msubsup>
<mi>n</mi>
<mi>H</mi>
<mrow>
<mo>(</mo>
<mn>2</mn>
<mo>)</mo>
</mrow>
</msubsup>
<mo>...</mo>
<msubsup>
<mi>n</mi>
<mi>H</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
</msubsup>
<mo>...</mo>
<msubsup>
<mi>n</mi>
<mi>H</mi>
<mrow>
<mo>(</mo>
<mi>I</mi>
<mo>)</mo>
</mrow>
</msubsup>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<msub>
<mi>N</mi>
<mi>S</mi>
</msub>
<mo>=</mo>
<mrow>
<mo>(</mo>
<msubsup>
<mi>n</mi>
<mi>S</mi>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</msubsup>
<mo>,</mo>
<msubsup>
<mi>n</mi>
<mi>S</mi>
<mrow>
<mo>(</mo>
<mn>2</mn>
<mo>)</mo>
</mrow>
</msubsup>
<mo>...</mo>
<msubsup>
<mi>n</mi>
<mi>S</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
</msubsup>
<mo>...</mo>
<msubsup>
<mi>n</mi>
<mi>S</mi>
<mrow>
<mo>(</mo>
<mi>I</mi>
<mo>)</mo>
</mrow>
</msubsup>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<msub>
<mi>N</mi>
<mi>F</mi>
</msub>
<mo>=</mo>
<mrow>
<mo>(</mo>
<msubsup>
<mi>n</mi>
<mi>F</mi>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</msubsup>
<mo>,</mo>
<msubsup>
<mi>n</mi>
<mi>F</mi>
<mrow>
<mo>(</mo>
<mn>2</mn>
<mo>)</mo>
</mrow>
</msubsup>
<mo>...</mo>
<msubsup>
<mi>n</mi>
<mi>F</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
</msubsup>
<mo>...</mo>
<msubsup>
<mi>n</mi>
<mi>F</mi>
<mrow>
<mo>(</mo>
<mi>I</mi>
<mo>)</mo>
</mrow>
</msubsup>
<mo>)</mo>
</mrow>
</mrow>
N is calculated respectivelyHDesired value and variance E (NH)、D(NH)；NSTDesired value and variance E (NS)、D(NS)；NFDesired value
With variance E (NF)、D(NF)。
3. the assembling connecting piece method for quickly identifying as claimed in claim 1 based on Corner Detection, it is characterised in that the step
Rapid B high robusts Corner Detection is quickly in identification, and connector possible position numerical lower limits are set up in setting confidence level requirement automatically
Calculation formula includes：
The confidence level can divide multiple stage (c1,c2...) choose, then under different confidence levels, Harris angle point numerical lower limits
nTHCalculation formula is：
<mrow>
<msub>
<mi>n</mi>
<mrow>
<mi>T</mi>
<mi>H</mi>
</mrow>
</msub>
<mo>=</mo>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mn>1</mn>
<mi>I</mi>
</munderover>
<msubsup>
<mi>n</mi>
<mi>H</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
</msubsup>
<mo>-</mo>
<mi>&lambda;</mi>
<mrow>
<mo>(</mo>
<mi>c</mi>
<mo>)</mo>
</mrow>
<msqrt>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mn>1</mn>
<mi>I</mi>
</munderover>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>n</mi>
<mi>H</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
</msubsup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>-</mo>
<msup>
<mrow>
<mo>(</mo>
<munderover>
<mo>&Sigma;</mo>
<mn>1</mn>
<mi>I</mi>
</munderover>
<msubsup>
<mi>n</mi>
<mi>H</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
</msubsup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</msqrt>
</mrow>
</mtd>
<mtd>
<mrow>
<mi>c</mi>
<mo><</mo>
<mn>100</mn>
<mi>%</mi>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>1</mn>
</mtd>
<mtd>
<mrow>
<mi>c</mi>
<mo>=</mo>
<mn>100</mn>
<mi>%</mi>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
Shi-Tomasi angle point numerical lower limits nTSCalculation formula is：
<mrow>
<msub>
<mi>n</mi>
<mrow>
<mi>T</mi>
<mi>S</mi>
</mrow>
</msub>
<mo>=</mo>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mn>1</mn>
<mi>I</mi>
</munderover>
<msubsup>
<mi>n</mi>
<mi>S</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
</msubsup>
<mo>-</mo>
<mi>&lambda;</mi>
<mrow>
<mo>(</mo>
<mi>c</mi>
<mo>)</mo>
</mrow>
<msqrt>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mn>1</mn>
<mi>I</mi>
</munderover>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>n</mi>
<mi>S</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
</msubsup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>-</mo>
<msup>
<mrow>
<mo>(</mo>
<munderover>
<mo>&Sigma;</mo>
<mn>1</mn>
<mi>I</mi>
</munderover>
<msubsup>
<mi>n</mi>
<mi>S</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
</msubsup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</msqrt>
</mrow>
</mtd>
<mtd>
<mrow>
<mi>c</mi>
<mo><</mo>
<mn>100</mn>
<mi>%</mi>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>1</mn>
</mtd>
<mtd>
<mrow>
<mi>c</mi>
<mo>=</mo>
<mn>100</mn>
<mi>%</mi>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
FAST angle point numerical lower limits nTFCalculation formula is：
<mrow>
<msub>
<mi>n</mi>
<mrow>
<mi>T</mi>
<mi>F</mi>
</mrow>
</msub>
<mo>=</mo>
<mrow>
<mo>{</mo>
<mrow>
<mtable>
<mtr>
<mtd>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mn>1</mn>
<mi>I</mi>
</munderover>
<msubsup>
<mi>n</mi>
<mi>F</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
</msubsup>
<mo>-</mo>
<mi>&lambda;</mi>
<mrow>
<mo>(</mo>
<mi>c</mi>
<mo>)</mo>
</mrow>
<msqrt>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mn>1</mn>
<mi>I</mi>
</munderover>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>n</mi>
<mi>F</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
</msubsup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>-</mo>
<msup>
<mrow>
<mo>(</mo>
<munderover>
<mo>&Sigma;</mo>
<mn>1</mn>
<mi>I</mi>
</munderover>
<msubsup>
<mi>n</mi>
<mi>F</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
</msubsup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</msqrt>
</mrow>
</mtd>
<mtd>
<mrow>
<mi>c</mi>
<mo><</mo>
<mn>100</mn>
<mi>%</mi>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>1</mn>
</mtd>
<mtd>
<mrow>
<mi>c</mi>
<mo>=</mo>
<mn>100</mn>
<mi>%</mi>
</mrow>
</mtd>
</mtr>
</mtable>
<mo>.</mo>
</mrow>
</mrow>
</mrow>
4. the assembling connecting piece method for quickly identifying as claimed in claim 1 based on Corner Detection, it is characterised in that the step
The full Corner Detections of rapid C quickly in identification, directly set angle point numerical lower limits nT=1, use Harris angle points, Shi-Tomasi angles
Point, three kinds of angular-point detection methods of FAST angle points.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710256335.3A CN107122783B (en) | 2017-04-19 | 2017-04-19 | Method for quickly identifying assembly connector based on angular point detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710256335.3A CN107122783B (en) | 2017-04-19 | 2017-04-19 | Method for quickly identifying assembly connector based on angular point detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107122783A true CN107122783A (en) | 2017-09-01 |
| CN107122783B CN107122783B (en) | 2020-11-13 |
Family
ID=59725704
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710256335.3A Active CN107122783B (en) | 2017-04-19 | 2017-04-19 | Method for quickly identifying assembly connector based on angular point detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107122783B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108280430A (en) * | 2018-01-24 | 2018-07-13 | 陕西科技大学 | A kind of flow image-recognizing method |
| CN112884784A (en) * | 2021-03-11 | 2021-06-01 | 南通大学 | Image-based lens detection and front-back judgment method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009068718A1 (en) * | 2007-11-29 | 2009-06-04 | Escribano Gonzalez Jesus | Environmentally-friendly device for collecting plastic sheets from cultivated soil |
| CN102072910A (en) * | 2010-11-13 | 2011-05-25 | 上海交通大学 | Visual inspection system for automobile piston assembly quality |
| CN106338521A (en) * | 2016-09-22 | 2017-01-18 | 华中科技大学 | Additive manufacturing surface defect, internal defect and shape composite detection method and device |
-
2017
- 2017-04-19 CN CN201710256335.3A patent/CN107122783B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009068718A1 (en) * | 2007-11-29 | 2009-06-04 | Escribano Gonzalez Jesus | Environmentally-friendly device for collecting plastic sheets from cultivated soil |
| CN102072910A (en) * | 2010-11-13 | 2011-05-25 | 上海交通大学 | Visual inspection system for automobile piston assembly quality |
| CN106338521A (en) * | 2016-09-22 | 2017-01-18 | 华中科技大学 | Additive manufacturing surface defect, internal defect and shape composite detection method and device |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108280430A (en) * | 2018-01-24 | 2018-07-13 | 陕西科技大学 | A kind of flow image-recognizing method |
| CN108280430B (en) * | 2018-01-24 | 2021-07-06 | 陕西科技大学 | Flow image identification method |
| CN112884784A (en) * | 2021-03-11 | 2021-06-01 | 南通大学 | Image-based lens detection and front-back judgment method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107122783B (en) | 2020-11-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109785316B (en) | Method for detecting apparent defects of chip | |
| CN104680519B (en) | Seven-piece puzzle recognition methods based on profile and color | |
| CN105160319B (en) | One kind realizing that pedestrian knows method for distinguishing again under monitor video | |
| CN103279765B (en) | Steel wire rope surface damage detection method based on images match | |
| CN109035273B (en) | Image signal fast segmentation method of immunochromatography test paper card | |
| CN107220649A (en) | A kind of plain color cloth defects detection and sorting technique | |
| CN103914708B (en) | Food kind detection method based on machine vision and system | |
| CN104867144B (en) | IC element welding point defect detection methods based on mixed Gauss model | |
| Rabby et al. | A modified canny edge detection algorithm for fruit detection & classification | |
| CN107610114A (en) | Optical satellite remote sensing image cloud snow mist detection method based on SVMs | |
| CN106991370B (en) | Pedestrian retrieval method based on color and depth | |
| TW201514472A (en) | Method of optical defect detection through image analysis and data mining integrated | |
| CN106951899A (en) | Method for detecting abnormality based on image recognition | |
| CN106501272B (en) | Machine vision soldering tin positioning detection system | |
| CN106651802B (en) | Machine vision scolding tin position finding and detection method | |
| CN107220664B (en) | Oil bottle boxing and counting method based on structured random forest | |
| Dong et al. | Visual UAV detection method with online feature classification | |
| CN104992453A (en) | Target tracking method under complicated background based on extreme learning machine | |
| CN104198497A (en) | Surface defect detection method based on visual saliency map and support vector machine | |
| CN113706490B (en) | Wafer defect detection method | |
| CN106548131A (en) | A kind of workmen's safety helmet real-time detection method based on pedestrian detection | |
| CN110619336B (en) | Goods identification algorithm based on image processing | |
| CN111739003A (en) | Machine vision algorithm for appearance detection | |
| CN107122783A (en) | A kind of assembling connecting piece method for quickly identifying based on Corner Detection | |
| CN111178405A (en) | Similar object identification method fusing multiple neural networks |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |