CN117492161B - Light-equalizing sheet positioning and correcting method, electronic equipment and computer readable medium - Google Patents
Light-equalizing sheet positioning and correcting method, electronic equipment and computer readable medium Download PDFInfo
- Publication number
- CN117492161B CN117492161B CN202311843380.0A CN202311843380A CN117492161B CN 117492161 B CN117492161 B CN 117492161B CN 202311843380 A CN202311843380 A CN 202311843380A CN 117492161 B CN117492161 B CN 117492161B
- Authority
- CN
- China
- Prior art keywords
- light
- sheet
- equalizing
- image
- homogenizing
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000001514 detection method Methods 0.000 claims abstract description 76
- 230000004044 response Effects 0.000 claims abstract description 22
- 230000000007 visual effect Effects 0.000 claims abstract description 12
- 238000007599 discharging Methods 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 11
- 230000005856 abnormality Effects 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 5
- 239000013598 vector Substances 0.000 description 34
- 230000006870 function Effects 0.000 description 13
- 238000010586 diagram Methods 0.000 description 9
- 238000000605 extraction Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 6
- 238000003062 neural network model Methods 0.000 description 6
- 238000013527 convolutional neural network Methods 0.000 description 5
- 239000003292 glue Substances 0.000 description 4
- 239000002994 raw material Substances 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000010030 laminating Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
-
- G—PHYSICS
- G02—OPTICS
- G02B—OPTICAL ELEMENTS, SYSTEMS OR APPARATUS
- G02B7/00—Mountings, adjusting means, or light-tight connections, for optical elements
Abstract
The embodiment of the disclosure discloses a light homogenizing sheet positioning and rectifying method, electronic equipment and a computer readable medium. One embodiment of the method comprises the following steps: in response to detecting that the light-equalizing sheet is on the anti-sticking stripping platform, controlling a visual deviation correcting device to shoot the light-equalizing sheet to obtain a light-equalizing sheet image; inputting the light-equalizing sheet image into a light-equalizing sheet position identification model to obtain a light-equalizing sheet position identification result; the method comprises the steps of responding to the fact that a light-equalizing sheet position identification result is determined to represent the deviation of the light-equalizing sheet, controlling a three-dimensional rubberizing manipulator to adjust and place the light-equalizing sheet at the center position of an anti-sticking stripping platform; responding to the fact that the identification result of the position of the light homogenizing sheet indicates that the light homogenizing sheet is not offset, controlling a sucker included in the three-dimensional rubberizing manipulator to suck the light homogenizing sheet onto a key board on a rubberizing position for pasting, and obtaining a finished product key board; and (5) carrying out light homogenizing sheet pasting detection on the finished product key board. The embodiment reduces the possibility of deviation of the light homogenizing sheet and improves the pasting efficiency.
Description
Technical Field
The embodiment of the disclosure relates to the field of light-equalizing sheet positioning, in particular to a light-equalizing sheet positioning and correcting method, electronic equipment and a computer readable medium.
Background
The light homogenizing sheet has the main function of homogenizing uneven light distribution, so that the light can be transmitted and applied better. At present, a light homogenizing sheet is attached to a key board in a general mode that: the key board is manually placed in the fixing device, and then the light homogenizing sheet is attached.
However, the inventors have found that folding a carton in the above manner often presents the following technical problem: the manual pasting and placing of the light homogenizing sheet possibly causes deviation of the position of the pasting and placing of the light homogenizing sheet, repeated pasting and placing are needed, and pasting and placing efficiency is low.
The above information disclosed in this background section is only for enhancement of understanding of the background of the inventive concept and, therefore, may contain information that does not form the prior art that is already known to those of ordinary skill in the art in this country.
Disclosure of Invention
The disclosure is in part intended to introduce concepts in a simplified form that are further described below in the detailed description. The disclosure is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
Some embodiments of the present disclosure provide methods, electronic devices, and computer-readable media for positioning and correcting a light homogenizing sheet to solve one or more of the technical problems mentioned in the background section above.
In a first aspect, some embodiments of the present disclosure provide a method for positioning and correcting a light homogenizing sheet, which is applied to an automatic light homogenizing sheet sticking machine, where the automatic light homogenizing sheet sticking machine includes: the method comprises the following steps of storing a bin, a key plate vibration disc, a visual deviation correcting device, a gumming paper feeder, a gumming position, a three-dimensional gumming manipulator, a discharging channel and a finished product collecting box, wherein: in response to detecting that the light homogenizing sheet is on the anti-sticking and stripping platform, controlling the visual deviation correcting device to shoot the light homogenizing sheet to obtain a light homogenizing sheet image, wherein the anti-sticking and stripping platform is displayed in the light homogenizing sheet image; inputting the light-equalizing sheet image into a pre-trained light-equalizing sheet position identification model to obtain a light-equalizing sheet position identification result; controlling the three-dimensional rubberizing manipulator to adjust and place the light-equalizing sheet at the central position of the anti-sticking stripping platform in response to the fact that the light-equalizing sheet position identification result represents the deviation of the light-equalizing sheet; responding to the fact that the position identification result of the light homogenizing sheet represents that the light homogenizing sheet is not offset, controlling a sucker included in the three-dimensional rubberizing manipulator to suck the light homogenizing sheet on a key board on the rubberizing position for pasting, and obtaining a finished product key board; carrying out uniform light sheet pasting detection on the finished product key board to obtain a uniform light sheet pasting detection result; and responding to the detection result of the light homogenizing sheet pasting and placing to indicate that the detection is passed, controlling the pasting position to incline towards the discharging channel, and sliding the finished product key board into the finished product collecting box through the discharging channel.
In a second aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device having one or more programs stored thereon, which when executed by one or more processors causes the one or more processors to implement the method described in any of the implementations of the first aspect above.
In a third aspect, some embodiments of the present disclosure provide a computer readable medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.
The above embodiments of the present disclosure have the following advantageous effects: through the light homogenizing sheet positioning and correcting method of some embodiments of the present disclosure, whether the light homogenizing sheet is at a preset position can be identified, and when the light homogenizing sheet is not at the preset position, correction can be performed through the three-dimensional rubberizing manipulator. Therefore, the sucking disc can accurately suck the light homogenizing sheet so as to be attached to the key board, the possibility of deviation of attaching and placing the light homogenizing sheet is reduced, and the attaching and placing efficiency is improved. Specifically, the reason that the pasting efficiency is low is that the pasting and placing of the light homogenizing sheet by manpower may cause deviation of the position of the pasting and placing of the light homogenizing sheet, and the pasting and placing needs to be repeated. Based on this, in the light-equalizing sheet positioning and correcting method according to some embodiments of the present disclosure, first, in response to detecting that the light-equalizing sheet is on the anti-sticking stripping platform, the vision correcting device is controlled to shoot the light-equalizing sheet, so as to obtain a light-equalizing sheet image. Wherein, the anti-sticking stripping platform is displayed in the image of the light-homogenizing sheet. And secondly, inputting the light-equalizing sheet image into a pre-trained light-equalizing sheet position recognition model to obtain a light-equalizing sheet position recognition result. Therefore, whether the light homogenizing sheet is positioned at the preset position of the anti-sticking stripping platform can be detected, so that the sucking disc can accurately suck the light homogenizing sheet. And then, in response to determining that the light-equalizing sheet position identification result represents the deviation of the light-equalizing sheet, controlling the three-dimensional rubberizing manipulator to adjust and place the light-equalizing sheet at the central position of the anti-sticking stripping platform. Thus, the offset light-equalizing sheet can be moved to the center position. And then, in response to determining that the identification result of the position of the light homogenizing sheet indicates that the light homogenizing sheet is not offset, controlling a sucker included in the three-dimensional rubberizing manipulator to suck the light homogenizing sheet on a key board on the rubberizing position for pasting, and obtaining a finished key board. Therefore, the sucking disc can accurately suck the light homogenizing sheet, so that the accuracy of the light homogenizing sheet for subsequent pasting and placing is improved. And then, carrying out light-homogenizing sheet pasting detection on the finished product key board to obtain a light-homogenizing sheet pasting detection result. And finally, responding to the detection result of the light-equalizing sheet pasting and placing to indicate that the detection is passed, controlling the pasting position to incline towards the discharging channel, and sliding the finished product key board into the finished product collecting box through the discharging channel. Therefore, whether the light-equalizing sheet is at the preset position or not can be identified, and when the light-equalizing sheet is not at the preset position, correction can be performed through the three-dimensional rubberizing manipulator. Therefore, the sucking disc can accurately suck the light homogenizing sheet so as to be attached to the key board, the possibility of deviation of attaching and placing the light homogenizing sheet is reduced, and the attaching and placing efficiency is improved.
Drawings
The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. The same or similar reference numbers will be used throughout the drawings to refer to the same or like elements. It should be understood that the figures are schematic and that elements and components are not necessarily drawn to scale.
FIG. 1 is a flow chart of some embodiments of a light balancing sheet positioning and deviation rectifying method according to the present disclosure;
FIG. 2 is a schematic diagram of a structural layout of an automatic light homogenizing machine in a light homogenizing sheet positioning and correcting method according to the present disclosure;
FIG. 3 is a schematic diagram of a structural layout of a storage bin, a keypad vibration plate in a light balancing piece positioning and correcting method according to the present disclosure;
FIG. 4 is a schematic diagram of a structural layout of a visual deviation correcting device, a gummed paper feeder, a three-dimensional rubberizing manipulator in a two-sided folding box machine apparatus according to the present disclosure;
fig. 5 is a schematic structural diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.
It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings. Embodiments of the present disclosure and features of embodiments may be combined with each other without conflict.
It should be noted that the terms "first," "second," and the like in this disclosure are merely used to distinguish between different devices, modules, or units and are not used to define an order or interdependence of functions performed by the devices, modules, or units.
It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be understood as "one or more" unless the context clearly indicates otherwise.
The names of messages or information interacted between the various devices in the embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.
The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
FIG. 1 is a flow chart of some embodiments of a light balancing sheet positioning and deviation rectifying method according to the present disclosure. A flow 100 of some embodiments of a light balancing sheet positioning and correction method according to the present disclosure is shown. The light homogenizing sheet positioning and correcting method is applied to an automatic light homogenizing sheet pasting machine, and the automatic light homogenizing sheet pasting machine comprises the following steps: the method for positioning and rectifying the light homogenizing sheet comprises the following steps of:
And step 101, controlling the visual deviation correcting device to shoot the light-equalizing sheet to obtain a light-equalizing sheet image in response to the detection that the light-equalizing sheet is on the anti-sticking stripping platform.
In some embodiments, an executing body of the light homogenizing sheet positioning and correcting method (for example, an automatic light homogenizing sheet pasting machine or a computing device for controlling the automatic light homogenizing sheet pasting machine) may control the visual correcting device to shoot the light homogenizing sheet to obtain a light homogenizing sheet image in response to detecting that the light homogenizing sheet is on the anti-adhesion stripping platform. Wherein, the anti-sticking stripping platform is displayed in the keyboard light-homogenizing sheet image. The anti-sticking stripping platform is engraved with a position alignment mark so as to determine whether the light-equalizing sheet is skewed or not. That is, the executing body can detect that the light homogenizing sheet is on the anti-sticking stripping platform through the sensor. The visual deviation correcting device can be intelligent equipment with an image acquisition function.
As illustrated in fig. 2, the automatic light homogenizing sheet attaching machine includes: the automatic glue applying device comprises a storage bin 201, a key plate vibration disc 202, a visual deviation correcting device 203, a glue feeder 204, a glue applying position 205, a three-dimensional glue applying mechanical arm 206, a discharging channel 207 and a finished product collecting box 208. Automatic paste light homogenizing piece machine still includes: a release stripping platform 209. Wherein the storage bin 201 is used for storing the keypad raw materials. The keypad vibration plate 202 vibrates the keypad raw material to feed the keypad raw material into the feed channel. As illustrated in fig. 3, includes a storage bin 201, a keypad vibration plate 202, a starved sensor 301, and a feed channel 302. The starved sensor 301 may be a sensor that senses whether there is keypad material on the feed channel 302. The visual correction device 203 may be an intelligent device with image acquisition function. The rubberizing station 205 may be a location where keypad stock is stored and used to place the light homogenizing sheet. The three-dimensional rubberizing manipulator 206 may be referred to as an XYZ rubberizing manipulator, and may move from three angles, and includes a suction cup for sucking a light homogenizing sheet onto a keypad raw material for pasting. The discharging channel 207 may be a channel for sliding the keypad plate on which the light equalizing sheet is mounted to the finished product collecting box 208. As illustrated in fig. 4, comprising: visual deviation correcting device 203, gummed paper feeder 204, three-dimensional rubberizing manipulator 206. The offset feeder 204 may refer to a machine that peels off the light separator from the offset film in the light separator film.
Continuing, when the position of the attached light homogenizing sheet is corrected by adopting the light homogenizing sheet positioning and correcting method, the following technical problem II further exists: the light homogenizing sheets may have different shapes, and position identification is performed through a single neural network model, so that different light homogenizing sheets are difficult to adapt, and the identified light homogenizing sheets have deviation in position.
Optionally, a light-equalizing sheet image tag set corresponding to the light-equalizing sheet is acquired.
In some embodiments, the executing body may acquire a light-equalizing sheet image tag set corresponding to the light-equalizing sheet. That is, the sample label corresponding to the light-equalizing sheet image sample set is the corresponding light-equalizing sheet image label. For example, the image label of the light homogenizing sheet may be "round light homogenizing sheet placed askew", and the sample label corresponding to the corresponding sample set of the light homogenizing sheet image is "round light homogenizing sheet placed askew". For another example, the image label of the light-equalizing sheet may be "square light-equalizing sheet is placed askew", and the sample label corresponding to the corresponding sample set of the light-equalizing sheet image is "square light-equalizing sheet is placed askew".
Optionally, classifying each light-equalizing sheet image label included in the light-equalizing sheet image label set according to the shape of the light-equalizing sheet, so as to obtain at least one light-equalizing sheet image classification label set.
In some embodiments, the executing body may classify each of the light-equalizing image labels included in the light-equalizing image label set according to a shape of the light-equalizing sheet, to obtain at least one light-equalizing image classification label set. For example, the image labels of the light-equalizing sheets corresponding to the same shape can be classified into one type, so as to obtain a light-equalizing sheet image classification label group.
Optionally, for each of the at least one light-equalizing image classification tag group, the light-equalizing image classification tag group is allocated to a corresponding light-equalizing image marking end, so that the light-equalizing image marking end generates a light-equalizing image sample set corresponding to the light-equalizing image classification tag group.
In some embodiments, the executing body may assign, for each of the at least one light-equalizing image classification tag group, the light-equalizing image classification tag group to a corresponding light-equalizing image marking end, so that the light-equalizing image marking end generates a light-equalizing image sample set corresponding to the light-equalizing image classification tag group. The light-equalizing sheet image marking end can be an operation end for marking the label of the initial sample light-equalizing sheet image. For example, the image marking end of the light equalizing sheet can be an operation terminal for marking the label by a related operator. And the light-equalizing sheet image samples in the light-equalizing sheet image sample set all have corresponding labels. And each light-equalizing image classification label group has a unique corresponding light-equalizing image marking end so as to execute the generation of a light-equalizing image sample set corresponding to the subsequent light-equalizing image classification label group. First, the executing body may determine label marking information corresponding to each light-equalizing sheet image marking end. The label mark information can be label generation information of a label corresponding to the light-equalizing sheet image sample. And then, distributing the light-equalizing image classification label group to a corresponding light-equalizing image marking end so as to generate a light-equalizing image sample set corresponding to the light-equalizing image classification label group by the light-equalizing image marking end. A label may refer to a callout.
Optionally, according to the obtained at least one light-homogenizing sheet image sample set, performing model training on the initial light-homogenizing sheet position identification model to obtain the light-homogenizing sheet position identification model.
In some embodiments, the executing body may perform model training on the initial light-equalizing position identification model according to the obtained at least one light-equalizing image sample set, so as to obtain the light-equalizing position identification model. For example, the initial light balancing sheet position identification model may be a convolutional neural network (Convolutional Neural Networks, CNN) model that trains incomplete multi-layer serial connections.
In practice, the execution main body can perform model training on the initial keypad light homogenizing sheet position identification model through the following steps of:
the first step, selecting a light-equalizing sheet image sample from the at least one light-equalizing sheet image sample set, taking the light-equalizing sheet image sample as a target average light-equalizing sheet image sample, and executing the following training steps:
1. and inputting the light-equalizing sheet image included in the target light-equalizing sheet image sample into a feature extraction network included in the initial light-equalizing sheet position identification model to obtain the light-equalizing sheet image feature information. Wherein the feature extraction network may be an untrained image feature extraction network. For example, the feature extraction network may be a multi-layer serial connected residual neural network model. The light-equalizing piece image characteristic information can represent the light-equalizing piece image content characteristic information of the light-equalizing piece image included in the target light-equalizing piece image sample.
2. And generating a light-equalizing image tag feature group corresponding to each light-equalizing image classification tag group in the at least one light-equalizing image classification tag group by using the initial light-equalizing position identification model, so as to obtain at least one light-equalizing image tag feature group. Wherein, the light-equalizing sheet image label characteristics in the at least one light-equalizing sheet image label characteristic group are in one-to-one correspondence with the light-equalizing sheet image classification labels in the at least one light-equalizing sheet image classification label group. The label characteristics of the light-equalizing sheet image can represent the content characteristic information of the label content of the light-equalizing sheet image classification label. For example, each of the at least one light-homogenizing sheet image classification tag group may be input into a multi-layer serial connected residual neural network model included in the initial light-homogenizing sheet position identification model to generate a light-homogenizing sheet image tag feature group, so as to obtain at least one light-homogenizing sheet image tag feature group.
3. And generating feature loss information according to the at least one light-homogenizing sheet image label feature group and the light-homogenizing sheet image feature information by using the initial light-homogenizing sheet position identification model. Firstly, the initial light-equalizing sheet position identification model can be utilized to determine similar information between each light-equalizing sheet image label characteristic and light-equalizing sheet image characteristic information in at least one light-equalizing sheet image label characteristic group, and a similar information set is obtained. Then, determining the label information included in the target light-equalizing sheet image sample. Next, similar information with the numerical value of the first 3 is selected from the similar information set, and a similar information subset is obtained. And finally, inputting the similar information subset and the label information into a preset loss function to output characteristic loss information. The predetermined loss function may be a cross entropy loss function.
4. And determining the initial light-equalizing sheet position recognition model as a trained light-equalizing sheet position recognition model in response to determining that the characteristic loss information meets a preset condition. The preset conditions may be: the value represented by the characteristic loss information is smaller than or equal to a preset value.
And secondly, in response to determining that the characteristic loss information does not meet the preset condition, adjusting network parameters of an initial light-homogenizing sheet position identification model, and re-selecting a target light-homogenizing sheet image sample from the at least one light-homogenizing sheet image sample set, and executing the training step again.
The above-mentioned related matters serve as an invention point of the present disclosure, and solve the second technical problem, which results in deviation of the identified positions of the light-equalizing sheets. ". Factors that cause deviations in the position of the identified light homogenizing sheet are often as follows: the light homogenizing sheet may have different shapes, and the position identification is performed through a single neural network model, so that the light homogenizing sheet is difficult to adapt to different light homogenizing sheets. If the above factors are solved, the effect of improving the accuracy of the position of the identified light homogenizing sheet can be achieved. To achieve this effect, first, a light-equalizing sheet image tag set corresponding to a light-equalizing sheet is acquired. And secondly, classifying each light-equalizing image label included in the light-equalizing image label set according to the shape of the light-equalizing sheet to obtain at least one light-equalizing image classification label group. And then, for each of the at least one light-equalizing image classification label group, distributing the light-equalizing image classification label group to a corresponding light-equalizing image marking end so as to generate a light-equalizing image sample set corresponding to the light-equalizing image classification label group by the light-equalizing image marking end. And finally, performing model training on the initial light-equalizing sheet position identification model according to the obtained at least one light-equalizing sheet image sample set to obtain the light-equalizing sheet position identification model. Therefore, semantic information (light-equalizing image label characteristics) corresponding to at least one light-equalizing image classification label group is considered, so that training of a subsequent initial light-equalizing position recognition model is performed, the light-equalizing position recognition model can learn more semantic information about labels, and the light-equalizing position recognition model with more accurate position recognition can be obtained by combining the image characteristic information. Thus, various shapes and positions of the light-equalizing sheet can be identified.
Step 102, inputting the image of the light homogenizing sheet into a pre-trained light homogenizing sheet position identification model to obtain a light homogenizing sheet position identification result.
In some embodiments, the executing body may input the light-equalizing sheet image into a pre-trained light-equalizing sheet position recognition model, to obtain a light-equalizing sheet position recognition result. The light-equalizing sheet position recognition model can be a neural network model which is trained in advance, takes a light-equalizing sheet image as input and takes a light-equalizing sheet position recognition result as output. For example, the light homogenizing sheet position identifying model may be a convolutional neural network model or a deep neural network model. The light homogenizing sheet position identification result can indicate whether the light homogenizing sheet on the anti-sticking stripping platform is deviated or not.
And step 103, in response to determining that the light-equalizing sheet position identification result represents the deviation of the light-equalizing sheet, controlling the three-dimensional rubberizing manipulator to adjust and place the light-equalizing sheet at the central position of the anti-sticking stripping platform.
In some embodiments, the executing body may control the three-dimensional rubberizing manipulator to place the light homogenizing sheet in a central position of the anti-sticking stripping platform in an adjusted manner in response to determining that the light homogenizing sheet position identification result represents the light homogenizing sheet offset. The three-dimensional rubberizing manipulator can be controlled to grasp the light-equalizing sheet to the central position of the anti-sticking stripping platform.
And 104, controlling a sucker included in the three-dimensional rubberizing manipulator to suck the light homogenizing sheet onto a key board on the rubberizing position for pasting in response to the fact that the light homogenizing sheet is not deflected as indicated by the position identification result of the light homogenizing sheet, and obtaining a finished key board.
In some embodiments, the executing body may control the sucker included in the three-dimensional rubberizing manipulator to suck the light homogenizing sheet onto the keypad on the rubberizing position to paste in response to determining that the light homogenizing sheet is not deflected by the light homogenizing sheet position identification result, so as to obtain a finished keypad. The suction cup included by the three-dimensional rubberizing manipulator can be a vacuum suction cup, and can absorb the light homogenizing sheet. The finished product key board can be the key board with the light-equalizing sheet adhered.
And 105, carrying out light-equalizing piece pasting and placing detection on the finished product key board to obtain a light-equalizing piece pasting and placing detection result.
In some embodiments, the executing body may perform the light-equalizing sheet pasting detection on the finished key board, to obtain a light-equalizing sheet pasting detection result. The detection result of the light-equalizing sheet pasting can indicate whether the light-equalizing sheet pasting on the finished key board is askew or not. For example, the light homogenizing sheet on the finished key sheet is not attached to a preset area on the key sheet.
In practice, the executing main body can carry out the light-homogenizing sheet pasting and placing detection on the finished product key board through the following steps of:
and a first step of controlling an associated camera device to acquire a key board image of the finished key board. The keyboard image shows the attached light homogenizing sheet.
And secondly, inputting the image of the key board into a pre-trained key board light-homogenizing sheet detection model to obtain a key board light-homogenizing sheet detection result. The keypad light-equalizing sheet detection model can be a convolutional neural network model which is trained in advance, takes a keypad image as input and takes a keypad light-equalizing sheet detection result as output. The detection result of the light-equalizing sheet pasting can indicate whether the light-equalizing sheet pasting on the finished product key board is inclined or not. For example, the light homogenizing sheet on the finished key sheet is not attached to a preset area on the key sheet.
Continuing, after correcting the position of the attached light homogenizing sheet by adopting the light homogenizing sheet positioning and correcting method, the inventor finds that the following problems are often accompanied: although the manipulator can accurately grasp the light-equalizing sheet to the key board after correcting the placement position of the light-equalizing sheet, the light-equalizing sheet on the key board is attached and placed in a deviation way due to faults or vibration and other reasons possibly caused by the operation of the machine. For these problems, conventional solutions generally include: detecting finished key boards one by manpower; or a batch of finished products are uniformly detected by professional equipment.
However, the above solution generally has the following technical problem three: the manual detection efficiency is low, and fine offset is difficult to find; when the shapes of the light-equalizing sheets are different, a plurality of devices are required to be used for detection, the detection efficiency is low, and the cost is high.
Optionally, before inputting the above-mentioned keypad image into the pre-trained keypad light-equalizing sheet detection model to obtain the keypad light-equalizing sheet detection result, the above-mentioned method further includes:
the first step, a marked key plate light-equalizing sheet image set and an unmarked key plate light-equalizing sheet image set are obtained. The mark key sheet light homogenizing sheet image may refer to an image in which a light homogenizing sheet and a preset area in the key sheet are marked. The unlabeled keypad light homogenizing sheet image may refer to an image of an unlabeled light homogenizing sheet and a preset area in the keypad.
The second step, based on the marked key-plate light-equalizing sheet image set and the unmarked key-plate light-equalizing sheet image set, performs the following marking steps:
1. and extracting the mark light-equalizing sheet image feature vector of each mark light-equalizing sheet image of the mark key sheet image set to obtain a mark light-equalizing sheet image feature vector set. And extracting the characteristic vector of the mark light-equalizing sheet image of each mark light-equalizing sheet image of the mark key-plate light-equalizing sheet image set through a characteristic extraction network to obtain a characteristic vector set of the mark light-equalizing sheet image. The feature extraction network may be a feature extraction model, e.g., a Bert model, a VGG model, etc.
2. And extracting the unmarked light-homogenizing sheet image feature vector of each unmarked key-plate light-homogenizing sheet image in the unmarked key-plate light-homogenizing sheet image set to obtain an unmarked light-homogenizing sheet image feature vector set. And extracting the unlabeled light-homogenizing sheet image feature vector of each unlabeled key-plate light-homogenizing sheet image in the unlabeled key-plate light-homogenizing sheet image set through a feature extraction network to obtain an unlabeled light-homogenizing sheet image feature vector set.
3. And constructing a light-equalizing piece image feature structure tree according to the marked light-equalizing piece image feature vector set and the unmarked light-equalizing piece image feature vector set. Wherein, above-mentioned light homogenizing sheet image feature structure tree includes: each marked light-equalizing sheet image node and each unmarked light-equalizing sheet image node.
The method for constructing the light-equalizing sheet image characteristic structure tree comprises the following steps:
first, the set of labeled light-equalizing sheet image feature vectors and the set of unlabeled light-equalizing sheet image feature vectors are determined as a set of light-equalizing sheet image feature vectors.
Then, for each of the above-described set of light-equalizing sheet image feature vectors, the following processing steps are performed:
1. and selecting each light-equalizing image feature vector with the similarity between the light-equalizing image feature vector and the light-equalizing image feature vector greater than or equal to the preset similarity from the light-equalizing image feature vector set.
2. And determining the selected image feature vectors of the light-equalizing sheets as a similar image feature vector group of the image feature vectors of the light-equalizing sheets.
And finally, constructing a light-equalizing piece image feature structure tree according to the similar light-equalizing piece image feature vector groups of the light-equalizing piece image feature vectors in the light-equalizing piece image feature vector set. And the feature vectors corresponding to the marked light-equalizing sheet images in the light-equalizing sheet image feature structure tree are marked light-equalizing sheet image nodes, and the feature vectors corresponding to the unmarked light-equalizing sheet images are unmarked light-equalizing sheet image nodes.
4. And selecting a to-be-marked light-equalizing sheet image node set from the light-equalizing sheet image feature structure tree according to each marked light-equalizing sheet image node included in the light-equalizing sheet image feature structure tree. For each of the respective unlabeled light-equalizing sheet image nodes, the execution body may execute the steps of: and determining the distance between the feature vector of the unlabeled light-equalizing sheet image corresponding to the unlabeled light-equalizing sheet image node and each labeled light-equalizing sheet image to obtain each feature distance. And secondly, determining the minimum feature distance from the minimum value of each feature distance. Then, the determined minimum feature distances may be arranged in a descending order to obtain a minimum feature distance sequence. Next, each minimum feature distance of the number of preceding targets in the minimum feature distance sequence described above may be determined as each target minimum feature distance. And finally, determining each unmarked light-equalizing sheet image node corresponding to each target minimum feature distance as a light-equalizing sheet image node set to be marked.
5. And carrying out marking treatment on each unmarked light-equalizing sheet image corresponding to the light-equalizing sheet image node set to be marked to obtain a marked light-equalizing sheet image group. The execution body can display each unmarked light-equalizing sheet image corresponding to the node set of the light-equalizing sheet image to be marked so as to receive marking information corresponding to the unmarked light-equalizing sheet image input by a technician and carry out marking processing on the unmarked light-equalizing sheet image. Here, the marking information may include a label of the untagged light-equalizing sheet image inputted by the user.
And thirdly, combining the mark key plate light-equalizing sheet image set with the mark light-equalizing sheet image set to obtain a combined mark key plate light-equalizing sheet image set serving as a target mark key plate light-equalizing sheet image set. Merging may refer to stitching.
And step four, clustering the target mark key plate light-equalizing sheet images in the target mark key plate light-equalizing sheet image set to obtain a target mark key plate light-equalizing sheet image set. That is, the key sheet light-equalizing sheet images corresponding to the same shape of the light-equalizing sheet can be grouped into one type.
And fifthly, determining an initial key plate light homogenizing sheet detection model according to the number of the target mark key plate light homogenizing sheet image groups included in the target mark key plate light homogenizing sheet image group set. The initial keypad light-equalizing sheet detection model comprises a target number of initial detection subnetworks, and one detection subnetwork corresponds to one target mark keypad light-equalizing sheet image group. The initial detection sub-network may refer to an untrained initial neural network. That is, the key sheet light-equalizing sheet detection model after training can identify the positions of light-equalizing sheets with different shapes and the key sheet.
And sixthly, performing model training on the initial keypad light-equalizing sheet detection model according to the target mark keypad light-equalizing sheet image group set to obtain the keypad light-equalizing sheet detection model.
Wherein, the sixth step may include the following substeps:
the first substep, for each target mark keypad light-equalizing sheet image group in the target mark keypad light-equalizing sheet image group set, executes the following processing steps:
1. and determining an initial detection sub-network corresponding to the target mark key board light-equalizing sheet image group.
2. And performing model training on the initial detection sub-network according to the target mark key board light-equalizing sheet image group to obtain a trained detection sub-network.
And a second sub-step, determining each trained detection sub-network as a keyboard light-equalizing sheet detection model.
The related content is taken as an invention point of the present disclosure, and solves the technical problem three, namely low detection efficiency and high cost. ". The detection efficiency is low, and the factors with higher cost are as follows: the manual detection efficiency is low, and fine offset is difficult to find; when the shapes of the light-equalizing sheets are different, a plurality of devices are required to be used for detection, the detection efficiency is low, and the cost is high. If the above factors are solved, the effects of improving the detection efficiency and reducing the cost can be achieved. To achieve this effect, first, a marked keypad light-equalizing sheet image set and an unmarked keypad light-equalizing sheet image set are acquired. Next, based on the labeled keypad light homogenizing sheet image set and the unlabeled keypad light homogenizing sheet image set, the following labeling steps are performed: extracting the mark light-equalizing sheet image feature vector of each mark light-equalizing sheet image of the mark key sheet image set to obtain a mark light-equalizing sheet image feature vector set; extracting the feature vector of the unlabeled light-homogenizing sheet image of each unlabeled key plate light-homogenizing sheet image in the unlabeled key plate light-homogenizing sheet image set to obtain a feature vector set of the unlabeled light-homogenizing sheet image; constructing a light-homogenizing sheet image feature structure tree according to the marked light-homogenizing sheet image feature vector set and the unmarked light-homogenizing sheet image feature vector set, wherein the light-homogenizing sheet image feature structure tree comprises: each marked light-equalizing sheet image node and each unmarked light-equalizing sheet image node; selecting a to-be-marked light-equalizing piece image node set from the light-equalizing piece image feature structure tree according to each marked light-equalizing piece image node included in the light-equalizing piece image feature structure tree; and carrying out marking treatment on each unmarked light-equalizing sheet image corresponding to the light-equalizing sheet image node set to be marked to obtain a marked light-equalizing sheet image group. Therefore, when the image nodes of the light homogenizing sheet to be marked are selected, the light homogenizing sheet image characteristic structure tree is selected, and is constructed by utilizing the relation between the marked light homogenizing sheet image characteristic vector set and the unmarked light homogenizing sheet image set, and a mechanism of correlation between the marked light homogenizing sheet image and the unmarked light homogenizing sheet image is utilized, so that the improvement effect of the marked image data on model training is improved. And combining the mark key plate light-equalizing sheet image set with the mark light-equalizing sheet image set to obtain a combined mark key plate light-equalizing sheet image set serving as a target mark key plate light-equalizing sheet image set. And then, clustering the target mark key plate light-equalizing sheet images in the target mark key plate light-equalizing sheet image set to obtain a target mark key plate light-equalizing sheet image set. Thus, the homogeneous light sheets with the same shape can be gathered into one type. And then, determining an initial key plate light homogenizing sheet detection model according to the number of the target mark key plate light homogenizing sheet image groups included in the target mark key plate light homogenizing sheet image group set. The initial keypad light-equalizing sheet detection model comprises a target number of initial detection subnetworks, and one detection subnetwork corresponds to one target mark keypad light-equalizing sheet image group. Thus, multiple detection networks can be trained so that the final trained model can identify light-equalizing sheets of different shapes. And finally, performing model training on the initial keypad light-homogenizing sheet detection model according to the target mark keypad light-homogenizing sheet image group set to obtain the keypad light-homogenizing sheet detection model. Therefore, the identification of the light homogenizing sheets with different shapes can be realized through one model, the detection efficiency is improved, and the cost is reduced.
And step 106, controlling the rubberizing position to incline towards the discharging channel in response to the detection passing of the representation of the rubberizing detection result of the light equalizing sheet, and sliding the finished product key board into the finished product collecting box through the discharging channel.
In some embodiments, the executing body may control the rubberizing position to incline towards the discharging channel in response to the detection result of the rubberizing sheet laminating detection indicating that the detection is passed, and slide the finished product key board into the finished product collecting box through the discharging channel. That is, the direction of the discharge port corresponding to the rubberizing position can be inclined towards the discharge channel, so that the finished product key board slides into the discharge channel to reach the finished product collecting box. The discharge port corresponding to the rubberizing position corresponds to the receiving port of the discharge channel.
Optionally, in response to the detection result of the light-equalizing sheet pasting and placing indicating that the detection fails, controlling the associated equipment abnormality prompting equipment to send an abnormality prompting voice.
In some embodiments, the executing body may control the associated device abnormality prompting device to issue an abnormality prompting voice in response to the detection result of the light-equalizing sheet placement indicating that the detection is not passed. The device abnormality alert device may refer to a voice device that emits an abnormality alert voice. For example, the device abnormality notification device may be a speaker. The content of the abnormal prompt voice can be used for indicating that the light-equalizing sheet is not accurately pasted and placed, and the three-dimensional rubberizing manipulator can have abnormal operation.
Referring now to fig. 3, a schematic diagram of an electronic device (e.g., computing device) 300 suitable for use in implementing some embodiments of the present disclosure is shown. The electronic devices in some embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), car terminals (e.g., car navigation terminals), and the like, as well as stationary terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 3 is merely an example and should not impose any limitations on the functionality and scope of use of embodiments of the present disclosure.
As shown in fig. 3, the electronic device 300 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 301 that may perform various suitable actions and processes in accordance with a program stored in a Read Only Memory (ROM) 302 or a program loaded from a storage means 308 into a Random Access Memory (RAM) 303. In the RAM303, various programs and task data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM302, and the RAM303 are connected to each other via a bus 304. An input/output (I/O) interface 305 is also connected to bus 304.
In general, the following devices may be connected to the I/O interface 305: input devices 306 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 307 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 308 including, for example, magnetic tape, hard disk, etc.; and communication means 309. The communication means 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange task data. While fig. 3 shows an electronic device 300 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead. Each block shown in fig. 3 may represent one device or a plurality of devices as needed.
In particular, according to some embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such embodiments, the computer program may be downloaded and installed from a network via communications device 309, or from storage device 308, or from ROM 302. The above-described functions defined in the methods of some embodiments of the present disclosure are performed when the computer program is executed by the processing means 301.
It should be noted that, the computer readable medium described in some embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, however, the computer-readable signal medium may comprise a task data signal that propagates in baseband or as part of a carrier wave, in which computer-readable program code is carried. Such a propagated signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.
In some implementations, the clients, servers may communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol ), and may be interconnected with any form or medium of digital task data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the internet (e.g., the internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.
The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: in response to detecting that the keypad light-equalizing sheet is on the anti-sticking and stripping platform, controlling the visual deviation correcting device to shoot the keypad light-equalizing sheet to obtain a keypad light-equalizing sheet image, wherein the anti-sticking and stripping platform is displayed in the keypad light-equalizing sheet image; inputting the key plate light-equalizing sheet image into a pre-trained key plate light-equalizing sheet position identification model to obtain a key plate light-equalizing sheet position identification result; the key plate light-equalizing sheet position identification result is determined to represent the key plate light-equalizing sheet deviation, and the three-dimensional rubberizing manipulator is controlled to adjust and place the key plate light-equalizing sheet at the center position of the anti-sticking stripping platform; responding to the fact that the key plate light-homogenizing sheet is not deviated according to the key plate light-homogenizing sheet position identification result, controlling the three-dimensional rubberizing manipulator to paste the key plate light-homogenizing sheet on the rubberizing position to obtain a finished product key plate; carrying out uniform light sheet pasting detection on the finished product key board to obtain a uniform light sheet pasting detection result; and responding to the detection result of the light homogenizing sheet pasting and placing to indicate that the detection is passed, controlling the pasting position to incline towards the discharging channel, and sliding the finished product key board into the finished product collecting box through the discharging channel.
Computer program code for carrying out operations for some embodiments of the present disclosure may be written in one or more programming languages, including a product oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in some embodiments of the present disclosure may be implemented by means of software, or may be implemented by means of hardware. The described units may also be provided in a processor, for example, described as: a processor comprising: the device comprises an acquisition unit, an analysis unit, a conversion unit, a selection unit and a filling unit. The names of the units do not limit the unit itself in some cases, for example, the determining unit may also be described as "a unit for determining the message class and the information transmission restriction information corresponding to the target message according to the message type corresponding to the target message" in response to receiving the message push instruction corresponding to the target message ".
The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a Complex Programmable Logic Device (CPLD), and the like.
The foregoing description is only of the preferred embodiments of the present disclosure and description of the principles of the technology being employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above technical features, but encompasses other technical features formed by any combination of the above technical features or their equivalents without departing from the spirit of the invention. Such as the above-described features, are mutually substituted with (but not limited to) the features having similar functions disclosed in the embodiments of the present disclosure.
Claims (5)
1. A method for positioning and correcting a light homogenizing sheet is applied to an automatic light homogenizing sheet sticking machine, and the automatic light homogenizing sheet sticking machine comprises the following steps: the method comprises the steps of storing a bin, a key plate vibration disc, a visual deviation correcting device, a gumming paper feeder, a gumming position, a three-dimensional gumming manipulator, a discharging channel and a finished product collecting box, wherein the method comprises the following steps:
in response to detecting that the light homogenizing sheet is on the anti-sticking and stripping platform, controlling the vision correction device to shoot the light homogenizing sheet to obtain a light homogenizing sheet image, wherein the anti-sticking and stripping platform is displayed in the light homogenizing sheet image;
acquiring a light-equalizing sheet image tag set corresponding to the light-equalizing sheet;
classifying each light-equalizing image label included in the light-equalizing image label set according to the shape of the light-equalizing sheet to obtain at least one light-equalizing image classification label group;
for each of the at least one light-equalizing image classification tag group, distributing the light-equalizing image classification tag group to a corresponding light-equalizing image marking end so that the light-equalizing image marking end can generate a light-equalizing image sample set corresponding to the light-equalizing image classification tag group;
according to the obtained at least one light-equalizing sheet image sample set, performing model training on an initial light-equalizing sheet position identification model to obtain a light-equalizing sheet position identification model;
Inputting the light-equalizing sheet image into a pre-trained light-equalizing sheet position identification model to obtain a light-equalizing sheet position identification result;
controlling the three-dimensional rubberizing manipulator to adjust and place the light homogenizing sheet at the central position of the anti-sticking stripping platform in response to the fact that the light homogenizing sheet position identification result represents the deviation of the light homogenizing sheet;
responding to the fact that the light homogenizing sheet is characterized by not shifting according to the position identification result of the light homogenizing sheet, controlling a sucker included in the three-dimensional rubberizing manipulator to suck the light homogenizing sheet onto a key board on the rubberizing position for pasting, and obtaining a finished product key board;
carrying out uniform light sheet pasting detection on the finished product key board to obtain a uniform light sheet pasting detection result;
and responding to the detection result of the light-equalizing sheet pasting and placing to indicate that the detection is passed, controlling the pasting position to incline towards the discharging channel, and enabling the finished product key board to slide into the finished product collecting box through the discharging channel.
2. The method of claim 1, wherein the performing the light homogenizing sheet placement detection on the finished key sheet to obtain a light homogenizing sheet placement detection result comprises:
controlling an associated camera device to acquire a key plate image of the finished key plate;
And inputting the key plate image into a pre-trained key plate light homogenizing sheet detection model to obtain a light homogenizing sheet pasting and placing detection result.
3. The method of claim 1, wherein the method further comprises:
and responding to the detection result of the light-equalizing sheet pasting and placing to indicate that the detection fails, and controlling the associated equipment abnormality prompting equipment to send abnormality prompting voice.
4. An electronic device, comprising:
one or more processors;
a storage device having one or more programs stored thereon,
when executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-3.
5. A computer readable medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the method of any of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311843380.0A CN117492161B (en) | 2023-12-29 | 2023-12-29 | Light-equalizing sheet positioning and correcting method, electronic equipment and computer readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311843380.0A CN117492161B (en) | 2023-12-29 | 2023-12-29 | Light-equalizing sheet positioning and correcting method, electronic equipment and computer readable medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117492161A CN117492161A (en) | 2024-02-02 |
| CN117492161B true CN117492161B (en) | 2024-04-12 |
Family
ID=89685301
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311843380.0A Active CN117492161B (en) | 2023-12-29 | 2023-12-29 | Light-equalizing sheet positioning and correcting method, electronic equipment and computer readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117492161B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2803977A1 (en) * | 2013-05-14 | 2014-11-19 | Carl Zeiss Microscopy GmbH | Method for high resolution 3D locating microscopy |
| CN209148831U (en) * | 2017-03-30 | 2019-07-23 | 深圳市汇顶科技股份有限公司 | The test device of light emitting device, test wafer |
| CN117091953A (en) * | 2023-10-19 | 2023-11-21 | 深圳市海塞姆科技有限公司 | Automatic measuring method, computer equipment, system and storage medium for sample deformation |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11294162B2 (en) * | 2019-02-07 | 2022-04-05 | Nanotronics Imaging, Inc. | Fluorescence microscopy inspection systems, apparatus and methods with darkfield channel |
-
2023
- 2023-12-29 CN CN202311843380.0A patent/CN117492161B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2803977A1 (en) * | 2013-05-14 | 2014-11-19 | Carl Zeiss Microscopy GmbH | Method for high resolution 3D locating microscopy |
| CN209148831U (en) * | 2017-03-30 | 2019-07-23 | 深圳市汇顶科技股份有限公司 | The test device of light emitting device, test wafer |
| CN117091953A (en) * | 2023-10-19 | 2023-11-21 | 深圳市海塞姆科技有限公司 | Automatic measuring method, computer equipment, system and storage medium for sample deformation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117492161A (en) | 2024-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109947989B (en) | Method and apparatus for processing video | |
| CN110084317B (en) | Method and device for recognizing images | |
| CN108830329A (en) | Image processing method and device | |
| CN112364829B (en) | Face recognition method, device, equipment and storage medium | |
| EP4047582A3 (en) | Method and apparatus of generating control signal for traffic light, electronic device, and medium | |
| CN117492161B (en) | Light-equalizing sheet positioning and correcting method, electronic equipment and computer readable medium | |
| CN113592033B (en) | Oil tank image recognition model training method, oil tank image recognition method and device | |
| WO2019066231A1 (en) | Representative image generation | |
| CN115994805B (en) | Invoice and certificate archiving method, electronic equipment and computer readable medium | |
| CN113033707A (en) | Video classification method and device, readable medium and electronic equipment | |
| CN112883966A (en) | Image character recognition method, device, medium and electronic equipment | |
| CN110689285A (en) | Test method, test device, electronic equipment and computer readable storage medium | |
| CN113033682B (en) | Video classification method, device, readable medium and electronic equipment | |
| CN110334763B (en) | Model data file generation method, model data file generation device, model data file identification device, model data file generation apparatus, model data file identification apparatus, and model data file identification medium | |
| CN115100492A (en) | Yolov3 network training and PCB surface defect detection method and device | |
| CN111310858B (en) | Method and device for generating information | |
| CN114187557A (en) | Method, device, readable medium and electronic equipment for determining key frame | |
| CN114612909A (en) | Character recognition method and device, readable medium and electronic equipment | |
| CN111401182A (en) | Image detection method and device for feeding fence | |
| CN111680754A (en) | Image classification method and device, electronic equipment and computer-readable storage medium | |
| CN114523985B (en) | Unmanned vehicle motion decision method and device based on sensing result of sensor | |
| CN117591048B (en) | Task information processing method, device, electronic equipment and computer readable medium | |
| CN117494734B (en) | Switch paper box detection method, device, electronic equipment and computer readable medium | |
| CN117824974B (en) | Switch drop test method, device, electronic equipment and computer readable medium | |
| CN116580701B (en) | Alarm audio frequency identification method, device, electronic equipment and computer medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |