CN118261901A - Photovoltaic cell defect detection method, device and medium based on image processing - Google Patents
Photovoltaic cell defect detection method, device and medium based on image processing Download PDFInfo
- Publication number
- CN118261901A CN118261901A CN202410493532.7A CN202410493532A CN118261901A CN 118261901 A CN118261901 A CN 118261901A CN 202410493532 A CN202410493532 A CN 202410493532A CN 118261901 A CN118261901 A CN 118261901A
- Authority
- CN
- China
- Prior art keywords
- image
- vector
- preset
- defect
- preprocessed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000007547 defect Effects 0.000 title claims abstract description 89
- 238000012545 processing Methods 0.000 title claims abstract description 57
- 238000001514 detection method Methods 0.000 title abstract description 22
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 58
- 238000001914 filtration Methods 0.000 claims abstract description 52
- 238000000034 method Methods 0.000 claims abstract description 50
- 230000009466 transformation Effects 0.000 claims abstract description 9
- 239000013598 vector Substances 0.000 claims description 150
- 238000000605 extraction Methods 0.000 claims description 15
- 230000002829 reductive effect Effects 0.000 claims description 15
- 238000003860 storage Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 12
- 238000007781 pre-processing Methods 0.000 claims description 10
- 238000012216 screening Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 10
- 230000006870 function Effects 0.000 description 9
- 230000006872 improvement Effects 0.000 description 8
- 238000004519 manufacturing process Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 4
- 229910021419 crystalline silicon Inorganic materials 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000005520 cutting process Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000005336 cracking Methods 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 238000011900 installation process Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 229920001296 polysiloxane Polymers 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000010979 ruby Substances 0.000 description 1
- 229910001750 ruby Inorganic materials 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000008646 thermal stress Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The application relates to a photovoltaic cell defect detection method, device and medium based on image processing. The method comprises the following steps: acquiring an original image; carrying out gray level transformation on the original image to obtain a preprocessed image; based on a preset transverse filtering algorithm, obtaining a first image according to the preprocessed image; based on a preset longitudinal filtering algorithm, obtaining a second image according to the preprocessed image; the preset transverse filtering algorithm and the longitudinal filtering algorithm are used for eliminating pixels of a gentle part of an image and highlighting a defect part; obtaining a hidden crack defect area based on a defect algorithm according to the preprocessed image, the first image and the second image; the defect algorithm is used for precisely locating the defect area. The method and the device are used for solving the problem that the detection accuracy is low because the interference information in the image to be detected is not processed in the prior art and the detection algorithm is directly used for positioning.
Description
Technical Field
The application relates to the field of image processing, in particular to a method, a device and a medium for detecting defects of a photovoltaic cell based on image processing.
Background
In recent years, in order to reduce the cost, manufacturers of crystalline silicon components make the crystalline silicon components thinner, thereby reducing the capability of the battery piece for preventing mechanical damage, and further causing hidden cracking of the components in the transportation and installation processes. When the hidden crack causes the thin grid line to break, the thin grid line cannot transmit the collected current to the main grid line, and the battery piece can be partially or even completely disabled.
The prior art is based on deep learning defect detection. The method comprises the steps of obtaining a solar panel image sample, then sequentially carrying out preprocessing operation, dividing a training set and a testing machine, constructing a multi-scale combined convolutional neural network model, and then importing the training set into the model for training to realize defect detection. Or a novel deep multi-wavelet automatic encoder is designed to learn important characteristics of a solar cell defect image, a parameter transfer principle is applied, multiple similarity relations between a target domain and each source domain are constructed based on multiple similarity measurement, a multi-source domain migration manifold regular term is defined according to a smoothness assumption that a target domain classifier and a related source domain classifier have similar decision values on a target domain unmarked sample, a classifier suitable for the target domain is learned by means of the learned source domain classifier, and the designed solar cell defect target classifier is utilized to carry out classification detection on the target domain sample of the solar cell defect image.
However, the prior art does not process interference information in the image to be detected, and the detection algorithm is directly used for positioning, so that the detection precision is low.
Disclosure of Invention
Aiming at the problems, the application aims to provide a photovoltaic cell defect detection method, device and medium based on image processing.
According to a first aspect of an embodiment of the present application, there is provided a method for detecting defects of a photovoltaic cell based on image processing, including: acquiring an original image; carrying out gray level transformation on the original image to obtain a preprocessed image; based on a preset transverse filtering algorithm, obtaining a first image according to the preprocessed image; based on a preset longitudinal filtering algorithm, obtaining a second image according to the preprocessed image; the preset transverse filtering algorithm and the longitudinal filtering algorithm are used for eliminating pixels of a gentle part of an image and highlighting a defect part; obtaining a hidden crack defect area based on a defect algorithm according to the preprocessed image, the first image and the second image; the defect algorithm is used for precisely locating the defect area.
Further, the obtaining a first image based on the preset transversal filtering algorithm according to the preprocessed image includes: constructing base vectors with odd-numbered dimensions of n, presetting the maximum number of column vectors A as c, and presetting the maximum number of row vectors B as c and the number of base vectors as c; the basic vector comprises a column vector A and a row vector B; generating row vectors B which are not more than the number c according to a preset row vector B generation rule; generating column vectors A with the number not exceeding c according to a preset column vector A generation rule; the row vector B generation rule is as follows: all the element sums in the n-dimensional row vector B are zero, the absolute value of the 1 st element and the n-th element is 1, the (n+1)/2 th element is any integer randomly generated between 0 and n-2, the absolute values of the elements at the two sides of the (n+1)/2 th element are randomly generated and sequentially reduced, and the n-dimensional row vector B is an antisymmetric array; wherein, the column vector A generation rule is: the (n+1)/2 th element of the n-dimensional column vector A is any integer randomly generated between 0 and n-2, the absolute values of the elements at the two sides of the (n+1)/2 th element are randomly generated and sequentially reduced, and the column vector A is a symmetrical number column; selecting the row vector B to obtain a first row vector B; selecting the column vector A to obtain a first column vector A; multiplying the first column vector a by the first row vector B to obtain the transversal filter; and filtering the preprocessed image by using the transverse filter to obtain a first image. Further, the obtaining a second image based on the preset longitudinal filtering algorithm according to the preprocessed image includes: multiplying the row vector B transpose by the column vector a transpose to obtain the longitudinal filter; and filtering the preprocessed image by using the longitudinal filter to obtain a second image.
Further, the obtaining the hidden crack defect area based on the defect algorithm according to the preprocessed image, the first image and the second image includes: subtracting the first image from the preprocessed image to obtain a third image; subtracting the second image from the preprocessed image to obtain a fourth image; performing binarization extraction and region closing operation on the third image to obtain a first area to be selected; performing binarization extraction and region closing operation on the fourth image to obtain a second to-be-selected region; taking intersection sets of the first to-be-selected area and the second to-be-selected area to obtain a target hidden crack area collection set; and screening the target hidden crack region aggregate according to a preset threshold value to obtain a hidden crack defect region.
Further, the performing gray level transformation on the original image to obtain a preprocessed image includes: performing gray scale closing operation on the original image to obtain a closed operation processing image; carrying out gray scale on operation on the original image to obtain an on operation processing image; and comparing the gray value of the closed operation image with the gray value of the open operation image, and taking a smaller value to obtain a preprocessed image.
Further, the performing binarization extraction and region closing operation on the third image to obtain a first candidate region includes: after the third image is extracted in a binarization mode, circular closing operation is carried out, and a region with a preset radius range is communicated to obtain a circular hidden crack region collection of the first image; after the third image is extracted in a binarization mode, rectangular closed operation is carried out, and a preset rectangular size area is communicated to obtain a first image rectangular hidden crack area collection; and forming a first candidate region by the first image round hidden crack region collection and the first image rectangular hidden crack region collection.
According to a second aspect of an embodiment of the present application, there is provided a photovoltaic cell defect detection apparatus based on image processing, including: the image acquisition module is used for acquiring an original image; the image preprocessing module is used for carrying out gray level transformation on the original image to obtain a preprocessed image; the first image processing module is used for obtaining a first image according to the preprocessing image based on a preset transverse filtering algorithm; the second image processing module is used for obtaining a second image according to the preprocessing image based on a preset longitudinal filtering algorithm; the preset transverse filtering algorithm and the longitudinal filtering algorithm are used for eliminating pixels of a gentle part of an image and highlighting a defect part; the defect area positioning module is used for obtaining a hidden crack defect area based on a defect algorithm according to the preprocessed image, the first image and the second image; the defect algorithm is used for precisely locating the defect area.
Further, the first image processing module is specifically configured to: constructing a basic vector with an odd dimension of n, presetting a maximum number of column vectors A as c and a maximum number of row vectors B as c; the basic vector comprises a column vector A and a row vector B; generating row vectors B which are not more than the number c according to a preset row vector B generation rule; generating column vectors A with the number not exceeding c according to a preset column vector A generation rule; the row vector B generation rule is as follows: all elements in the n-dimensional row vector B sum to zero, the 1 st and nth elements absolute value is 1, the nthThe elements are any randomly generated integer between 0 and n 2 The absolute values of the elements on two sides of each element are randomly generated and sequentially reduced, and n-dimensional row vectors B are antisymmetric number columns; wherein, the column vector A generation rule is: n-dimensional column vector AThe elements are any randomly generated integer between 0 and n 2, the thThe absolute values of the elements on two sides of each element are randomly generated and sequentially reduced, and a column vector A is a symmetrical number column; selecting the row vector B to obtain a first row vector B; selecting the column vector A to obtain a first column vector A; multiplying the first column vector a by the first row vector B to obtain the transversal filter; and filtering the preprocessed image by using the transverse filter to obtain a first image. According to a third aspect of an embodiment of the present application, there is provided an electronic apparatus including: a memory for storing processor-executable instructions; the processor is used for reading the executable instructions from the memory and executing the instructions to realize the photovoltaic cell defect detection method based on image processing.
According to a fourth aspect of embodiments of the present application, there is provided a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the steps of a method for detecting defects of a photovoltaic cell based on image processing provided in the first aspect of the present application.
The technical scheme provided by the embodiment of the application can comprise the following beneficial effects:
In the production process of the photovoltaic cell, the physical production mode is used for generating the cell through linear cutting, and the interference of the attribute characteristics of the transverse direction and the longitudinal direction is generated. The application realizes a high-precision detection algorithm for eliminating the interference characteristics of the photovoltaic cell.
Drawings
For a clearer description of one or more embodiments of the present description or of the solutions of the prior art, the drawings that are necessary for the description of the embodiments or of the prior art will be briefly described, it being apparent that the drawings in the description that follow are only some of the embodiments described in the description, from which, for a person skilled in the art, other drawings can be obtained without inventive faculty.
FIG. 1 is a flowchart illustrating a method for detecting defects of a photovoltaic cell based on image processing, according to an exemplary embodiment;
FIG. 2 is a schematic view of a preprocessed image of a photovoltaic cell defect detection method based on image processing, according to an exemplary embodiment;
FIG. 3 is a first image schematic diagram illustrating a method for detecting defects in a photovoltaic cell based on image processing, according to an exemplary embodiment;
FIG. 4 is a second image schematic diagram illustrating a method for detecting defects in a photovoltaic cell based on image processing, according to an exemplary embodiment;
FIG. 5 is a third image schematic diagram illustrating a method for detecting defects in a photovoltaic cell based on image processing, according to an exemplary embodiment;
FIG. 6 is a fourth image schematic diagram illustrating a method for detecting defects in a photovoltaic cell based on image processing, according to an exemplary embodiment;
fig. 7 is a schematic diagram illustrating a photovoltaic cell defect detection apparatus based on image processing according to an exemplary embodiment.
Detailed Description
In order to enable a person skilled in the art to better understand the technical solutions in one or more embodiments of the present specification, the technical solutions in one or more embodiments of the present specification will be clearly and completely described below with reference to the drawings in one or more embodiments of the present specification, and it is obvious that the described embodiments are only some embodiments of the present specification, not all embodiments. All other embodiments, which can be made by one or more embodiments of the present disclosure without inventive faculty, are intended to be within the scope of the present disclosure.
In recent years, in order to reduce the cost, manufacturers of crystalline silicon components make the crystalline silicon components thinner, thereby reducing the capability of the battery piece for preventing mechanical damage, and further causing hidden cracking of the components in the transportation and installation processes. By hidden cracks is meant that when the battery sheet (assembly) is subjected to a large mechanical or thermal stress, hidden cracks may be generated in the battery cells that are not easily perceived by the naked eye. The hidden cracks can cause the fine grid lines to break, thereby causing partial or even complete failure of the battery cells. In the production process of the photovoltaic cell, the physical production mode is wire cutting. Wire cutting can create a number of interfering features on the battery plate. These features have either lateral or longitudinal properties, which greatly increases the difficulty of defect detection
Exemplary method one
Aiming at the scene and the technical problems, as shown in fig. 1, the embodiment of the application provides a photovoltaic cell defect detection method based on image processing, which comprises the following steps:
S101, acquiring an original image.
And acquiring an image of the photovoltaic cell, and acquiring an image to be detected.
S102, carrying out gray level transformation on the original image to obtain a preprocessed image. There is a disturbance in the preprocessed image with lateral and longitudinal directional properties, as in fig. 2.
And carrying out gray scale closing operation on the original image to obtain a closed operation processing image. The closing operation process is to perform expansion operation and then corrosion operation, so as to seal two finely connected blocks together.
And carrying out gray scale on operation on the original image to obtain an on operation processing image. The open operation process is to perform an erosion operation and then an expansion operation to separate two objects which are finely linked together.
And comparing the gray value of the closed operation image with the gray value of the open operation image, and taking a smaller value to obtain a preprocessed image, wherein the obtained preprocessed image has less noise and is convenient for subsequent use.
S103, obtaining a first image according to the preprocessed image based on a preset transverse filtering algorithm.
Constructing a basic vector with an odd dimension of n, presetting a maximum number of column vectors A as c and a maximum number of row vectors B as c; the base vector includes a column vector a and a row vector B.
The operator inputs the basic vector dimension parameter n, the column vector A and the row vector B number parameter c.
Generating row vectors B which are not more than the number c according to a preset row vector B generation rule.
The row vector B generation rule is as follows:
all elements in the n-dimensional row vector B sum to zero, the 1 st and nth elements absolute value is 1, the nth The elements are any randomly generated integer between 0 and n 2 The absolute values of the elements on both sides of each element are randomly generated and sequentially reduced, and the n-dimensional row vector B is an antisymmetric array.
D row vectors are actually generated, and when c is greater than d, d row vectors are generated, otherwise c row vectors are generated. Generating the column vectors A with the number not exceeding c according to a preset column vector A generation rule.
Wherein, the column vector A generation rule is:
n-dimensional column vector A The elements are any randomly generated integer between 0 and n 2, the thThe absolute values of the elements on both sides of each element are randomly generated and sequentially reduced, and the column vector A is a symmetrical number column.
And actually generating e column vectors, when c is greater than e, generating e row vectors, and otherwise, generating e column vectors. Selecting the row vector B to obtain a first row vector B; selecting the column vector A to obtain a first column vector A; the pick process is performed.
Multiplying the first column vector a by the first row vector B results in the transversal filter. Such a filter may bring the gray value at a particular location to zero.
The pre-processed image is filtered by using the transverse filter to obtain a first image, as shown in fig. 3, the first image eliminates most of longitudinal characteristics, darkens the background and highlights the defective area, and the gray value of the defective area changes more obviously along the transverse direction.
Convolving the preprocessed image with a transversal filter: for each pixel in the large matrix of the preprocessed image, the product of the surrounding pixels and the corresponding position elements of the filter matrix is calculated, and the results are added together, so that the finally obtained value is used as the new value of the pixel, and the primary filtering is completed, and the first image is finally obtained.
S104, based on a preset longitudinal filtering algorithm, a second image is obtained according to the preprocessed image, as shown in fig. 4, most of transverse characteristics of the second image are eliminated, the background is darkened, meanwhile, the defect area is highlighted, and the change of gray values of the defect area along the longitudinal direction is more obvious.
The transverse filtering algorithm and the longitudinal filtering algorithm are used for eliminating pixels in a gentle part of an image and highlighting a defect part.
The first image is obtained by using the processed image through transverse filtering, a lot of basic information of the first image is lost, and then the first image is used for longitudinal filtering to cause local distortion.
And (3) transposing the first row vector B by the first column vector A to obtain a longitudinal filter, and filtering the preprocessed image by using the longitudinal filter, namely performing convolution calculation on the longitudinal filter and the preprocessed image to obtain a second image.
The transverse filtering algorithm respectively eliminates or weakens transverse characteristics, and the longitudinal filtering algorithm respectively eliminates or weakens longitudinal characteristics, so that the disturbance characteristics with transverse and longitudinal direction attributes are reduced, defect parts are highlighted, and the difficulty of defect detection is reduced.
S105, obtaining a hidden crack defect area based on a defect algorithm according to the preprocessed image, the first image and the second image; the defect algorithm is used for precisely locating the defect area.
Subtracting the first image from the pre-processed image yields a third image, fig. 5, and subtracting the second image from the pre-processed image yields a fourth image, fig. 6.
The preprocessed image comprises transverse interference and longitudinal interference, and the transverse interference is removed through transverse filtering to obtain a first image. Therefore, the longitudinal interference in the third image is subtracted, the transverse interference is reserved, the characteristic that the gray value of the defect area changes along the longitudinal direction is obvious, and compared with the original image, the contrast of the defect area in the longitudinal direction is larger, so that the extraction of the defect area with the longitudinal change is facilitated.
The preprocessing image comprises transverse interference and longitudinal interference, and the second image is obtained after the longitudinal interference is removed through longitudinal filtering, so that the transverse interference in the fourth image is subtracted, the longitudinal interference is reserved, the characteristic that the gray value of the defect area changes along the transverse direction is obvious, and compared with the original image, the transverse contrast of the characteristic area is larger, and the extraction of the defect area with the transverse change is facilitated.
Performing binarization extraction and region closing operation on the third image to obtain a first area to be selected:
After the third image is extracted in a binarization mode, circular closing operation is carried out, and a region with a preset radius range is communicated to obtain a circular hidden crack region collection of the first image; and performing binarization extraction on the third image, and then performing rectangular closed operation, and communicating a preset rectangular size area to obtain a first image rectangular hidden crack area collection. And forming a first candidate region by the first image round hidden crack region collection and the first image rectangular hidden crack region collection.
Rectangular closure operations are good at processing image areas with rectangular or right-angled features, such as lines, rectangular borders, etc., filling right-angled shaped holes and connecting right-angled edges, and can precisely refine and strengthen borders when processing straight line or square features. The circular closure operation is more suitable for processing image features with smooth edges and more circular or approximately circular shapes, and can better fill and connect curve boundaries and circular holes with smaller radiuses. And respectively using rectangular closed operation and circular closed operation for extraction, and considering hidden crack characteristics of different forms.
Rectangular and circular closed operations can cover most image region features.
Performing binarization extraction and region closing operation on the fourth image to obtain a second candidate region:
After the fourth image is extracted in a binarization mode, circular closing operation is carried out, and a region with a preset radius range is communicated to obtain a circular hidden crack region collection of the second image; and performing binarization extraction on the fourth image, and then performing rectangular closed operation, and communicating a preset rectangular size area to obtain a second image rectangular hidden crack area collection. And forming a second candidate region by the second image round hidden crack region collection and the second image rectangular hidden crack region collection.
And taking intersection sets of the first candidate area and the second candidate area to obtain a target hidden crack area set.
And screening the target hidden crack region aggregate according to a preset threshold value to obtain a hidden crack defect region.
And carrying out first screening on the target hidden crack region according to the height and width characteristics of the minimum circumscribed rectangle of the preset single region to obtain a primary hidden crack region set, and carrying out second screening on the primary hidden crack region according to the area characteristics of the preset minimum single region to obtain a hidden crack region.
The pretreatment image is processed based on a pre-preset transverse filtering algorithm, transverse interference is eliminated by the transverse filtering algorithm for the pretreatment image processing to obtain a first image only containing longitudinal interference, the longitudinal filtering algorithm for the pretreatment image processing is used for the longitudinal filtering algorithm for the pretreatment image processing to obtain a second image only containing transverse interference, the first image only containing longitudinal interference is subtracted from the pretreatment image to obtain a third image only containing transverse interference, the first image only containing transverse interference is subtracted from the pretreatment image to obtain a fourth image only containing longitudinal interference, interference is eliminated, difficulty in defect detection is greatly reduced, accuracy of a detection algorithm is increased, and a hidden crack defect area is obtained.
Exemplary apparatus
In an embodiment of the present application, as shown in fig. 7, the image processing device includes an image acquisition module 701, an image preprocessing module 702, a first image processing module 703, a second image processing module 704, and a defect area localization module 705
An image acquisition module 701, configured to acquire an original image;
an image preprocessing module 702, configured to perform gray level transformation on the original image to obtain a preprocessed image; performing gray scale closing operation on the original image to obtain a closed operation processing image; carrying out gray scale on operation on the original image to obtain an on operation processing image; and comparing the gray value of the closed operation image with the gray value of the open operation image, and taking a smaller value to obtain a preprocessed image.
A first image processing module 703, configured to obtain a first image according to the preprocessed image based on a preset transversal filtering algorithm; constructing a basic vector with an odd dimension of n, presetting a maximum number of column vectors A as c and a maximum number of row vectors B as c; the basic vector comprises a column vector A and a row vector B; generating row vectors B which are not more than the number c according to a preset row vector B generation rule; generating column vectors A with the number not exceeding c according to a preset column vector A generation rule; the row vector B generation rule is as follows: all elements in the n-dimensional row vector B sum to zero, the 1 st and nth elements absolute value is 1, the nthThe elements are any randomly generated integer between 0 and n 2 The absolute values of the elements on two sides of each element are randomly generated and sequentially reduced, and n-dimensional row vectors B are antisymmetric number columns; wherein, the column vector A generation rule is: n-dimensional column vector AThe elements are any randomly generated integer between 0 and n 2, the thThe absolute values of the elements on two sides of each element are randomly generated and sequentially reduced, and a column vector A is a symmetrical number column; selecting the row vector B to obtain a first row vector B; selecting the column vector A to obtain a first column vector A; multiplying the first column vector a by the first row vector B to obtain the transversal filter; and filtering the preprocessed image by using the transverse filter to obtain a first image. A second image processing module 704, configured to obtain a second image according to the preprocessed image based on a preset longitudinal filtering algorithm; the preset transverse filtering algorithm and the longitudinal filtering algorithm are used for eliminating pixels of a gentle part of an image and highlighting a defect part; multiplying the row vector B transpose by the column vector a transpose to obtain the longitudinal filter; and filtering the preprocessed image by using the longitudinal filter to obtain a second image.
The defect area positioning module 705 is configured to obtain a hidden crack defect area based on a defect algorithm according to the preprocessed image, the first image, and the second image; the defect algorithm is used for precisely locating the defect area. Subtracting the first image from the preprocessed image to obtain a third image; subtracting the second image from the preprocessed image to obtain a fourth image; performing binarization extraction and region closing operation on the third image to obtain a first area to be selected; performing binarization extraction and region closing operation on the fourth image to obtain a second to-be-selected region; taking intersection sets of the first to-be-selected area and the second to-be-selected area to obtain a target hidden crack area collection set; and screening the target hidden crack region aggregate according to a preset threshold value to obtain a hidden crack defect region. After the third image is extracted in a binarization mode, circular closing operation is carried out, and a region with a preset radius range is communicated to obtain a circular hidden crack region collection of the first image; after the third image is extracted in a binarization mode, rectangular closed operation is carried out, and a preset rectangular size area is communicated to obtain a first image rectangular hidden crack area collection; and forming a first candidate region by the first image round hidden crack region collection and the first image rectangular hidden crack region collection.
Exemplary electronic device
The present embodiment proposes an electronic device including: the photovoltaic cell defect detection method based on image processing according to any one of the preceding embodiments is performed by one or more processors, and an internal memory and an external memory, wherein the internal memory stores instructions that, when executed by the one or more processors, cause the one or more processors to perform the method.
Wherein the processor is configured to perform all or part of the steps in the image processing-based method for detecting defects in a photovoltaic cell as described in the embodiments. The memory is used to store various types of data, which may include, for example, instructions for any application or method in the electronic device, as well as application-related data.
The Processor may be an Application SPECIFIC INTEGRATED Cricuit (ASIC), a digital signal Processor (DIGITAL SIGNAL Processor, DSP), a programmable logic device (Programmable Logic Device, PLD), a field programmable gate array (Field Programmable GATE ARRAY, FPGA), a controller, a microcontroller, a microprocessor, or other electronic components, for executing the method for detecting defects of a photovoltaic cell based on image processing described in the embodiment.
Computer storage medium
The computer readable storage medium stores thereon a computer program which, when executed by one or more processors, implements a method for detecting defects of a photovoltaic cell based on image processing as described in any of the foregoing embodiments.
The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In the 30 s of the 20 th century, improvements to one technology could clearly be distinguished as improvements in hardware (e.g., improvements to circuit structures such as diodes, transistors, switches, etc.) or software (improvements to the process flow). However, with the development of technology, many improvements of the current method flows can be regarded as direct improvements of hardware circuit structures. Designers almost always obtain corresponding hardware circuit structures by programming improved method flows into hardware circuits. Therefore, an improvement of a method flow cannot be said to be realized by a hardware entity module. For example, a programmable logic device (Programmable Logic Device, PLD) (e.g., field programmable gate array (Field Programmable GATE ARRAY, FPGA)) is an integrated circuit whose logic functions are determined by user programming of the device. A designer programs to "integrate" a digital system onto a PLD without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Moreover, nowadays, instead of manually manufacturing integrated circuit chips, such programming is mostly implemented with "logic compiler (logic compiler)" software, which is similar to the software compiler used in program development and writing, and the original code before being compiled is also written in a specific programming language, which is called hardware description language (Hardware Description Language, HDL), but HDL is not just one, but a plurality of kinds, such as ABEL(Advanced Boolean Expression Language)、AHDL(Altera Hardware Description Language)、Confluence、CUPL(Cornell University Programming Language)、HDCal、JHDL(Java Hardware Description Language)、Lava、Lola、MyHDL、PALASM、RHDL(Ruby Hardware Description Language), and VHDL (Very-High-SPEED INTEGRATED Circuit Hardware Description Language) and Verilog are currently most commonly used. It will also be apparent to those skilled in the art that a hardware circuit implementing the logic method flow can be readily obtained by merely slightly programming the method flow into an integrated circuit using several of the hardware description languages described above.
The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer readable medium storing computer readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, application SPECIFIC INTEGRATED Circuits (ASICs), programmable logic controllers, and embedded microcontrollers, examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, atmel AT91SAM, microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic of the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller in a pure computer readable program code, it is well possible to implement the same functionality by logically programming the method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. Such a controller may thus be regarded as a kind of hardware component, and means for performing various functions included therein may also be regarded as structures within the hardware component. Or even means for achieving the various functions may be regarded as either software modules implementing the methods or structures within hardware components.
The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. One typical implementation is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being functionally divided into various units, respectively. Of course, the functions of each unit may be implemented in the same piece or pieces of software and/or hardware when implementing the embodiments of the present specification.
One skilled in the relevant art will recognize that one or more embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, one or more embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present description can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
The present description is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the specification. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
One or more embodiments of the present specification may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. One or more embodiments of the specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.
The foregoing description is by way of example only and is not intended to limit the present disclosure. Various modifications and changes may occur to those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. that fall within the spirit and principles of the present document are intended to be included within the scope of the claims of the present document.
Claims (10)
1. The method for detecting the defects of the photovoltaic cell based on image processing is characterized by comprising the following steps of:
Acquiring an original image;
Carrying out gray level transformation on the original image to obtain a preprocessed image;
Based on a preset transverse filtering algorithm, obtaining a first image according to the preprocessed image;
Based on a preset longitudinal filtering algorithm, obtaining a second image according to the preprocessed image; the preset transverse filtering algorithm and the longitudinal filtering algorithm are used for eliminating pixels of a gentle part of an image and highlighting a defect part;
Obtaining a hidden crack defect area based on a defect algorithm according to the preprocessed image, the first image and the second image; the defect algorithm is used for precisely locating the defect area.
2. The method according to claim 1, wherein the obtaining a first image from the preprocessed image based on a preset transversal filtering algorithm comprises:
Constructing a basic vector with an odd dimension of n, presetting a maximum number of column vectors A as c and a maximum number of row vectors B as c; the basic vector comprises a column vector A and a row vector B;
generating row vectors B which are not more than the number c according to a preset row vector B generation rule;
generating column vectors A with the number not exceeding c according to a preset column vector A generation rule;
The row vector B generation rule is as follows: all elements in the n-dimensional row vector B sum to zero, the 1 st and nth elements absolute value is 1, the nth The elements are any randomly generated integer between 0 and n 2 The absolute values of the elements on two sides of each element are randomly generated and sequentially reduced, and n-dimensional row vectors B are antisymmetric number columns;
Wherein, the column vector A generation rule is: n-dimensional column vector A The elements are any randomly generated integer between 0 and n 2, the thThe absolute values of the elements on two sides of each element are randomly generated and sequentially reduced, and a column vector A is a symmetrical number column;
selecting the row vector B to obtain a first row vector B; selecting the column vector A to obtain a first column vector A;
multiplying the first column vector a by the first row vector B to obtain the transversal filter; and filtering the preprocessed image by using the transverse filter to obtain a first image.
3. The method according to claim 2, wherein the obtaining a second image from the preprocessed image based on a preset longitudinal filtering algorithm comprises:
Multiplying the row vector B transpose by the column vector a transpose to obtain the longitudinal filter;
and filtering the preprocessed image by using the longitudinal filter to obtain a second image.
4. The method of claim 1, wherein the deriving the hidden crack defect region based on a defect algorithm based on the pre-processed image, the first image, and the second image comprises:
Subtracting the first image from the preprocessed image to obtain a third image;
subtracting the second image from the preprocessed image to obtain a fourth image;
Performing binarization extraction and region closing operation on the third image to obtain a first area to be selected;
Performing binarization extraction and region closing operation on the fourth image to obtain a second to-be-selected region;
Taking intersection sets of the first to-be-selected area and the second to-be-selected area to obtain a target hidden crack area collection set;
and screening the target hidden crack region aggregate according to a preset threshold value to obtain a hidden crack defect region.
5. The method of claim 1, wherein said subjecting said original image to a gray scale transformation results in a preprocessed image, comprising:
performing gray scale closing operation on the original image to obtain a closed operation processing image;
Carrying out gray scale on operation on the original image to obtain an on operation processing image;
And comparing the gray value of the closed operation image with the gray value of the open operation image, and taking a smaller value to obtain a preprocessed image.
6. The method of claim 4, wherein performing the binarization extraction and region-wise block operation on the third image to obtain a first candidate region comprises:
After the third image is extracted in a binarization mode, circular closing operation is carried out, and a region with a preset radius range is communicated to obtain a circular hidden crack region collection of the first image;
after the third image is extracted in a binarization mode, rectangular closed operation is carried out, and a preset rectangular size area is communicated to obtain a first image rectangular hidden crack area collection;
And forming a first candidate region by the first image round hidden crack region collection and the first image rectangular hidden crack region collection.
7. The device for detecting the defects of the photovoltaic cell based on image processing is characterized by comprising the following components:
The image acquisition module is used for acquiring an original image;
the image preprocessing module is used for carrying out gray level transformation on the original image to obtain a preprocessed image;
The first image processing module is used for obtaining a first image according to the preprocessing image based on a preset transverse filtering algorithm;
The second image processing module is used for obtaining a second image according to the preprocessing image based on a preset longitudinal filtering algorithm; the preset transverse filtering algorithm and the longitudinal filtering algorithm are used for eliminating pixels of a gentle part of an image and highlighting a defect part;
the defect area positioning module is used for obtaining a hidden crack defect area based on a defect algorithm according to the preprocessed image, the first image and the second image; the defect algorithm is used for precisely locating the defect area.
8. The apparatus of claim 7, wherein the first image processing module is specifically configured to:
Constructing a basic vector with an odd dimension of n, presetting a maximum number of column vectors A as c and a maximum number of row vectors B as c; the basic vector comprises a column vector A and a row vector B;
generating row vectors B which are not more than the number c according to a preset row vector B generation rule;
generating column vectors A with the number not exceeding c according to a preset column vector A generation rule;
The row vector B generation rule is as follows: all elements in the n-dimensional row vector B sum to zero, the 1 st and nth elements absolute value is 1, the nth The elements are any randomly generated integer between 0 and n 2 The absolute values of the elements on two sides of each element are randomly generated and sequentially reduced, and n-dimensional row vectors B are antisymmetric number columns;
Wherein, the column vector A generation rule is: n-dimensional column vector A The elements are any randomly generated integer between 0 and n 2, the thThe absolute values of the elements on two sides of each element are randomly generated and sequentially reduced, and a column vector A is a symmetrical number column;
selecting the row vector B to obtain a first row vector B; selecting the column vector A to obtain a first column vector A;
multiplying the first column vector a by the first row vector B to obtain the transversal filter; and filtering the preprocessed image by using the transverse filter to obtain a first image.
9. An electronic device, comprising:
A memory for storing a computer program;
A processor for implementing the steps of a method for detecting defects of a photovoltaic cell based on image processing according to any one of claims 1 to 6 when executing said computer program.
10. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the method for detecting defects of a photovoltaic cell based on image processing according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410493532.7A CN118261901A (en) | 2024-04-23 | 2024-04-23 | Photovoltaic cell defect detection method, device and medium based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410493532.7A CN118261901A (en) | 2024-04-23 | 2024-04-23 | Photovoltaic cell defect detection method, device and medium based on image processing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118261901A true CN118261901A (en) | 2024-06-28 |
Family
ID=91613113
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410493532.7A Pending CN118261901A (en) | 2024-04-23 | 2024-04-23 | Photovoltaic cell defect detection method, device and medium based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118261901A (en) |
-
2024
- 2024-04-23 CN CN202410493532.7A patent/CN118261901A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109034183B (en) | Target detection method, device and equipment | |
| CN112927253B (en) | Rock core FIB-SEM image segmentation method based on convolutional neural network | |
| CN109615171B (en) | Feature threshold determining method and device and problem object determining method and device | |
| CN116205290A (en) | Knowledge distillation method and device based on intermediate feature knowledge fusion | |
| CN116152933A (en) | Training method, device, equipment and storage medium of anomaly detection model | |
| CN117197781B (en) | Traffic sign recognition method and device, storage medium and electronic equipment | |
| CN115049927A (en) | SegNet-based SAR image bridge detection method and device and storage medium | |
| CN116342888B (en) | Method and device for training segmentation model based on sparse labeling | |
| CN118261901A (en) | Photovoltaic cell defect detection method, device and medium based on image processing | |
| CN115830633B (en) | Pedestrian re-recognition method and system based on multi-task learning residual neural network | |
| CN114359935A (en) | Model training and form recognition method and device | |
| CN117575886B (en) | Image edge detector, detection method, electronic equipment and medium | |
| CN111523539A (en) | Character detection method and device | |
| CN112541507A (en) | Multi-scale convolutional neural network feature extraction method, system, medium and application | |
| CN116451808B (en) | Model training method and device, storage medium and electronic equipment | |
| CN116363390B (en) | Infrared dim target detection method and device, storage medium and electronic equipment | |
| CN116681980B (en) | Deep learning-based large-deletion-rate image restoration method, device and storage medium | |
| CN112115952B (en) | Image classification method, device and medium based on full convolution neural network | |
| CN117893396B (en) | Image edge detection task execution method and device based on resistive random access memory | |
| CN116188919B (en) | Test method and device, readable storage medium and electronic equipment | |
| CN116432048A (en) | Abnormality detection method and device, storage medium and electronic equipment | |
| CN117575941A (en) | Image denoising method based on self-adaptive value range filtering, electronic equipment and medium | |
| CN116977732A (en) | Subway tunnel water seepage detection method and device based on point cloud reflection intensity | |
| CN116894819A (en) | Concrete structure surface pixel level defect detection method, device and storage medium | |
| CN117011147A (en) | Infrared remote sensing image feature detection and splicing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |