CN105513046B - The polar recognition methods of electronic component and system, mask method and system - Google Patents
The polar recognition methods of electronic component and system, mask method and system Download PDFInfo
- Publication number
- CN105513046B CN105513046B CN201510822818.6A CN201510822818A CN105513046B CN 105513046 B CN105513046 B CN 105513046B CN 201510822818 A CN201510822818 A CN 201510822818A CN 105513046 B CN105513046 B CN 105513046B
- Authority
- CN
- China
- Prior art keywords
- electronic component
- polar orientation
- training
- convolutional neural
- neural networks
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
Abstract
The present invention relates to a kind of recognition methods of electronic component polar orientation and systems, mask method and system.Present electronic component polar orientation judging nicety rate is lower, limited scalability.The present invention is first to obtain the image comprising electronic component, convolutional neural networks after recycling training make forward calculation to it, obtain the probability distribution of the polar orientation classification of electronic component, select the polar orientation classification of wherein maximum probability as the polar orientation classification of electronic component, due to having used convolutional neural networks, it can automatically and accurately identify the polar orientation of electronic component, and not for specific electronic component structure, suitable for the polar electronic component of various bands, realize the polar orientation identification of the electronic component across classification, applicability is wider.According to the polar orientation of determining target electronic components, board-like production can be applied to, carrying out polar orientation mark to electronic component improves the efficiency and accuracy of board-like production to promote the automatization level of board-like production.
Description
Technical field
The present invention relates to automatic optics inspection fields, more particularly to a kind of polar recognition methods of electronic component and are
System, mask method and system.
Background technique
Currently, needing carrying out polar orientation judgement to electronic component thereon for pcb board.Now for electronics member
The judgement of part polar orientation, there are mainly two types of methods: first is that the polar orientation based on component structure feature judges that this method is base
It in specific component structure feature, is usually designed just for certain class component, applicability is limited, in addition, part-structure feature is not
It is unstable with (such as illumination is different, shooting angle is different, noise jamming) under environment, cause judging nicety rate lower;Second is that base
Judge in the polar orientation of positive and negative template matching, as long as all setting a template for every kind of element, but in this way may be because more
Class template is mixed and accuracy rate is caused to reduce, as long as and element appearance is slightly different must introduce new template, it is expansible
Property it is limited, calculating the time can also increase because of the increase of template library.
Summary of the invention
Based on this, it is necessary to for the problem that electronic component polar orientation judging nicety rate is low, applicability is limited, provide one
The recognition methods and system, mask method and system of kind electronic component polar orientation.
A kind of recognition methods of electronic component polar orientation, comprising the following steps:
Obtain the image comprising target electronic components;
Forward calculation is made to image using the convolutional neural networks after training, obtains target electronic components and belongs to each electron-like
The probability distribution of the various polar orientation classifications of element;
Choose polar orientation classification of the polar orientation classification of maximum probability as target electronic components.
It is first to obtain the image including electronic component according to above-mentioned recognition methods, the convolutional Neural after recycling training
Network makees forward calculation to it, obtains the probability distribution of the polar orientation classification of electronic component, selects the pole of wherein maximum probability
Property polar orientation classification of the direction classification as electronic component, used convolutional neural networks in this scheme, can automatically precisely
Ground identifies the polar orientation of electronic component, and not for specific electronic component structure, is suitable for the polar electricity of various bands
Subcomponent, realizes the polar orientation identification of the electronic component across classification, and applicability is wider.
In one of the embodiments, after the step of obtaining includes the image of target electronic components, including following step
It is rapid:
The Prototype drawing for obtaining target electronic components, with the Prototype drawing of target electronic components to the target electronic components in image
It is matched, obtains the exact position of the target electronic components in image, according to exact position to the target electronic member in image
Part is adjusted, and so that the target electronic components in image is located at the center of image, image adjusted is for the convolution mind after training
Make forward calculation through network.
Convolutional neural networks after training in one of the embodiments, are obtained by following steps:
Establish the image pattern collection of the various polar orientations of all kinds of electronic components;
By preset external data collection pre-training convolutional neural networks, wherein external data collection includes the more of multiple classifications
Open the natural image marked in advance;
According to image pattern collection, the convolutional neural networks after pre-training are adjusted and made with further training, is instructed
Convolutional neural networks after white silk.
The step of establishing the sample set of the various polar orientations of all kinds of electronic components in one of the embodiments, include with
Lower step:
Pcb board card graphic and PCB Prototype drawing are obtained, and is reference with PCB Prototype drawing, position is carried out to pcb board card graphic
Registration;
All kinds of electronic component images after interception position registration on pcb board card graphic, with each electron-like in PCB Prototype drawing
Element matches electronic component corresponding in all kinds of electronic component images, obtains corresponding electronics in all kinds of electronic component images
The exact position of element is adjusted corresponding electronic element according to the exact position of corresponding electronic element, makes corresponding electronics member
Part is located at the center of all kinds of electronic component images, obtains the image pattern collection of the various polar orientations of all kinds of electronic components.
In one of the embodiments, by the step of preset external data collection pre-training convolutional neural networks include with
Lower step:
Pre-training is carried out to convolutional neural networks with external data collection, convolutional neural networks is made to learn the standard drawing of each level
As feature, the initial parameter value of the convolutional neural networks after obtaining pre-training.
In one of the embodiments, according to image pattern collection, the convolutional neural networks after pre-training are adjusted simultaneously
Make further trained step the following steps are included:
According to image pattern collection, by the last layer number of nodes of the convolutional neural networks after the pre-training in initial parameter value
It is adjusted to the classification number of the various polar orientations of various electronic components, and further instruction is made to convolutional neural networks adjusted
Practice.
A kind of mask method of electronic component polar orientation, comprising the following steps:
According to the polar orientation for the target electronic components that the recognition methods of above-mentioned electronic component polar orientation determines, board-like
The polar orientation information of label target electronic component in file, board-like file are used to save the various attribute informations of electronic component.
The mask method of above-mentioned electronic component polar orientation can be applied to the board-like production of AOI, automatically, accurately to PCB
Element on board, which carries out polar orientation mark, improves the efficiency of board-like production to promote the automatization level of board-like production
With accuracy.
A kind of identifying system of electronic component polar orientation, including with lower unit:
Acquiring unit, for obtaining the image comprising target electronic components;
Computing unit obtains target electronic member for making forward calculation to image using the convolutional neural networks after training
Part belongs to the probability distribution of the various polar orientation classifications of all kinds of electronic components;
Selection unit, for choosing polar orientation class of the polar orientation classification as target electronic components of maximum probability
Not.
It is first to obtain the image including electronic component according to above-mentioned identifying system, the convolutional Neural after recycling training
Network makees forward calculation to it, obtains the probability distribution of the polar orientation classification of electronic component, selects the pole of wherein maximum probability
Property polar orientation classification of the direction classification as electronic component, used convolutional neural networks in this scheme, can automatically precisely
Ground identifies the polar orientation of electronic component, and not for specific electronic component structure, is suitable for the polar electricity of various bands
Subcomponent, realizes the polar orientation identification of the electronic component across classification, and applicability is wider.
The identifying system of electronic component polar orientation further includes establishing unit, pre-training list in one of the embodiments,
Member and adjustment unit;
Establish the image pattern collection of various polar orientations of the unit for establishing all kinds of electronic components;
Pre-training unit is used for through preset external data collection pre-training convolutional neural networks, wherein external data Ji Bao
Multiple natural images marked in advance containing multiple classifications;
Adjustment unit is used to be adjusted the convolutional neural networks after pre-training according to image pattern collection and make further
Training, the convolutional neural networks after being trained.
A kind of labeling system of electronic component polar orientation, the knowledge including marking unit and above-mentioned electronic component polar orientation
Other system, wherein polar orientation information of the mark unit for the label target electronic component in board-like file, board-like file are used
In the various attribute informations for saving electronic component.
The labeling system of above-mentioned electronic component polar orientation can be applied to the board-like production of AOI, automatically, accurately to PCB
Element on board, which carries out polar orientation mark, improves the efficiency of board-like production to promote the automatization level of board-like production
With accuracy.
Detailed description of the invention
Fig. 1 is the flow diagram of the recognition methods of electronic component polar orientation in one embodiment;
Fig. 2 is the part flow diagram of the recognition methods of electronic component polar orientation in one embodiment;
Fig. 3 is the structural schematic diagram of the identifying system of electronic component polar orientation in one embodiment;
Fig. 4 is the structural schematic diagram of the identifying system of electronic component polar orientation in one embodiment;
Fig. 5 is the structural schematic diagram of the identifying system of electronic component polar orientation in one embodiment;
Fig. 6 is the partial structure diagram of the identifying system of electronic component polar orientation in one embodiment;
Fig. 7 is the structural schematic diagram of the identifying system of electronic component polar orientation in one embodiment;
Fig. 8 is the structural schematic diagram of the labeling system of electronic component polar orientation in one embodiment.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention more comprehensible, with reference to the accompanying drawings and embodiments, to this
Invention is described in further detail.It should be appreciated that the specific embodiments described herein are only used to explain the present invention,
And the scope of protection of the present invention is not limited.
It is shown in Figure 1, it is the recognition methods embodiment of electronic component polar orientation of the invention.As shown in Figure 1, the reality
Apply the recognition methods of the electronic component polar orientation in example the following steps are included:
Step S101: the image comprising target electronic components is obtained;
In this step, the image comprising electronic component, which can be, needs to identify the polar pcb board card graphic of electronic component,
It is also possible to other and needs to identify the polar image of electronic component.
Step S102: forward calculation is made to image using the convolutional neural networks after training, obtains target electronic components category
In the probability distribution of the various polar orientation classifications of all kinds of electronic components;
In this step, various polar orientation classifications refer to the various polar orientations of various electronic components, include a variety of
Electronic component, the probability distribution of acquisition can be adapted for various electronic components;Convolutional neural networks after training can be to image
It is operated, the polar orientation of target electronic components therein is identified, obtain probability distribution.
Step S103: polar orientation classification of the polar orientation classification as target electronic components of maximum probability is chosen;
Above-mentioned steps S101, S102 and S103 are the processes that on-line testing is carried out using the convolutional neural networks after training.
The recognition methods of electronic component polar orientation described in present embodiment is first obtained comprising target electronic components
Image, the convolutional neural networks after recycling training make forward calculation to it, obtain target electronic components and belong to each electron-like member
The probability distribution of the various polar orientation classifications of part, selects the polar orientation classification of wherein maximum probability as target electronic components
Polar orientation classification, used convolutional neural networks in this scheme, can automatically and accurately identify the polarity side of electronic component
To, and not for specific electronic component structure, it is suitable for the polar electronic component of various bands, realizes the electronics across classification
The polar orientation of element identifies that applicability is wider.
In one of the embodiments, after the step of obtaining includes the image of target electronic components, including following step
It is rapid:
The Prototype drawing for obtaining target electronic components, with the Prototype drawing of target electronic components to the target electronic components in image
It is matched, obtains the exact position of the target electronic components in image, according to exact position to the target electronic member in image
Part is adjusted, and target electronic components is made to be located at the center of image.
The target electronic components in image are adjusted with the Prototype drawing of target electronic components, so that the convolution after training
Neural network is more easier to identify target electronic components.
Convolutional neural networks are trained in disconnection mode in one of the embodiments, as shown in Fig. 2, step is such as
Under:
Step S104: the image pattern collection of the various polar orientations of all kinds of electronic components is established;
Step S105: by preset external data collection pre-training convolutional neural networks, wherein external data collection includes more
Multiple natural images marked in advance of a classification;
Step S106: according to image pattern collection, the convolutional neural networks after pre-training is adjusted and are further instructed
Practice, the convolutional neural networks after being trained.
Off-line training can be carried out to convolutional neural networks through the above steps, electronic component in image can be handled
Polar orientation information, so as in on-line testing use the training after convolutional neural networks.
In one of the embodiments, step S104 the following steps are included:
Pcb board card graphic and PCB Prototype drawing are obtained, and is reference with PCB Prototype drawing, position is carried out to pcb board card graphic
Registration;
All kinds of electronic component images after interception position registration on pcb board card graphic, with each electron-like in PCB Prototype drawing
Element matches electronic component corresponding in all kinds of electronic component images, obtains corresponding electronics in all kinds of electronic component images
The exact position of element is adjusted corresponding electronic element according to the exact position of corresponding electronic element, makes corresponding electronics member
Part is located at the center of all kinds of electronic component images, obtains the image pattern collection of the various polar orientations of all kinds of electronic components.
The image pattern collection obtained through the above way is directly intercepted from pcb board card graphic, is all practical electricity
The image of subcomponent, with more directiveness.
Preferably, camera, and the pcb board card figure of batch capture different model can be set up on pcb board card production line
Picture, and avoid repeating to shoot a certain pcb board card with board tracking technique, the pcb board card of every kind in this way model includes multiple
Image pattern, each image pattern correspond to certain pcb board card of a certain model;It needs to save phase when acquiring pcb board card graphic
The PCB Prototype drawing answered;
Pcb board card graphic position in multiple images sample may deviate, need using the PCB Prototype drawing of respective model as
With reference to the progress image registration of each image pattern, and using the positions of electronic parts information of the model pcb board card (from plate
Formula file or artificial mark) electronic component picture is intercepted automatically, and board-like file or people (are come from according to electronic component classification information
Work mark) automatic marking is carried out to electronic component picture;
The exact position of electronic component in image pattern is further acquired with the electronic component matching in PCB Prototype drawing, it is right
Electronic component image carries out alignment adjustment, to guarantee that electronic component is located at image center location, obtains the various poles of electronic component
The image pattern collection in property direction.
In one of the embodiments, step S105 the following steps are included:
Pre-training is carried out to convolutional neural networks with external data collection, convolutional neural networks is made to learn the standard drawing of each level
As feature, the initial parameter value of the convolutional neural networks after obtaining pre-training.
Preferably, pre-training is used for using ImageNet data set as external data collection.
Currently, the recognition methods of existing electronic component polar orientation often utilize be electronic component colouring information etc.
Low layer pictures feature, this conventional method are all too simple for many application scenarios, and robustness is lower, the scope of application also by
Limit, effect are poor;And convolutional neural networks study multilayer feature representation (including low layer, middle layer, high level are used in this programme
Characteristics of image, rather than just low layer pictures feature), and comprehensive such multilayer feature goes identification electronic component polar orientation,
To greatly promote accuracy of identification, the scope of application is also extended.
In actual scene, the image pattern collection of the various polar orientations of all kinds of electronic components of foundation is relative to expression energy
It is still less for the stronger convolutional neural networks of power.Therefore, the present invention quotes this external data collection pre-training of ImageNet
Convolutional neural networks, although ImageNet data set is not electronic component data collection, it includes more than 22000 classifications
15000000 natural images with mark, can learn the general image feature of each level out for pre-training, preferably be rolled up
Product neural network initial parameter value.
The ability to express of convolutional neural networks is very strong, can effectively solve the problems, such as that the precision in more classification tasks is not high,
Even if also can reach very high accuracy rate in the electronic component polar orientation identification mission across classification.
In one of the embodiments, step S106 the following steps are included:
According to image pattern collection, by the last layer number of nodes of the convolutional neural networks after the pre-training in initial parameter value
It is adjusted to the classification number of the various polar orientations of various electronic components, and further instruction is made to convolutional neural networks adjusted
Practice.
Preferably, the convolutional neural networks being adjusted are similar with unadjusted convolutional neural networks structure, and difference exists
It is originally 1000 nodes in the last layer, it is assumed that the total N class of the various polar orientations of all electronic components, then existing by the layer
It is changed to N number of node.
The step is directed to obtained image pattern collection, is based on the obtained convolutional neural networks initial parameter of previous step
Value, adjusts the last layer number of nodes of convolutional neural networks, and according to image pattern collection, using transfer learning strategy, to adjustment
Convolutional neural networks afterwards make further training, the convolutional neural networks after being trained.
Choosing polarity of the polar orientation classification of maximum probability as the electronic component in one of the embodiments,
It is further comprising the steps of after the step of direction classification:
If the polar orientation classification for the maximum probability chosen is different from preset electronic component polar orientation classification, provide
False alarm information.
Above-mentioned steps are the detection process to polar orientation, can correctly be judged whether electronic component is installed.
The image comprising target electronic components that on-line testing obtains in one of the embodiments, is pcb board card graphic,
With corresponding PCB template come compare matching, obtain the exact position of target electronic components, to the target electronic components in image into
Row alignment adjustment, to guarantee that target electronic components are located at the center of image.
In the present embodiment, corresponding PCB template is used when control matching, which can be image sample
Concentrate the corresponding PCB template of image, be also possible to from the image sample PCB template that concentrate the corresponding PCB template of image different, such as
Fruit is for the former, PCB template corresponding with image sample concentration image has been saved in off-line training, can directly acquire makes
With.If it is the latter, in addition to also needing to obtain corresponding PCB template from the external world when obtaining pcb board card graphic when on-line testing, with
Control matching after realization.Polarity can be carried out to all electronic components in the pcb board card graphic of acquisition by implementing this programme
The identification in direction.
In one of the embodiments, step S101 and step S104 the following steps are included:
The size of image adjusted is normalized.
In step s101, it after being normalized, can be handled convenient for forward calculation of the convolutional neural networks to image,
Accelerate the identification process of electronic component.
In step S104, after being normalized, convolution can be made convenient for the further training to convolutional neural networks
Neural network is more accurate to the study of the multilayer feature of image pattern.
The recognition methods of electronic component polar orientation of the invention, has used convolutional neural networks, can be automatically and accurately
It identifies the polar orientation of electronic component, and not for specific electronic component structure, is suitable for the polar electronics of various bands
Element, as long as the image pattern collection of training convolutional neural networks covers the electronic component of multiple types, so that it may realize across
The polar orientation of the electronic component of classification identifies that applicability is wider;Either off-line training step or on-line testing stage,
Manual intervention is reduced as far as possible, and independent of special hardware mechanism, cost is relatively low;Due to reference external data collection and use
Transfer learning strategy, the bright implementation of we do not need the image pattern for collecting the electronic component polar orientation of magnanimity in advance, because
This is also applied for electronic component image pattern and obtains under more difficult scene.
The present invention also provides a kind of mask methods of electronic component polar orientation, comprising the following steps:
According to the polar orientation for the target electronic components that the recognition methods of above-mentioned electronic component polar orientation determines, board-like
The polar orientation information of label target electronic component in file, board-like file are used to save the various attribute informations of electronic component.
The mask method of above-mentioned electronic component polar orientation can be applied to the board-like production of AOI, automatically, accurately to PCB
Element on board, which carries out polar orientation mark, improves the efficiency of board-like production to promote the automatization level of board-like production
With accuracy.
According to the recognition methods of above-mentioned electronic component polar orientation, the present invention also provides a kind of electronic component polar orientations
Identifying system, just the embodiment of the identifying system of electronic component polar orientation of the invention is described in detail below.
It is shown in Figure 3, it is the embodiment of the identifying system of electronic component polar orientation of the invention.In the embodiment
The identifying system of electronic component polar orientation, including the acquiring unit 200 in Fig. 3, computing unit 210, selection unit 220;
Acquiring unit 200, for obtaining the image comprising target electronic components;
Computing unit 210 obtains target electronic for making forward calculation to image using the convolutional neural networks after training
Element belongs to the probability distribution of the various polar orientation classifications of all kinds of electronic components;
Selection unit 220, for choosing polar orientation of the polar orientation classification of maximum probability as target electronic components
Classification.
In one of the embodiments, as shown in figure 4, the identifying system of electronic component polar orientation further includes that pretreatment is single
Member 230;
Pretreatment unit 230 is used for after acquiring unit obtains the image comprising target electronic components, obtains target electronic
The Prototype drawing of element matches the target electronic components in image with the Prototype drawing of target electronic components, obtains in image
Target electronic components exact position, the target electronic components in image are adjusted according to exact position, are made in image
Target electronic components be located at the center of image, image adjusted makees forward calculation for the convolutional neural networks after training.
In one of the embodiments, as shown in figure 5, the identifying system of electronic component polar orientation further includes establishing unit
240, pre-training unit 250 and adjustment unit 260;
Establish the image pattern collection of various polar orientations of the unit 240 for establishing all kinds of electronic components;
Pre-training unit 250 is used for through preset external data collection pre-training convolutional neural networks, wherein external data
Collection includes multiple natural images marked in advance of multiple classifications;
Adjustment unit 260 be used for according to image pattern collection, the convolutional neural networks after pre-training are adjusted and make into
The training of one step, the convolutional neural networks after being trained.
In one of the embodiments, as shown in fig. 6, establishing unit 240 includes registration unit 241, intercepting process unit
242;
Registration unit 241 is reference for obtaining pcb board card graphic and PCB Prototype drawing, and with PCB Prototype drawing, to pcb board
Card graphic carries out position registration;
Electronic component image of the intercepting process unit 242 on pcb board card graphic after interception position registration, with PCB mould
All kinds of electronic components in plate figure match electronic component corresponding in all kinds of electronic component images, obtain each electron-like member
The exact position of corresponding electronic element in part image, adjusts corresponding electronic element according to the exact position of corresponding electronic element
It is whole, so that corresponding electronic element is located at the center of all kinds of electronic component images, obtains the various polar orientations of all kinds of electronic components
Image pattern collection.
Pre-training unit 250 is for carrying out in advance convolutional neural networks with external data collection in one of the embodiments,
Training makes convolutional neural networks learn the general image feature of each level, the convolutional neural networks after obtaining pre-training it is initial
Parameter value.
Adjustment unit 260 is used for according to image pattern collection, by the pre- instruction in initial parameter value in one of the embodiments,
The last layer number of nodes of convolutional neural networks after white silk is adjusted to the classification number of the various polar orientations of various electronic components, and
Further training is made to convolutional neural networks adjusted.
In one of the embodiments, as shown in fig. 7, the identifying system of electronic component polar orientation further includes alarm unit
270, if the polar orientation classification of the maximum probability for selection is different from preset electronic component polar orientation classification, provide
False alarm information.
The identification side of the identifying system of electronic component polar orientation of the invention and electronic component polar orientation of the invention
Method corresponds, in the technical characteristic and its advantages of the embodiment elaboration of the recognition methods of above-mentioned electronic component polar orientation
Suitable for the embodiment of the identifying system of electronic component polar orientation.
The present invention also provides a kind of labeling systems of electronic component polar orientation, as shown in figure 8, including mark unit 280
And the identifying system of above-mentioned electronic component polar orientation, mark unit 280 are used for according to above-mentioned electronic component polar orientation
Recognition methods determine target electronic components polar orientation, in board-like file mark electronic component polar orientation letter
Breath, board-like file are used to save the various attribute informations of electronic component.
The labeling system of above-mentioned electronic component polar orientation can be applied to the board-like production of AOI, automatically, accurately to PCB
Element on board, which carries out polar orientation mark, improves the efficiency of board-like production to promote the automatization level of board-like production
With accuracy.
Each technical characteristic of embodiment described above can be combined arbitrarily, for simplicity of description, not to above-mentioned reality
It applies all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, all should be considered as described in this specification.
The embodiments described above only express several embodiments of the present invention, and the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to protection of the invention
Range.Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.
Claims (10)
1. a kind of recognition methods of electronic component polar orientation, which comprises the following steps:
Obtain the image comprising target electronic components;
Forward calculation is made to described image using the convolutional neural networks after training, obtain the target electronic components belong to it is all kinds of
The probability distribution of the various polar orientation classifications of electronic component;Wherein, the various polar orientation classifications include a variety of electronics members
The polar orientation classification of part;The forward calculation includes identifying to the polar orientation of the target electronic components;
Choose polar orientation classification of the polar orientation classification of maximum probability as the target electronic components.
2. the recognition methods of electronic component polar orientation according to claim 1, which is characterized in that include in the acquisition
After the step of image of target electronic components, comprising the following steps:
The Prototype drawing of the target electronic components is obtained, with the Prototype drawing of the target electronic components to the target in described image
Electronic component is matched, and the exact position of the target electronic components in described image is obtained, according to the exact position to institute
The target electronic components stated in image are adjusted, and the target electronic components in described image is made to be located at the center of described image,
Image adjusted supplies the convolutional neural networks after the training to make forward calculation.
3. the recognition methods of electronic component polar orientation according to claim 1, which is characterized in that the volume after the training
Product neural network is obtained by following steps:
Establish the image pattern collection of the various polar orientations of all kinds of electronic components;
By preset external data collection pre-training convolutional neural networks, wherein the external data collection includes the more of multiple classifications
Open the natural image marked in advance;
According to described image sample set, the convolutional neural networks after pre-training are adjusted and made with further training, obtains institute
Convolutional neural networks after stating training.
4. the recognition methods of electronic component polar orientation according to claim 3, which is characterized in that establish each electron-like member
The step of sample set of the various polar orientations of part the following steps are included:
Pcb board card graphic and PCB Prototype drawing are obtained, and is reference with the PCB Prototype drawing, the pcb board card graphic is carried out
Position registration;
All kinds of electronic component images after interception position registration on pcb board card graphic, with each electron-like in the PCB Prototype drawing
Element matches electronic component corresponding in all kinds of electronic component images, obtains in all kinds of electronic component images
The corresponding electronic element is adjusted according to the exact position of the corresponding electronic element in the exact position of corresponding electronic element
It is whole, so that the corresponding electronic element is located at the center of all kinds of electronic component images, obtains the various poles of all kinds of electronic components
The image pattern collection in property direction.
5. the recognition methods of electronic component polar orientation according to claim 3, which is characterized in that described by preset
The step of external data collection pre-training convolutional neural networks the following steps are included:
Pre-training is carried out to convolutional neural networks with the external data collection, convolutional neural networks is made to learn the standard drawing of each level
As feature, the initial parameter value of the convolutional neural networks after obtaining pre-training.
6. the recognition methods of electronic component polar orientation according to claim 5, which is characterized in that described according to
Image pattern collection, the convolutional neural networks after pre-training are adjusted and make the step further trained the following steps are included:
According to described image sample set, by the last layer section of the convolutional neural networks after the pre-training in the initial parameter value
Points are adjusted to the classification number of the various polar orientations of various electronic components, and make to convolutional neural networks adjusted further
Training.
7. a kind of mask method of electronic component polar orientation, which comprises the following steps:
The target electronic that the recognition methods of electronic component polar orientation as claimed in any of claims 1 to 6 determines
The polar orientation of element, marks the polar orientation information of the target electronic components in board-like file, and the board-like file is used
In the various attribute informations for saving electronic component.
8. a kind of identifying system of electronic component polar orientation characterized by comprising
Acquiring unit, for obtaining the image comprising target electronic components;
Computing unit obtains the target electricity for making forward calculation to described image using the convolutional neural networks after training
Subcomponent belongs to the probability distribution of the various polar orientation classifications of all kinds of electronic components;Wherein, the various polar orientation classifications
Polar orientation classification including a variety of electronic components;The forward calculation include to the polar orientations of the target electronic components into
Row identification;
Selection unit, for choosing polar orientation class of the polar orientation classification as the target electronic components of maximum probability
Not.
9. the identifying system of electronic component polar orientation according to claim 8, which is characterized in that further include establishing list
Member, pre-training unit and adjustment unit;
The image pattern collection established unit and be used to establish the various polar orientations of all kinds of electronic components;
The pre-training unit is used for by preset external data collection pre-training convolutional neural networks, wherein the external data
Collection includes multiple natural images marked in advance of multiple classifications;
The adjustment unit be used for according to described image sample set, the convolutional neural networks after pre-training are adjusted and make into
The training of one step, the convolutional neural networks after obtaining the training.
10. a kind of labeling system of electronic component polar orientation, which is characterized in that including mark unit and such as claim 8 or 9
The identifying system of the electronic component polar orientation, wherein the mark unit in board-like file for marking the mesh
The polar orientation information of electronic component is marked, the board-like file is used to save the various attribute informations of electronic component.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510822818.6A CN105513046B (en) | 2015-11-23 | 2015-11-23 | The polar recognition methods of electronic component and system, mask method and system |
PCT/CN2016/098227 WO2017088552A1 (en) | 2015-11-23 | 2016-09-06 | Method and system for identifying electronic component polarity, and method and system for marking electronic component polarity |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510822818.6A CN105513046B (en) | 2015-11-23 | 2015-11-23 | The polar recognition methods of electronic component and system, mask method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105513046A CN105513046A (en) | 2016-04-20 |
CN105513046B true CN105513046B (en) | 2019-03-01 |
Family
ID=55721003
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510822818.6A Active CN105513046B (en) | 2015-11-23 | 2015-11-23 | The polar recognition methods of electronic component and system, mask method and system |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN105513046B (en) |
WO (1) | WO2017088552A1 (en) |
Families Citing this family (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105513046B (en) * | 2015-11-23 | 2019-03-01 | 广州视源电子科技股份有限公司 | The polar recognition methods of electronic component and system, mask method and system |
CN105426917A (en) * | 2015-11-23 | 2016-03-23 | 广州视源电子科技股份有限公司 | Component classification method and apparatus |
CN107563123A (en) * | 2017-09-27 | 2018-01-09 | 百度在线网络技术(北京)有限公司 | Method and apparatus for marking medical image |
CN107886131A (en) * | 2017-11-24 | 2018-04-06 | 佛山科学技术学院 | One kind is based on convolutional neural networks detection circuit board element polarity method and apparatus |
CN108984992B (en) * | 2018-09-25 | 2022-03-04 | 郑州云海信息技术有限公司 | Circuit board design method and device |
CN109859164B (en) * | 2018-12-21 | 2023-08-01 | 苏州绿控传动科技股份有限公司 | Method for visual inspection of PCBA (printed circuit board assembly) through rapid convolutional neural network |
CN111640088B (en) * | 2020-04-22 | 2023-12-01 | 深圳拓邦股份有限公司 | Electronic element polarity detection method and system based on deep learning and electronic device |
CN113468833B (en) * | 2021-06-11 | 2024-02-09 | 山东英信计算机技术有限公司 | Method, device, equipment and medium for marking attribute of component in schematic diagram |
CN114399502A (en) * | 2022-03-24 | 2022-04-26 | 视睿(杭州)信息科技有限公司 | Appearance defect detection method and system suitable for LED chip and storage medium |
CN115221832A (en) * | 2022-08-03 | 2022-10-21 | 上海望友信息科技有限公司 | Packaging polarity identification design method and system, electronic equipment and storage medium |
EP4358020A1 (en) | 2022-10-17 | 2024-04-24 | Fitech sp. z o.o. | Method of detecting errors in the placement of elements in the pcb |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103544705A (en) * | 2013-10-25 | 2014-01-29 | 华南理工大学 | Image quality testing method based on deep convolutional neural network |
CN103927534A (en) * | 2014-04-26 | 2014-07-16 | 无锡信捷电气股份有限公司 | Sprayed character online visual detection method based on convolutional neural network |
CN104459421A (en) * | 2014-12-30 | 2015-03-25 | 广州视源电子科技股份有限公司 | Diode polarity detecting method and system |
CN104537650A (en) * | 2014-12-16 | 2015-04-22 | 广州视源电子科技股份有限公司 | Polarity direction judging method and device for aluminum electrolytic capacitor |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100668303B1 (en) * | 2004-08-04 | 2007-01-12 | 삼성전자주식회사 | Method for detecting face based on skin color and pattern matching |
CN105513046B (en) * | 2015-11-23 | 2019-03-01 | 广州视源电子科技股份有限公司 | The polar recognition methods of electronic component and system, mask method and system |
-
2015
- 2015-11-23 CN CN201510822818.6A patent/CN105513046B/en active Active
-
2016
- 2016-09-06 WO PCT/CN2016/098227 patent/WO2017088552A1/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103544705A (en) * | 2013-10-25 | 2014-01-29 | 华南理工大学 | Image quality testing method based on deep convolutional neural network |
CN103927534A (en) * | 2014-04-26 | 2014-07-16 | 无锡信捷电气股份有限公司 | Sprayed character online visual detection method based on convolutional neural network |
CN104537650A (en) * | 2014-12-16 | 2015-04-22 | 广州视源电子科技股份有限公司 | Polarity direction judging method and device for aluminum electrolytic capacitor |
CN104459421A (en) * | 2014-12-30 | 2015-03-25 | 广州视源电子科技股份有限公司 | Diode polarity detecting method and system |
Also Published As
Publication number | Publication date |
---|---|
CN105513046A (en) | 2016-04-20 |
WO2017088552A1 (en) | 2017-06-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105513046B (en) | The polar recognition methods of electronic component and system, mask method and system | |
CN105469400B (en) | The quick method and system for identifying, marking of electronic component polar orientation | |
CN112115895B (en) | Pointer type instrument reading identification method, pointer type instrument reading identification device, computer equipment and storage medium | |
CN109064454A (en) | Product defects detection method and system | |
CN109100370A (en) | A kind of pcb board defect inspection method based on sciagraphy and connected domain analysis | |
CN109120919B (en) | A kind of automatic analysis system and method for the evaluation and test of picture quality subjectivity | |
CN107886131A (en) | One kind is based on convolutional neural networks detection circuit board element polarity method and apparatus | |
CN108960404A (en) | A kind of people counting method and equipment based on image | |
CN110991297A (en) | Target positioning method and system based on scene monitoring | |
CN106385544A (en) | Camera exposure adjustment method and apparatus | |
CN110688955A (en) | Building construction target detection method based on YOLO neural network | |
CN105868269A (en) | Precise image searching method based on region convolutional neural network | |
CN114581760B (en) | Equipment fault detection method and system for machine room inspection | |
CN105678301A (en) | Method, system and device for automatically identifying and segmenting text image | |
CN112733723A (en) | Vehicle type identification method and terminal | |
CN114148103B (en) | Solder paste printing mark recognition method and system based on neural network learning | |
CN107967468A (en) | A kind of supplementary controlled system based on pilotless automobile | |
CN110059617A (en) | A kind of recognition methods of target object and device | |
CN113824874A (en) | Auxiliary shooting method and device, electronic equipment and storage medium | |
CN113591767A (en) | Method and device for determining image recognition evaluation value, storage medium and electronic device | |
CN113920450A (en) | Method and device for identifying insulator RTV coating based on intrinsic image decomposition | |
CN113205163A (en) | Data labeling method and device | |
CN113674207A (en) | Automatic PCB component positioning method based on graph convolution neural network | |
CN108875832A (en) | A kind of colorimetric analysis system | |
CN116563770B (en) | Method, device, equipment and medium for detecting vehicle color |
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 |