CN104504375B - A kind of recognition methods of PCB element and device - Google Patents
A kind of recognition methods of PCB element and device Download PDFInfo
- Publication number
- CN104504375B CN104504375B CN201410802195.1A CN201410802195A CN104504375B CN 104504375 B CN104504375 B CN 104504375B CN 201410802195 A CN201410802195 A CN 201410802195A CN 104504375 B CN104504375 B CN 104504375B
- Authority
- CN
- China
- Prior art keywords
- picture
- histogram
- matching
- pcb board
- calibration
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30141—Printed circuit board [PCB]
Abstract
The invention discloses a kind of recognition methods of PCB element and devices, comprising: obtains pcb board picture to be measured；Pcb board picture to be measured is calibrated, calibration picture is obtained；Calibration picture is matched using element template picture, obtains matching area；Extract the tone and saturation infromation of matching area；According to the tone and saturation infromation of matching area, histogram to be detected is generated；Histogram to be detected is matched with standard histogram, obtains recognition result.The accuracy rate that element identification can be improved using technical solution of the present invention, avoids influence of the background color from different brightness to recognition result.
Description
Technical field
The present invention relates to the recognition methods of technical field of optical detection more particularly to a kind of PCB element and devices.
Background technique
In pcb board production process, needs to plug various components on pcb board, after pcb board finished product, need to PCB
Plug-in unit on plate is detected, and wrong plug is occurred to avoid the plug-in unit on pcb board, is inserted leakage or anti-inserted phenomenon.Existing PCB element
Detection with normal view is matched using artificial detection or according to multiple views of pcb board to be measured, to identify pcb board
Whether pin goes wrong.There can be the problems such as recognition efficiency is low, subjectivity is strong using manual identified, and use views registered
Method, the picture to be measured acquired under different intensities of illumination cause very big influence to entire recognition result, and pcb board
Background color can generate serious interference to identification process, and recognition accuracy and stability are low.
Summary of the invention
The embodiment of the present invention proposes recognition methods and the device of a kind of PCB element, can improve the accuracy rate of element identification, keep away
Exempt from influence of the background color from different brightness to recognition result.
On the one hand, the embodiment of the invention provides a kind of recognition methods of PCB element, comprising:
Obtain pcb board picture to be measured；
The pcb board picture to be measured is calibrated, calibration picture is obtained；
The calibration picture is matched using element template picture, obtains matching area；
Extract the tone and saturation infromation of the matching area；
According to the tone and saturation infromation of the matching area, histogram to be detected is generated；
The histogram to be detected is matched with standard histogram, obtains recognition result.
Further, the calibration pcb board picture to be measured, obtains calibration picture, comprising:
Extract the scale invariant feature transitional information of the pcb board picture to be measured；
Match the scale invariant feature transitional information of the pcb board picture to be measured and the Scale invariant of standard pcb board picture
Feature Conversion information obtains the scale invariant feature transitional information of successful match；
According to the scale invariant feature transitional information of the successful match, the pcb board to be measured is calibrated using affine transformation
Picture obtains calibration picture.
Further, described that the calibration picture is matched using element template picture, obtain matching area, comprising:
The image block of sliding and the element template picture same size on the calibration picture；
According to the pixel value of the pixel value of element template picture and described image block, using squared difference formula to the element
Template picture and described image block are matched, and determine that the pixel difference of two squares of the element template picture and described image block is minimum
Region as the matching area.
Further, the tone and saturation infromation for extracting the matching area, comprising:
The matching area is converted into hsv color picture from RGB color picture；
The luminance information of the hsv color picture is filtered, and extracts the tone and saturation degree letter of the hsv color picture
Breath.
Further, described to match the histogram to be detected with standard histogram, obtain recognition result, packet
It includes:
The histogram to be detected is calculated at a distance from standard histogram；
Compare the distance and preset threshold value；
If the distance is less than the threshold value, the recognition result of successful match is obtained；
If the distance is greater than or equal to the threshold value, the unsuccessful recognition result of matching is obtained.
On the other hand, the embodiment of the invention provides a kind of identification devices of PCB element, comprising:
Module is obtained, for obtaining pcb board picture to be measured；
Calibration module obtains calibration picture for calibrating the pcb board picture to be measured；
First matching module obtains matching area for matching the calibration picture using element template picture；
Filtering module is extracted, for extracting the tone and saturation infromation of the matching area；
Histogram generation module generates histogram to be detected for the tone and saturation infromation according to the matching area
Figure；With,
Second matching module obtains recognition result for matching the histogram to be detected with standard histogram.
Further, the calibration module includes:
Feature extraction unit, for extracting the scale invariant feature transitional information of the pcb board picture to be measured；
First matching unit, for matching the scale invariant feature transitional information and standard PCB of the pcb board picture to be measured
The scale invariant feature transitional information of plate picture obtains the scale invariant feature transitional information of successful match；With,
Calibration transfer unit, for the scale invariant feature transitional information according to the successful match, using affine transformation
The picture of the pcb board to be measured is calibrated, calibration picture is obtained.
Further, first matching module includes:
Sliding unit, the image block for sliding and the element template picture same size on the calibration picture；
With,
Second matching unit, for according to the pixel value of element template picture and the pixel value of described image block, using flat
Formula of variance matches the element template picture and described image block, determines the element template picture and described image
The smallest region of the pixel difference of two squares of block is as the matching area.
Further, the extraction filtering module includes:
Converting unit, for the matching area to be converted to hsv color picture from RGB color picture；With,
Filter element is extracted, for filtering the luminance information of the hsv color picture, and extracts the hsv color picture
Tone and saturation infromation.
Further, second matching module includes:
Computing unit, for calculating the histogram to be detected at a distance from standard histogram；
Comparing unit is used for the distance and preset threshold value；With,
Recognition unit, for obtaining successful match when the comparing unit determines that the distance is less than the threshold value
Recognition result, and when the comparing unit determines that the distance is greater than or equal to the threshold value, it is unsuccessful to obtain matching
Recognition result.
As it can be seen that the implementation of the embodiments of the present invention has the following beneficial effects:
A kind of recognition methods of PCB element provided in an embodiment of the present invention, shoots the picture of pcb board to be measured, then school first
It is corresponding to find out the element template picture using the element template picture matching calibration picture in component library for the quasi- pcb board picture
Element is in the corresponding region of pcb board to be measured, then extracts the tone and saturation infromation of matching area, filter background color, generates
Then histogram to be detected matches histogram to be detected with standard histogram, obtain corresponding knowledge according to matching result
Not as a result, to identify the element whether in the corresponding position of the pcb board, if situations such as wrong plug occurs, inserts leakage or is anti-inserted.Phase
Than using manual identified or passing through each view progress element identification of pcb board, technical solution of the present invention energy in the prior art
Recognition efficiency is improved, background information and luminance information are filtered, anti-background interference and anti-illumination condition ability are strong, and identification is quasi-
True property is high.And technical solution of the present invention need to only provide pcb board to be measured, not need additional generation data, and it is dry to production process
It disturbs small, is suitable for all ninsolid color elements, versatility is high.
Detailed description of the invention
Fig. 1 is a kind of flow diagram of embodiment of the recognition methods of PCB element provided by the invention；
Fig. 2 is a kind of structural schematic diagram of embodiment of the identification device of PCB element provided by the invention；
Fig. 3 is a kind of structural schematic diagram of embodiment of calibration module provided by the invention；
Fig. 4 is a kind of structural schematic diagram of embodiment of the first matching module provided by the invention；
Fig. 5 is a kind of structural schematic diagram of the embodiment provided by the invention for extracting filtering module；
Fig. 6 is a kind of structural schematic diagram of embodiment of the second matching module provided by the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Embodiment 1
It is a kind of flow diagram of embodiment of the recognition methods of PCB element provided by the invention referring to Fig. 1, we
Method is suitable for the identification of all ninsolid color elements, method includes the following steps:
Step 101: obtaining pcb board picture to be measured.
In the present embodiment, pcb board to be measured is shot using colour imagery shot, obtains pcb board picture to be measured, the shooting image
Region need to include entire pcb board.
Step 102: the picture of the calibration pcb board to be measured obtains calibration picture.
In the present embodiment, since pcb board is likely to occur the variation of position in shooting process, lead to the picture of shooting
The location of middle pcb board is different with scale.At this moment, the characteristic information and affine transformation of the standard pcb board according to setting are needed,
The picture of shooting is calibrated.The calibration process specifically: extract pcb board picture to be measured and standard pcb board picture respectively
(scale invariant feature converts Scale-invariant feature transform to scale invariant feature transitional information, referred to as
Sift), the scale invariant feature of the scale invariant feature transitional information and standard pcb board picture that match pcb board picture to be measured turns
Information is changed, the scale invariant feature transitional information of successful match is obtained, is finally converted according to the scale invariant feature of successful match
Information calibrates the picture of pcb board to be measured using translating or scaling equiaffine transformation, obtains calibration picture.
In the present embodiment, only need three successful match scale invariant feature transitional information can accurate alignment it is to be measured
PCB picture can be according to the scales of all successful match not if possessing the scale invariant feature transitional information of multiple successful match
Become Feature Conversion information to be matched, reduces calibration error.Wherein, scale invariant feature transitional information can be, but not limited to wrap
It includes: the characteristic informations such as texture information, boundary information or crosspoint.
Step 103: the calibration picture being matched using element template picture, obtains matching area.
In the present embodiment, element template picture is stored in component library, and element is all ninsolid color elements, for example electric
Appearance, resistance etc..In recognition component, region of the element on pcb board need to be matched, the accuracy of identification is improved.
In the present embodiment, an image block identical with element template picture size is needed, is being calibrated by image block
It is slided on picture, matching area is determined according to the difference of two squares of picture block and element template picture, specifically: on calibration picture
Image block is slided, according to the pixel value of the pixel value of element template picture and image block, using squared difference formula to element template
Picture and image block are matched, and determine that the smallest region of the pixel difference of two squares of the element template picture and described image block is made
For the matching area.For example, it is assumed that element template is the picture of a 2*2, and pixel value isEach was slided
The pixel value of image block beThe difference of two squares of that identical element part template picture and image block is
The minimum corresponding image block of the difference of two squares is matched with element template picture as a result, the corresponding region of the image block is to match
Region.
Step 104: extracting the tone and saturation infromation of the matching area.
In the present embodiment, in order to reduce the interference of background colour from different brightness, matching area is turned by RGB color picture
It is changed to hsv color picture.Conversion formula is as follows:
V=max (R, G, B)
S=255S, H=H/2
For pcb board card, research finds that green background noise is to recognition result shadow when H ∈ (50,70), (0,60) S ∈
Sound is larger, therefore filters out the data in the region.And consider filtering background and to the adaptability under different illumination, therefore neglect
The slightly information in the channel brightness (V) filters the luminance information of hsv color picture, and filtered tone (H) and saturation degree is used only
(S) information generates corresponding histogram.
Step 105: according to the tone and saturation infromation of matching area, and the tone of the hsv color picture according to extraction
Histogram to be detected is generated with saturation infromation.
In the present embodiment, the histogram to be detected of generation can be, but not limited to for individual hue histogram, individually
Saturation histogram and mixed tone saturation histogram.The present embodiment using mixed type histogram, for example, one
In a three-dimensional coordinate, X-coordinate is the value range of tone, and Y-coordinate is the value range of saturation degree, and Z coordinate is corresponding number.
Corresponding histogram is generated according to the tone of matching area and saturation infromation.
Step 106: histogram to be detected being matched with standard histogram, obtains recognition result.
In the present embodiment, the histogram of the corresponding standard of the element template, the information comprising tone and saturation degree, directly
The matching of square figure, specifically: histogram to be detected is calculated at a distance from standard histogram, and calculation formula is as follows:
Wherein, H1 is histogram to be detected, and H2 is standard histogram, and distance is d (H1, H2).
According to development test, different threshold value D is defined to different elements, if d (H1, H2) < D, then obtain successful match
Recognition result, illustrate there is element identical with element template picture in matching area；If d (H1, H2) >=D, then acquisition
With unsuccessful recognition result, illustrate that there is no elements identical with element template picture in matching area.User can basis
It is identified above as a result, judge PCB element whether occur insert leakage, anti-inserted or wrong plug situations such as.
Therefore a kind of recognition methods of PCB element provided in an embodiment of the present invention, pcb board to be measured is shot first
Picture, the recalibration pcb board picture find out the element template using the element template picture matching calibration picture in component library
The corresponding element of picture is in the corresponding region of pcb board to be measured, then extracts the tone and saturation infromation of matching area, filter background
Color generates histogram to be detected, then matches histogram to be detected with standard histogram, is obtained according to matching result
Corresponding recognition result, to identify the element whether in the corresponding position of the pcb board, if wrong plug occurs, inserts leakage or anti-inserted
Situations such as.Element identification, skill of the present invention are carried out using manual identified or by each view of pcb board compared with the prior art
Art scheme can improve recognition efficiency, save human cost, be filtered to background information and luminance information, anti-background interference and anti-
Illumination condition ability is strong, and identification accuracy is high.And technical solution of the present invention need to only provide pcb board to be measured, not need additional
Data are generated, it is small to production process interference, it is suitable for all ninsolid color elements, versatility is high.
Embodiment 2
Referring to fig. 2, Fig. 2 is a kind of structural schematic diagram of embodiment of the identification device of PCB element provided by the invention.It should
Device includes: to obtain module 201, calibration module 202, the first matching module 203, extract filtering module 204, histogram generation mould
Block 205 and the second matching module 206.
Module 201 is obtained, for obtaining pcb board picture to be measured.
Calibration module 202 is electrically connected with module 201 is obtained, and for calibrating the pcb board picture to be measured, obtains calibration figure
Piece.
First matching module 203, is electrically connected with calibration module 202, for matching the calibration using element template picture
Picture obtains matching area；
Extract filtering module 204, be electrically connected with the first matching module 203, for extract the tone of the matching area with
Saturation infromation；
Histogram generation module 205 is electrically connected, for the tone according to the matching area with filtering module 204 is extracted
And saturation infromation, generate histogram to be detected.
Second matching module 206, is electrically connected with histogram generation module 205, is used for the histogram to be detected and mark
Quasi- histogram is matched, and recognition result is obtained.
In the present embodiment, show referring to the structure of a kind of embodiment that Fig. 3, Fig. 3 are calibration modules 202 provided by the invention
It is intended to.Calibration module 202 includes: feature extraction unit 2021, the first matching unit 2022 and calibration transfer unit 2023.
Feature extraction unit 2021, for extracting the scale invariant feature transitional information of pcb board picture to be measured.
First matching unit 2022, is electrically connected with feature extraction unit 2021, for matching the scale of pcb board picture to be measured
The scale invariant feature transitional information of invariant features transitional information and standard pcb board picture, obtains the Scale invariant of successful match
Feature Conversion information.
Calibration transfer unit 2023 is electrically connected, for the Scale invariant according to successful match with the first matching unit 2022
Feature Conversion information calibrates the picture of pcb board to be measured using affine transformation, obtains calibration picture.
Referring to fig. 4, Fig. 4 is a kind of structural schematic diagram of embodiment of the first matching module 203 provided by the invention, first
Matching module 203 includes: sliding unit 2031 and the second matching unit 2032.
Sliding unit 2031, the image block for sliding and element template picture same size on calibration picture.
Second matching unit 2032, is electrically connected with sliding unit 2031, for according to the pixel value of element template picture and
The pixel value of image block matches element template picture and image block using squared difference formula, determines the element template
The smallest region of the pixel difference of two squares of picture and described image block is as the matching area.
It is a kind of structural schematic diagram of the embodiment provided by the invention for extracting filtering module 204 referring to Fig. 5, Fig. 5.It extracts
Filtering module includes: converting unit 2041 and extraction filter element 2042.
Converting unit 2041, for matching area to be converted to hsv color picture from RGB color picture.
Filter element 2042 is extracted, is electrically connected with converting unit 2041, for filtering the luminance information of hsv color picture,
And extract the tone and saturation infromation of hsv color picture.
It is a kind of structural schematic diagram of embodiment of the second matching module 206 provided by the invention referring to Fig. 6, Fig. 6.Second
Matching module 206 includes: computing unit 2061, comparing unit 2062 and recognition unit 2063.
Computing unit 2061, for calculating histogram to be detected at a distance from standard histogram.
Comparing unit 2062 is electrically connected with computing unit 2061, for comparing the distance and preset threshold value；,
Recognition unit 2063 is electrically connected with comparing unit 2062, for determining that the distance is less than threshold in comparing unit 2062
When value, the recognition result of successful match is obtained, and when comparing unit 2062 determines that the distance is greater than or equal to threshold value, obtain
Match unsuccessful recognition result.
The more detailed implementing procedure of the present embodiment and working principle can be, but not limited to referring to correlation documented by embodiment 1
Content.
Therefore the identification device of PCB element provided in this embodiment, first acquisition module 201 obtain pcb board to be measured
Picture, calibration module 202 calibrate the pcb board picture, and the first matching module 203 is using the element template picture matching in component library
Picture is calibrated, finds out the corresponding element of element template picture in the corresponding region of pcb board to be measured, then by extraction filtering module
204 extract the tone and saturation infromation of matching area, and filter background color, then histogram generation module 205 is according to tone
And saturation infromation, generate histogram to be detected, the second last matching module 206 by histogram to be detected and standard histogram into
Row matching obtains corresponding recognition result according to matching result, with identify the element whether in the corresponding position of the pcb board,
Situations such as wrong plug whether occurs, inserts leakage or is anti-inserted.Manual identified or each view by pcb board are used compared with the prior art
Figure carries out element identification, and technical solution of the present invention can improve recognition efficiency, be filtered to background information and luminance information, anti-back
Scape interference and anti-illumination condition ability are strong, and identification accuracy is high.And technical solution of the present invention need to only provide pcb board to be measured, no
Additional generation data are needed, it is small to production process interference, it is suitable for all ninsolid color elements, versatility is high.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the program can be stored in a computer-readable storage medium
In, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, the storage medium can be magnetic
Dish, CD, read-only memory (Read-Only Memory, ROM) or random access memory (Random Access
Memory, RAM) etc..
The above is a preferred embodiment of the present invention, it is noted that for those skilled in the art
For, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also considered as
Protection scope of the present invention.
Claims (6)
1. a kind of recognition methods of PCB element characterized by comprising
Obtain pcb board picture to be measured；
The pcb board picture to be measured is calibrated, calibration picture is obtained；
The calibration picture is matched using element template picture, obtains matching area；
Extract the tone and saturation infromation of the matching area；The tone and saturation infromation for extracting the matching area
Matching area is specially converted into hsv color picture by RGB color image, and the luminance information for filtering hsv color picture comes
Obtain the tone and saturation infromation of the matching area；
According to the tone and saturation infromation of the matching area, histogram to be detected is generated；It is described according to the matching area
Tone and saturation infromation, generating histogram to be detected is specially the tone of the matching area for being used only and obtaining after filtering
Histogram to be detected is generated with saturation infromation；
The histogram to be detected is matched with standard histogram, obtains recognition result；
Wherein, according to formulaCalculate the histogram to be detected and standard straight
The distance of square figure, H1 are histogram to be detected, and H2 is standard histogram, and distance is d (H1, H2)；
Compare the distance and preset threshold value；
If the distance is less than the threshold value, the recognition result of successful match is obtained；
If the distance is greater than or equal to the threshold value, the unsuccessful recognition result of matching is obtained.
2. the recognition methods of PCB element according to claim 1, which is characterized in that the calibration pcb board figure to be measured
Piece obtains calibration picture, comprising:
Extract the scale invariant feature transitional information of the pcb board picture to be measured；
The scale invariant feature of the scale invariant feature transitional information of the pcb board picture to be measured and standard pcb board picture is turned
It changes information to be matched, obtains the scale invariant feature transitional information of successful match；
According to the scale invariant feature transitional information of the successful match, the pcb board picture to be measured is calibrated using affine transformation,
Obtain calibration picture.
3. the recognition methods of PCB element according to claim 1, which is characterized in that described to use element template picture
With the calibration picture, matching area is obtained, comprising:
The image block of sliding and the element template picture same size on the calibration picture；
According to the pixel value of the pixel value of element template picture and described image block, using squared difference formula to the element template
Picture and described image block are matched, and determine the smallest area of the pixel difference of two squares of the element template picture Yu described image block
Domain is as the matching area.
4. a kind of identification device of PCB element characterized by comprising
Module is obtained, for obtaining pcb board picture to be measured；
Calibration module obtains calibration picture for calibrating the pcb board picture to be measured；
First matching module obtains matching area for matching the calibration picture using element template picture；
Filtering module is extracted, for extracting the tone and saturation infromation of the matching area；It is described to extract the matching area
Tone and saturation infromation be specially matching area to be converted into hsv color picture by RGB color image, and filter HSV face
The luminance information of chromatic graph piece obtains the tone and saturation infromation of the matching area；
Histogram generation module generates histogram to be detected for the tone and saturation infromation according to the matching area；Institute
The tone and saturation infromation according to the matching area are stated, generating histogram to be detected is specially to obtain after filtering is used only
The tone and saturation infromation of the matching area generates histogram to be detected；With,
Second matching module obtains recognition result for matching the histogram to be detected with standard histogram；
Wherein, second matching module includes:
Computing unit, for according to calculation formula
The histogram to be detected is calculated at a distance from standard histogram, H1 is histogram to be detected, and H2 is standard histogram, away from
From for d (H1, H2)；
Comparing unit is used for the distance and preset threshold value；With,
Recognition unit, for obtaining the identification of successful match when the comparing unit determines that the distance is less than the threshold value
As a result, and when the comparing unit determines that the distance is greater than or equal to the threshold value, obtaining and matching unsuccessful identification
As a result.
5. the identification device of PCB element according to claim 4, which is characterized in that the calibration module includes:
Feature extraction unit, for extracting the scale invariant feature transitional information of the pcb board picture to be measured；
First matching unit, for matching the scale invariant feature transitional information and standard pcb board figure of the pcb board picture to be measured
The scale invariant feature transitional information of piece obtains the scale invariant feature transitional information of successful match；With,
Calibration transfer unit is calibrated for the scale invariant feature transitional information according to the successful match using affine transformation
The picture of the pcb board to be measured obtains calibration picture.
6. the identification device of PCB element according to claim 4, which is characterized in that first matching module includes:
Sliding unit, the image block for sliding and the element template picture same size on the calibration picture；With,
Second matching unit, for according to the pixel value of element template picture and the pixel value of described image block, using the difference of two squares
Formula matches the element template picture and described image block, determines the element template picture and described image block
The smallest region of the pixel difference of two squares is as the matching area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410802195.1A CN104504375B (en) | 2014-12-18 | 2014-12-18 | A kind of recognition methods of PCB element and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410802195.1A CN104504375B (en) | 2014-12-18 | 2014-12-18 | A kind of recognition methods of PCB element and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104504375A CN104504375A (en) | 2015-04-08 |
| CN104504375B true CN104504375B (en) | 2019-03-05 |
Family
ID=52945771
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410802195.1A Active CN104504375B (en) | 2014-12-18 | 2014-12-18 | A kind of recognition methods of PCB element and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104504375B (en) |
Families Citing this family (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104923494A (en) * | 2015-06-30 | 2015-09-23 | 歌尔声学股份有限公司 | Method and system for automatically distinguishing qualified products from electronic components on large scale |
| CN105389818B (en) * | 2015-11-12 | 2018-11-27 | 广州视源电子科技股份有限公司 | The localization method and system of element |
| CN105550081A (en) * | 2015-12-07 | 2016-05-04 | 广州视源电子科技股份有限公司 | Board card error display method and system |
| CN105551033B (en) * | 2015-12-09 | 2019-11-26 | 广州视源电子科技股份有限公司 | Component labelling mthods, systems and devices |
| CN105469085B (en) * | 2015-12-23 | 2019-03-26 | 广州视源电子科技股份有限公司 | Board image acquiring method and system |
| EP3472599B1 (en) * | 2016-04-04 | 2022-06-01 | Soreq Nuclear Research Center | A method and a system for xrf marking and reading xrf marks of electronic systems |
| CN105976354B (en) * | 2016-04-14 | 2019-02-01 | 广州视源电子科技股份有限公司 | Element localization method and system based on color and gradient |
| CN105957065A (en) * | 2016-04-21 | 2016-09-21 | 广州视源电子科技股份有限公司 | Method and system for detecting omitted elements |
| CN106548200A (en) * | 2016-10-31 | 2017-03-29 | 黄建文 | A kind of image comparison system and method |
| CN106651802B (en) * | 2016-12-24 | 2019-10-18 | 大连日佳电子有限公司 | Machine vision scolding tin position finding and detection method |
| CN108254380B (en) * | 2018-01-03 | 2023-02-10 | 浙江涵普电力科技有限公司 | PCB template comparison method based on digital image processing |
| CN108333190A (en) * | 2018-04-19 | 2018-07-27 | 东莞市郝视智能科技有限公司 | A kind of stokehold plug-in unit Quality Detection equipment and its control method |
| CN109222964B (en) * | 2018-07-20 | 2021-02-09 | 广州视源电子科技股份有限公司 | Atrial fibrillation detection apparatus and storage medium |
| CN109711414A (en) * | 2018-12-19 | 2019-05-03 | 国网四川省电力公司信息通信公司 | Equipment indicating lamp color identification method and system based on camera image acquisition |
| CN109961447B (en) * | 2019-03-29 | 2021-02-19 | 京东方科技集团股份有限公司 | Price tag detection method and device, electronic equipment and storage medium |
| CN110674863B (en) * | 2019-09-19 | 2022-06-21 | 北京迈格威科技有限公司 | Hamming code identification method and device and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6122391A (en) * | 1994-08-18 | 2000-09-19 | Autodesk, Inc. | Spectrally coordinated pattern search-imaging system and method |
| CN102662949A (en) * | 2012-02-27 | 2012-09-12 | 安科智慧城市技术（中国）有限公司 | Method and system for retrieving specified object based on multi-feature fusion |
| CN102937595A (en) * | 2012-11-13 | 2013-02-20 | 浙江省电力公司电力科学研究院 | Method, device and system for detecting printed circuit board (PCB) |
-
2014
- 2014-12-18 CN CN201410802195.1A patent/CN104504375B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6122391A (en) * | 1994-08-18 | 2000-09-19 | Autodesk, Inc. | Spectrally coordinated pattern search-imaging system and method |
| CN102662949A (en) * | 2012-02-27 | 2012-09-12 | 安科智慧城市技术（中国）有限公司 | Method and system for retrieving specified object based on multi-feature fusion |
| CN102937595A (en) * | 2012-11-13 | 2013-02-20 | 浙江省电力公司电力科学研究院 | Method, device and system for detecting printed circuit board (PCB) |
Non-Patent Citations (1)
| Title |
|---|
| 印制电路板光学检测算法研究;苏国松;《中国优秀硕士学位论文全文数据库 信息科技辑》;20100115;第7-52页 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104504375A (en) | 2015-04-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104504375B (en) | A kind of recognition methods of PCB element and device | |
| Tang et al. | A novel feature descriptor invariant to complex brightness changes | |
| CN106548462B (en) | Non-linear SAR image geometric correction method based on thin-plate spline interpolation | |
| CN107729875A (en) | Three-dimensional face identification method and device | |
| CN109118528A (en) | Singular value decomposition image matching algorithm based on area dividing | |
| CN108647264B (en) | Automatic image annotation method and device based on support vector machine | |
| CN108960344A (en) | Difference detecting method, device and the terminal device of cultural relic images | |
| CN105894520B (en) | A kind of automatic cloud detection method of optic of satellite image based on gauss hybrid models | |
| Kagarlitsky et al. | Piecewise-consistent color mappings of images acquired under various conditions | |
| CN104914105A (en) | Tea leaf grade identification method based on image recognition technology | |
| CN109447062A (en) | Pointer-type gauges recognition methods based on crusing robot | |
| Lu et al. | Color constancy using 3D scene geometry | |
| CN109587466A (en) | The method and apparatus of colored shadow correction | |
| CN103714544B (en) | A kind of optimization method based on SIFT feature Point matching | |
| Adjeroh et al. | On ratio-based color indexing | |
| CN110321869A (en) | Personnel's detection and extracting method based on Multiscale Fusion network | |
| CN109816782A (en) | A kind of indoor scene three-dimensional rebuilding method based on binocular vision | |
| Lankinen et al. | A comparison of local feature detectors and descriptors for visual object categorization by intra-class repeatability and matching | |
| CN109035199A (en) | High-spectral data end member extraction method, computer readable storage medium, electronic equipment based on space characteristics | |
| CN112329654B (en) | Hyperspectral image data classification method and system based on multi-manifold learning algorithm | |
| CN110909696B (en) | Scene detection method and device, storage medium and terminal equipment | |
| CN113807320A (en) | Human body skin color identification method and system based on multispectral imaging technology | |
| CN110222688A (en) | A kind of instrument localization method based on multi-level correlation filtering | |
| Huang et al. | Multi-color space threshold segmentation and self-learning k-NN algorithm for surge test EUT status identification | |
| Zhang et al. | Features Extraction and Matching of Binocular Image Based on SIFT Algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |