CN113936002A - Period extraction method and device, computer equipment and readable storage medium - Google Patents
Period extraction method and device, computer equipment and readable storage medium Download PDFInfo
- Publication number
- CN113936002A CN113936002A CN202111550080.4A CN202111550080A CN113936002A CN 113936002 A CN113936002 A CN 113936002A CN 202111550080 A CN202111550080 A CN 202111550080A CN 113936002 A CN113936002 A CN 113936002A
- Authority
- CN
- China
- Prior art keywords
- image
- period
- determining
- sequence
- autocorrelation function
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30121—CRT, LCD or plasma display
Abstract
The invention provides a period extraction method, a period extraction device, computer equipment and a readable storage medium, wherein the method comprises the following steps: acquiring an image of a display panel to be detected; wherein, the image comprises characteristic regions which are periodically distributed; the characteristic region comprises a key structure on the display panel to be detected; preprocessing the image to obtain a binary image; the binary image comprises a first pixel point and a second pixel point; the second pixel point corresponds to the characteristic region; and performing autocorrelation analysis on all the second pixel points, and extracting the period of the characteristic region. Compared with the mode of manually setting the period in the prior art, the method can quickly and accurately automatically extract the period of the image based on the self-phase analysis of the key features in the image, avoids the complexity of manually setting the period, improves the extraction efficiency, and is suitable for different display panels to be detected.
Description
Technical Field
The invention relates to the technical field of image analysis, in particular to a period extraction method, a period extraction device, computer equipment and a readable storage medium.
Background
In the field of display panel inspection, the automatic optical (visual) inspection technology (AOI) for surface defects based on optical image sensing instead of manual visual inspection of surface defects has gradually become an important means for surface defect inspection.
In the surface defect automatic optical (visual) detection technology, it is often necessary to extract a period with periodic characteristics in an image, further intercept an image without a defect period as a template, and compare the image with other images with periodic characteristics, thereby automatically locating a target defect.
However, many current display panel factories cannot directly calculate the period of the periodic features in the image according to the image, but manually set the period, and once the process is changed or the products are different, the period needs to be reset, so that the operation is very inconvenient, and the detection efficiency is reduced.
Disclosure of Invention
An objective of the present invention is to provide a method, an apparatus, a computer device and a readable storage medium for extracting periodic features, so as to solve the above technical problems.
Embodiments of the invention may be implemented as follows:
in a first aspect, the present invention provides a method for periodic extraction, the method comprising: acquiring an image of a display panel to be detected; wherein, the image comprises characteristic regions which are periodically distributed; the characteristic region comprises a key structure on the display panel to be detected; preprocessing the image to obtain a binary image; the binary image comprises a first pixel point and a second pixel point; the second pixel point corresponds to the characteristic region; and performing autocorrelation analysis on all the second pixel points, and extracting the period of the characteristic region.
Through the technical scheme, the image of the display panel to be detected can be rapidly and accurately extracted periodically, the complexity of manually setting the period is avoided, the extraction efficiency is improved, and the method is suitable for different display panels to be detected.
In an optional embodiment, performing autocorrelation analysis on all the second pixel points to extract a period of the feature region includes: determining a first autocorrelation function of all the second pixel points in the horizontal direction and a second autocorrelation function of all the second pixel points in the vertical direction; the first autocorrelation function is used for measuring the correlation between the quantity of the second pixel points corresponding to each row offset in the horizontal direction; the second autocorrelation function represents correlation between the quantity of second pixels corresponding to each column offset in the vertical direction; determining the period of the characteristic region in the horizontal direction from the first autocorrelation function; determining a period of the feature region in the vertical direction from the second autocorrelation function.
By the aid of the self-correlation analysis mode, the period of the image can be determined quickly and accurately, and the efficiency of period extraction is improved.
In an optional embodiment, in the binarized image, the number of the second pixel points existing in each row is counted to form a first sequence, and the number of the second pixel points existing in each column is counted to form a second sequence; determining the first autocorrelation function of all the second pixel points in the horizontal direction according to the first sequence; and determining the second autocorrelation function of the second pixel point in the vertical direction according to the second sequence.
The autocorrelation analysis is carried out by establishing autocorrelation functions among the pixel points corresponding to the periodically distributed features, so that the obtained period is matched with the feature region, and the reliability of the extraction result is improved.
In an optional embodiment, determining the period of the feature region in the horizontal direction from the first autocorrelation function includes: carrying out maximum solving on the first autocorrelation function to obtain a plurality of local maximum autocorrelation coefficients; determining a distance difference between a position corresponding to a largest maximum value of the local maximum autocorrelation coefficients and an image start pixel position as a period of the feature region in the horizontal direction.
By analyzing the local maximum value of the first autocorrelation function, the size relationship of autocorrelation among all positions of the image in the horizontal direction can be determined, so that the periodic features of the image in the horizontal direction can be quickly positioned on the basis of the size relationship.
In an optional embodiment, determining the period of the feature region in the vertical direction from the second autocorrelation function includes: carrying out maximum solving on the second autocorrelation function to obtain positions corresponding to the local maximum autocorrelation coefficients; determining a distance difference between a position corresponding to one maximum value of the local maximum autocorrelation coefficients and a start pixel position of the binarized image as a period of the feature region in the vertical direction.
By analyzing the local maximum value of the second autocorrelation function, the size relationship of autocorrelation among positions of the image in the vertical direction can be determined, so that the periodic features of the image in the vertical direction can be quickly positioned on the basis of the size relationship.
In an optional embodiment, determining, according to the first sequence, the first autocorrelation function of the second pixel point in the horizontal direction includes: determining the mean value and the variance of the first sequence, and calculating an autocovariance function corresponding to the first sequence according to the mean value; and determining the first autocorrelation function according to the length of the first sequence, the autocovariance function corresponding to the first sequence and the variance.
By the technical scheme, the accumulated distribution of the pixel points corresponding to the key features in the horizontal direction can be quickly determined, so that the first autocorrelation function is determined, and a basis is provided for the subsequent extraction of the periodic features of the image in the horizontal direction based on the first autocorrelation function.
In an optional embodiment, determining, according to the second sequence, the second autocorrelation function of the second pixel point in the vertical direction includes: determining the mean value and the variance of the second sequence, and calculating an autocovariance function corresponding to the second sequence according to the mean value; and determining the second autocorrelation function according to the length of the second sequence, the autocovariance function corresponding to the second sequence and the variance.
By the technical scheme, the accumulated distribution of the pixel points corresponding to the key features in the vertical direction can be quickly determined, so that the second autocorrelation function is determined, and a basis is provided for the subsequent extraction of the periodic features of the image in the vertical direction based on the second autocorrelation function.
In an optional embodiment, the preprocessing the image to obtain a binarized image comprises: carrying out image transformation and image enhancement on the image to obtain a gray level image; according to a first pixel value and a second pixel value, carrying out binarization conversion on the gray-scale image to obtain a binarization image, wherein the first pixel value corresponds to the first pixel point; the second pixel value corresponds to the second pixel point.
By the technical scheme, the key features in the image can be extracted, the period of the image is extracted quickly and accurately based on the accumulative distribution of the key features, and the period extraction efficiency is improved.
In an optional embodiment, the method further comprises: and processing the binary image by threshold segmentation to determine the characteristic region.
By the technical scheme, noise factors in the image can be eliminated, and the accuracy of periodic extraction is ensured.
In a second aspect, the present invention provides a cycle extracting apparatus, comprising: the acquisition module is used for acquiring an image of a display panel to be detected; the image comprises characteristic regions which are periodically distributed; the characteristic region is a key shape region on the display panel to be detected; the processing module is used for preprocessing the image to obtain a binary image, and the binary image comprises first pixel points and second pixel points; the second pixel point corresponds to the characteristic region; and the extraction module is used for performing autocorrelation analysis on all the second pixel points and extracting the period of the characteristic region.
In a third aspect, the present invention provides a computer device comprising a processor and a memory, the memory storing a computer program executable by the processor, the processor being capable of executing the computer program to implement the cycle extraction method of the first aspect.
In a fourth aspect, the present invention provides a readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the cycle extraction method according to the first aspect.
The invention provides a period extraction method, a period extraction device, computer equipment and a readable storage medium, wherein the method comprises the following steps: acquiring an image of a display panel to be detected; wherein, the image comprises characteristic regions which are periodically distributed; the characteristic region comprises a key structure on the display panel to be detected; preprocessing the image to obtain a binary image; the binary image comprises a first pixel point and a second pixel point; the second pixel point corresponds to the characteristic region; and performing autocorrelation analysis on all the second pixel points, and extracting the period of the characteristic region. Compared with the mode of manually setting the period in the prior art, the method can quickly and accurately automatically extract the period of the image based on the self-phase analysis of the key features in the image, avoids the complexity of manually setting the period, improves the extraction efficiency, and is suitable for different display panels to be detected.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
FIG. 1 is a schematic flow chart of a periodic extraction method provided by an embodiment of the present invention;
FIG. 2 is an image of several feature areas with periodic distribution provided by an embodiment of the present invention;
fig. 3 is a schematic diagram of a binarized image according to an embodiment of the present invention;
fig. 4 is a schematic flowchart of step S102 provided by the embodiment of the present invention;
fig. 5 is a schematic flowchart of step S103 provided by the embodiment of the present invention;
fig. 6 is a diagram illustrating an accumulation distribution of second pixels in a horizontal direction according to an embodiment of the present invention;
fig. 7 is a cumulative distribution diagram of second pixel points in the vertical direction according to the embodiment of the present invention;
fig. 8 is a diagram illustrating a first autocorrelation function of a second pixel in the horizontal direction according to an embodiment of the present invention;
fig. 9 is a diagram illustrating a second autocorrelation function of a second pixel point in the vertical direction according to an embodiment of the present invention;
FIG. 10 is a schematic flow chart of step S103-2 provided by an embodiment of the present invention;
FIG. 11 is a functional block diagram of a cycle extracting apparatus according to an embodiment of the present invention;
fig. 12 is a block diagram of a computer device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
In the description of the present invention, it should be noted that if the terms "upper", "lower", "inside", "outside", etc. indicate an orientation or a positional relationship based on that shown in the drawings or that the product of the present invention is used as it is, this is only for convenience of description and simplification of the description, and it does not indicate or imply that the device or the element referred to must have a specific orientation, be constructed in a specific orientation, and be operated, and thus should not be construed as limiting the present invention.
Furthermore, the appearances of the terms "first," "second," and the like, if any, are used solely to distinguish one from another and are not to be construed as indicating or implying relative importance.
It should be noted that the features of the embodiments of the present invention may be combined with each other without conflict.
Defects of various forms can be generated due to factors such as process fluctuation, machine table difference and the like in the manufacturing process of the display panel, the defects not only affect the performance of products and cause huge economic loss to manufacturers, but also even harm the personal safety of users in severe cases. Therefore, the detection of the product is particularly important.
With the development of artificial intelligence and corresponding automatic detection systems, the efficiency and accuracy of defect detection of display panels are higher and higher. In the detection process, in order to save labor, it is usually necessary to calculate the period of the image for each frame of the display panel image, then intercept the image without defect period as a template, and compare it with other images with period, so as to automatically locate the target defect.
However, many current display panel factories cannot directly calculate the period of the periodic features in the image according to the image, but manually set the period, and once the process is changed or the product is different, the period needs to be reset, which is very inconvenient to operate and reduces the detection efficiency.
In order to solve the above technical problem, an embodiment of the present invention provides a period extraction method, please refer to fig. 1, where fig. 1 is a schematic flowchart of the period extraction method provided in the embodiment of the present invention, and the method includes:
s101, obtaining an image of a display panel to be detected.
Wherein, the image comprises characteristic regions which are periodically distributed; the feature area includes a key structure on the display panel to be detected.
For the convenience of understanding the feature regions in the periodic distribution, please refer to fig. 2, in which fig. 2 is an image of various feature regions in the periodic distribution provided by the embodiment of the present invention, and the dotted line frame is the feature regions in the periodic distribution. It is understood that the key structures described above refer to metal lines (data lines) and silicon island regions (tft regions) of the display panel to be tested, and as can be seen from the various images shown in fig. 2, the data lines and the tft regions in each image exhibit a periodic distribution.
S102, preprocessing the image to obtain a binary image.
The binary image comprises a first pixel point and a second pixel point; the second pixel point corresponds to the characteristic region;
the binary image in the embodiment of the invention can highlight the position of the key feature in the image, and the key region is highlighted because the key feature is distinguished by the pixel points different from the background, so that the self-correlation analysis among the pixel points in the key region can be conveniently carried out subsequently.
In a possible implementation manner, the pixel value of the first pixel point may be set to 255, the second pixel point is set to 0, the obtained binarized image may be as shown in fig. 3, and fig. 3 is a schematic diagram of a binarized image according to an embodiment of the present invention, where a pixel point of a white region corresponds to a feature region, and a pixel point of a black region may be considered as a background.
It should be noted that the binarized image shown in fig. 3 is only an example, and in order to highlight the key feature and the background, the key feature and the background may also be marked by using pixel values with other color differences, which is not limited herein.
S103, performing autocorrelation analysis on all the second pixel points, and extracting the period of the characteristic region.
It can be understood that, since the second pixel points are all the pixel points representing the key features, the distribution condition among the key features can be determined by performing autocorrelation analysis on all the second pixel points, and then the period is determined based on the distribution condition.
Optionally, regarding step S102, a possible implementation manner is further provided in the embodiment of the present invention, please refer to fig. 4, where fig. 4 is a schematic flowchart of step S102 provided in the embodiment of the present invention, and step S102 may include:
s102-1, carrying out image transformation and image enhancement on the image to obtain a gray level image.
In this embodiment, HSV (Hue, Saturation, Value) transformation is performed on an image to extract S channel (Saturation channel) information of the image, and then gamma transformation is used to enhance the image to obtain a grayscale corresponding to the image.
S102-2, performing binarization conversion on the gray-scale image according to the first pixel value and the second pixel value to obtain a binarized image, wherein the first pixel value corresponds to a first pixel point; the second pixel value corresponds to a second pixel point.
In one possible implementation, in the process of performing binarization conversion on the grayscale map, threshold segmentation (optional switching operation) may be used to determine the region where the key feature in the image is located, so as to generate a binarized image as shown in fig. 3.
The binary image obtained by the method does not have other image noises, so that the characteristic region can be highlighted, and the subsequent period extraction is facilitated.
Optionally, an embodiment of the present invention further provides an implementation manner that may perform autocorrelation analysis on all second pixel points to extract a period of the feature region, specifically, please refer to fig. 5, where fig. 5 is a schematic flowchart of step S103 provided in the embodiment of the present invention, and step S103 may include:
s103-1, determining a first autocorrelation function of all second pixel points in the horizontal direction and a second autocorrelation function of all second pixel points in the vertical direction;
the first autocorrelation function is used for measuring correlation between the quantity of second pixel points corresponding to each row offset in the horizontal direction; and the second autocorrelation function represents the correlation between the number of second pixels corresponding to each column offset in the vertical direction.
S103-2, determining the period of the characteristic region in the horizontal direction from the first autocorrelation function;
and S103-3, determining the period of the characteristic region in the vertical direction from the second autocorrelation function.
In a possible implementation manner, regarding step S103-1, an embodiment of the present invention further provides a possible implementation manner, that is, step S103-1 may include the following steps:
From the binarized image shown in fig. 3, white pixels correspond to key features, and therefore, the number of white pixels in each line is counted to form a first sequence X, and then X can be in the form of: x = { XiH, i =1,2, …, n, where xiRepresenting the number of white pixel points in the ith row, and representing the total row number by n;
similarly, the number of white pixels in each column is counted to form a second sequence Y, and Y can be in the form of { Y }jJ =1,2, …, m, wherein yjThe number of white pixel points in the jth column is represented, m represents the total row number, and n and m can be the same or different and are determined according to the size of the image.
For convenience of understanding, the distribution diagram of the second pixel points of the first sequence may be as shown in fig. 6, where fig. 6 is a cumulative distribution diagram of the second pixel points in the horizontal direction according to the embodiment of the present invention, where the ordinate represents the number of the second pixel points, and the abscissa represents the rows of the image; fig. 7 is a cumulative distribution diagram of second pixel points in the vertical direction according to the embodiment of the present invention, in which the ordinate represents the number of the second pixel points, and the abscissa represents the columns of the image.
Step 2, determining a first autocorrelation function of all second pixel points in the horizontal direction according to the first sequence;
and 3, determining a second autocorrelation function of the second pixel point in the vertical direction according to the second sequence.
The following describes in detail an embodiment of obtaining the first autocorrelation function, taking the first sequence as an example. For a first sequence X = { xi }, a first autocorrelation function may be obtained by:
and 2-1, determining the mean value and the variance of the first sequence, and calculating an autocovariance function corresponding to the first sequence according to the mean value.
And 2-2, determining a first autocorrelation function according to the length of the first sequence, the autocovariance function and the variance corresponding to the first sequence.
First the mean μ of the first sequence X is calculated:
where n is the length of the sequence, i.e. the total number of rows, xiIs the ith element in the first sequence, i.e. the number of white pixel points in the ith row.
The variance s of the first sequence is then calculated:
where s is the variance, μ is the sequence mean, xiIs the ith element in the sequence, i.e. the number of white pixel points in the ith row, and n is the length of the sequence.
Then the autocovariance r (h) of the first sequence is calculated:
wherein: h is the offset, μ is the sequence mean, xiIs the ith element in the sequence, i.e. the number of white pixel points in the ith row, and n is the length of the sequence.
And finally, calculating an autocorrelation coefficient ACF:
where r (h) is the autocovariance corresponding to the offset and s is the variance of the first sequence.
The second autocorrelation function is obtained in a similar manner as the first autocorrelation function, i.e. step 3 may comprise the steps of:
step 3-1, determining the mean value and the variance of the second sequence, and calculating an autocovariance function corresponding to the second sequence according to the mean value;
and 3-2, determining a second autocorrelation function according to the length of the second sequence, the autocovariance function and the variance corresponding to the second sequence.
It is understood that the implementation manner of the above step 3-1 and step 3-2 is similar to the implementation manner of the above step 2-1 and step 2-2, and is not described herein again.
For convenience of understanding, the first autocorrelation function may be as shown in fig. 8, where fig. 8 provides a first autocorrelation function of the second pixel point in the horizontal direction according to an embodiment of the present invention, where the ordinate represents an autocorrelation coefficient, and the abscissa represents an offset in the horizontal direction; fig. 9 is a diagram illustrating a second autocorrelation function of the second pixel point in the vertical direction according to the embodiment of the present invention, where the ordinate represents an autocorrelation coefficient and the abscissa represents a column offset in the vertical direction.
Optionally, in a possible implementation manner, the step S103-2 may be implemented as follows, please refer to fig. 10, where fig. 10 is a schematic flowchart of the step S103-2 provided in an embodiment of the present invention:
s103-2-1, carrying out maximum value solving on the first autocorrelation function, and obtaining the positions corresponding to the local maximum autocorrelation coefficients.
In a possible embodiment, the following is obtained by the relation: index = argrelmax (acf) may obtain a plurality of positions to which the local maximum autocorrelation coefficients correspond, where: index is a set of positions of local maximum autocorrelation coefficients, argrelmax is a maximum solving function of signal processing, and ACF is a set of autocorrelation coefficients in the first autocorrelation function.
And S103-2-2, determining the distance difference between the position corresponding to the largest maximum value in the local maximum autocorrelation coefficients and the start pixel position of the binary image as the period of the characteristic region in the horizontal direction.
In a possible embodiment, the corresponding position is obtained by the maximum value of the plurality of local maximum autocorrelation coefficients, i.e. the period T, T = np.where (ACF = ACF [ index ]. max ()) [0] [0 ]. Where [0] [0] is the starting pixel position of the image.
It can be understood that, in the horizontal direction, assuming that T is 230, it indicates that the position from the position of image 0 to 230 is one period of the image, and the position from 230 to 230+230 is the second period.
Similarly, the step S103-3 can be realized by performing maximum solution on the second autocorrelation function to obtain a plurality of local maximum autocorrelation coefficients; and determining the distance difference between the image position corresponding to one maximum value in the plurality of local maximum autocorrelation coefficients and the starting pixel position of the binarized image as the period of the feature region in the vertical direction.
In order to implement the steps in the foregoing embodiments to achieve the corresponding technical effects, the period extraction method provided in the embodiments of the present invention may be implemented in a hardware device or in a form of a software module, and when the period extraction method is implemented in a form of a software module, an embodiment of the present invention further provides a period extraction apparatus, please refer to fig. 11, where fig. 11 is a functional block diagram of the period extraction apparatus provided in the embodiments of the present invention, and the period extraction apparatus 200 may include:
an obtaining module 210, configured to obtain an image of a display panel to be detected; the image comprises characteristic regions which are periodically distributed; the characteristic region is a key shape region on the display panel to be detected;
the processing module 220 is configured to pre-process the image to obtain a binarized image, where the binarized image includes first pixel points and second pixel points; the second pixel point corresponds to the characteristic region;
the extracting module 230 is configured to perform autocorrelation analysis on all the second pixel points, and extract a period of the feature region.
In an alternative embodiment, the extraction module 230 includes a determination unit and an extraction unit: the determining unit is used for determining a first autocorrelation function of all the second pixel points in the horizontal direction and a second autocorrelation function of all the second pixel points in the vertical direction; the first autocorrelation function is used for measuring correlation between the quantity of second pixel points corresponding to each row offset in the horizontal direction; the second autocorrelation function represents the correlation between the number of second pixel points corresponding to each column offset in the vertical direction; the extraction unit is used for determining the period of the characteristic region in the horizontal direction from the first autocorrelation function; and determining the period of the characteristic region in the vertical direction from the second autocorrelation function.
In an optional embodiment, the determining unit is specifically configured to: in the binary image, counting the number of second pixel points in each line to form a first sequence, and counting the number of second pixel points in each column to form a second sequence; determining a first autocorrelation function of all second pixel points in the horizontal direction according to the first sequence; and determining a second autocorrelation function of the second pixel point in the vertical direction according to the second sequence.
In an optional embodiment, the extraction unit is specifically configured to: solving the maximum value of the first autocorrelation function to obtain a plurality of local maximum autocorrelation coefficients; determining a distance difference between a position corresponding to a largest maximum value in the plurality of local maximum autocorrelation coefficients and a start pixel position of the image as a period of the feature region in the horizontal direction;
in an optional embodiment, the extracting unit is further configured to perform maximum solution on the second autocorrelation function to obtain respective corresponding positions of the plurality of local maximum autocorrelation coefficients; and determining the distance difference between the position corresponding to one maximum value in the local maximum autocorrelation coefficients and the starting pixel position of the two images as the period of the characteristic region in the vertical direction.
In an optional embodiment, the determining unit is specifically configured to: determining the mean value and the variance of the first sequence, and calculating an autocovariance function corresponding to the first sequence according to the mean value; and determining a first autocorrelation function according to the length of the first sequence, the autocovariance function and the variance corresponding to the first sequence.
In an optional embodiment, the determining unit is specifically configured to: determining the mean value and the variance of the second sequence, and calculating an autocovariance function corresponding to the second sequence according to the mean value; and determining a second autocorrelation function according to the length of the second sequence, the autocovariance function and the variance corresponding to the second sequence.
In an optional embodiment, the processing module 220 is specifically configured to: carrying out image transformation and image enhancement on the image to obtain a gray level image; according to the first pixel value and the second pixel value, carrying out binarization conversion on the gray level image to obtain a binarization image, wherein the first pixel value corresponds to a first pixel point; the second pixel value corresponds to a second pixel point.
In an alternative embodiment, the processing module 220 is further specifically configured to process the binarized image by threshold segmentation to determine the feature region.
It should be noted that each functional module in the cycle extracting apparatus 200 provided by the embodiment of the present invention may be stored in a memory in the form of software or Firmware (Firmware) or be solidified in an Operating System (OS) of the computer device, and may be executed by a processor in the computer device. Meanwhile, data, codes of programs, and the like required to execute the above modules may be stored in the memory.
Therefore, an embodiment of the present invention further provides a computer device, as shown in fig. 12, and fig. 12 is a block diagram of a computer device provided in an embodiment of the present invention. The computer device 300 comprises a communication interface 301, a processor 302 and a memory 303. The processor 302, memory 303 and communication interface 301 are electrically connected to each other, directly or indirectly, to enable the transfer or interaction of data. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The memory 303 may be used for storing software programs and modules, such as program instructions/modules corresponding to the cycle extraction method provided by the embodiment of the present invention, and the processor 302 executes various functional applications and data processing by executing the software programs and modules stored in the memory 303. The communication interface 301 may be used for communicating signaling or data with other node devices. The computer device 300 may have a plurality of communication interfaces 301 in the present invention.
The memory 303 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a programmable read-only memory (PROM), an erasable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), and the like.
The processor 302 may be an integrated circuit chip having signal processing capabilities. The processor may be a general-purpose processor including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, etc.
An embodiment of the present invention further provides a readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the cycle extraction method according to any one of the foregoing embodiments. The computer readable storage medium may be, but is not limited to, various media that can store program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a PROM, an EPROM, an EEPROM, a magnetic or optical disk, etc.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (12)
1. A method of periodic extraction, the method comprising:
acquiring an image of a display panel to be detected; wherein, the image comprises characteristic regions which are periodically distributed; the characteristic region comprises a key structure on the display panel to be detected;
preprocessing the image to obtain a binary image; the binary image comprises a first pixel point and a second pixel point; the second pixel point corresponds to the characteristic region;
and performing autocorrelation analysis on all the second pixel points, and extracting the period of the characteristic region.
2. The period extraction method according to claim 1, wherein performing autocorrelation analysis on all the second pixels to extract the period of the feature region includes:
determining a first autocorrelation function of all the second pixel points in the horizontal direction and a second autocorrelation function of all the second pixel points in the vertical direction;
the first autocorrelation function is used for measuring the correlation between the quantity of the second pixel points corresponding to each row offset in the horizontal direction; the second autocorrelation function represents correlation between the quantity of second pixels corresponding to each column offset in the vertical direction;
determining the period of the characteristic region in the horizontal direction from the first autocorrelation function;
determining a period of the feature region in the vertical direction from the second autocorrelation function.
3. The period extraction method according to claim 2, wherein determining a first autocorrelation function in a horizontal direction and a second autocorrelation function in a vertical direction for all the second pixel points comprises:
in the binary image, counting the number of the second pixel points in each row to form a first sequence, and counting the number of the second pixel points in each column to form a second sequence;
determining the first autocorrelation function of all the second pixel points in the horizontal direction according to the first sequence;
and determining the second autocorrelation function of the second pixel point in the vertical direction according to the second sequence.
4. The period extraction method according to claim 3, wherein determining the period of the feature region in the horizontal direction from the first autocorrelation function comprises:
carrying out maximum solving on the first autocorrelation function to obtain a plurality of local maximum autocorrelation coefficients;
determining a distance difference between a position corresponding to a largest maximum value of the local maximum autocorrelation coefficients and an image start pixel position as a period of the feature region in the horizontal direction.
5. The period extraction method according to claim 3, wherein determining the period of the feature region in the vertical direction from the second autocorrelation function comprises:
carrying out maximum solving on the second autocorrelation function to obtain positions corresponding to the local maximum autocorrelation coefficients;
determining a distance difference between a position corresponding to one maximum value of the local maximum autocorrelation coefficients and a start pixel position of the binarized image as a period of the feature region in the vertical direction.
6. The periodic extraction method of claim 4, wherein determining the first autocorrelation function of the second pixel point in the horizontal direction according to the first sequence comprises:
determining the mean value and the variance of the first sequence, and calculating an autocovariance function corresponding to the first sequence according to the mean value;
and determining the first autocorrelation function according to the length of the first sequence, the autocovariance function corresponding to the first sequence and the variance.
7. The periodic extraction method of claim 4, wherein determining the second autocorrelation function of the second pixel point in the vertical direction according to the second sequence comprises:
determining the mean value and the variance of the second sequence, and calculating an autocovariance function corresponding to the second sequence according to the mean value;
and determining the second autocorrelation function according to the length of the second sequence, the autocovariance function corresponding to the second sequence and the variance.
8. The period extraction method according to claim 1, wherein the preprocessing the image to obtain a binarized image comprises:
carrying out image transformation and image enhancement on the image to obtain a gray level image;
according to a first pixel value and a second pixel value, carrying out binarization conversion on the gray-scale image to obtain a binarization image, wherein the first pixel value corresponds to the first pixel point; the second pixel value corresponds to the second pixel point.
9. The cycle extraction method according to claim 8, wherein after the binarizing converting the grayscale map based on the first pixel value and the second pixel value to obtain the binarized image, the method further comprises:
and processing the binary image by threshold segmentation to determine the characteristic region.
10. A cycle extracting apparatus, characterized by comprising:
the acquisition module is used for acquiring an image of a display panel to be detected; the image comprises characteristic regions which are periodically distributed; the characteristic region is a key shape region on the display panel to be detected;
the processing module is used for preprocessing the image to obtain a binary image, and the binary image comprises first pixel points and second pixel points; the second pixel point corresponds to the characteristic region;
and the extraction module is used for performing autocorrelation analysis on all the second pixel points and extracting the period of the characteristic region.
11. A computer device comprising a processor and a memory, the memory storing a computer program executable by the processor, the processor being operable to execute the computer program to implement the cycle extraction method of any one of claims 1 to 9.
12. A readable storage medium on which a computer program is stored, which computer program, when being executed by a processor, carries out the cycle extraction method according to any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111550080.4A CN113936002A (en) | 2021-12-17 | 2021-12-17 | Period extraction method and device, computer equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111550080.4A CN113936002A (en) | 2021-12-17 | 2021-12-17 | Period extraction method and device, computer equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113936002A true CN113936002A (en) | 2022-01-14 |
Family
ID=79289250
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111550080.4A Pending CN113936002A (en) | 2021-12-17 | 2021-12-17 | Period extraction method and device, computer equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113936002A (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1493870A (en) * | 2002-09-26 | 2004-05-05 | 株式会社日立国际电气 | Apparatus and method for inspecting pattern defect |
| US20160275671A1 (en) * | 2015-03-16 | 2016-09-22 | Kla-Tencor Corporation | Systems and Methods for Enhancing Inspection Sensitivity of an Inspection Tool |
| CN106198569A (en) * | 2016-08-03 | 2016-12-07 | 广东工业大学 | A kind of LTPS/IGZO glass substrate broken hole method for quick |
| CN109166092A (en) * | 2018-07-05 | 2019-01-08 | 深圳市国华光电科技有限公司 | A kind of image defect detection method and system |
| CN109829912A (en) * | 2019-02-14 | 2019-05-31 | 深圳市华星光电半导体显示技术有限公司 | The defect inspection method of tft array substrate |
| CN110175997A (en) * | 2019-05-30 | 2019-08-27 | 深圳市洲明科技股份有限公司 | Show screen dead pixel detection method, device, computer equipment and storage medium |
| US20190353767A1 (en) * | 2016-11-17 | 2019-11-21 | Trinamix Gmbh | Detector for optically detecting at least one object |
| US20190362481A1 (en) * | 2018-05-24 | 2019-11-28 | Keysight Technologies, Inc. | Detecting mura defects in master panel of flat panel displays during fabrication |
| CN111739020A (en) * | 2020-07-31 | 2020-10-02 | 成都数之联科技有限公司 | Automatic labeling method, device, equipment and medium for periodic texture background defect label |
| US20210012474A1 (en) * | 2019-07-10 | 2021-01-14 | International Business Machines Corporation | Object defect detection |
| CN113205480A (en) * | 2021-03-19 | 2021-08-03 | 哈工大机器人(中山)无人装备与人工智能研究院 | Periodic extraction method, device and system for detecting defects of display panel |
| CN113538603A (en) * | 2021-09-16 | 2021-10-22 | 深圳市光明顶照明科技有限公司 | Optical detection method and system based on array product and readable storage medium |
-
2021
- 2021-12-17 CN CN202111550080.4A patent/CN113936002A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1493870A (en) * | 2002-09-26 | 2004-05-05 | 株式会社日立国际电气 | Apparatus and method for inspecting pattern defect |
| US20160275671A1 (en) * | 2015-03-16 | 2016-09-22 | Kla-Tencor Corporation | Systems and Methods for Enhancing Inspection Sensitivity of an Inspection Tool |
| CN106198569A (en) * | 2016-08-03 | 2016-12-07 | 广东工业大学 | A kind of LTPS/IGZO glass substrate broken hole method for quick |
| US20190353767A1 (en) * | 2016-11-17 | 2019-11-21 | Trinamix Gmbh | Detector for optically detecting at least one object |
| US20190362481A1 (en) * | 2018-05-24 | 2019-11-28 | Keysight Technologies, Inc. | Detecting mura defects in master panel of flat panel displays during fabrication |
| CN109166092A (en) * | 2018-07-05 | 2019-01-08 | 深圳市国华光电科技有限公司 | A kind of image defect detection method and system |
| CN109829912A (en) * | 2019-02-14 | 2019-05-31 | 深圳市华星光电半导体显示技术有限公司 | The defect inspection method of tft array substrate |
| CN110175997A (en) * | 2019-05-30 | 2019-08-27 | 深圳市洲明科技股份有限公司 | Show screen dead pixel detection method, device, computer equipment and storage medium |
| US20210012474A1 (en) * | 2019-07-10 | 2021-01-14 | International Business Machines Corporation | Object defect detection |
| CN111739020A (en) * | 2020-07-31 | 2020-10-02 | 成都数之联科技有限公司 | Automatic labeling method, device, equipment and medium for periodic texture background defect label |
| CN113205480A (en) * | 2021-03-19 | 2021-08-03 | 哈工大机器人(中山)无人装备与人工智能研究院 | Periodic extraction method, device and system for detecting defects of display panel |
| CN113538603A (en) * | 2021-09-16 | 2021-10-22 | 深圳市光明顶照明科技有限公司 | Optical detection method and system based on array product and readable storage medium |
Non-Patent Citations (3)
| Title |
|---|
| TENG-DA ZHANG等: "Surface defect inspection of TFT-LCD panels based on 1D Fourier method", 《SEVENTH INTERNATIONAL SYMPOSIUM ON PRECISION MECHANICAL MEASUREMENTS》 * |
| 王新新等: "TFT-LCD缺陷检测系统的研究", 《电子测量与仪器学报》 * |
| 邓祖新等: "《数据分析和SAS系统》", 31 August 2006 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11403839B2 (en) | Commodity detection terminal, commodity detection method, system, computer device, and computer readable medium | |
| CN109886928B (en) | Target cell marking method, device, storage medium and terminal equipment | |
| US11699283B2 (en) | System and method for finding and classifying lines in an image with a vision system | |
| CN115205223B (en) | Visual inspection method and device for transparent object, computer equipment and medium | |
| CN110909640A (en) | Method and device for determining water level line, storage medium and electronic device | |
| CN112149667A (en) | Method for automatically reading pointer type instrument based on deep learning | |
| CN111598913B (en) | Image segmentation method and system based on robot vision | |
| JP2024016287A (en) | System and method for detecting lines in a vision system | |
| KR101842535B1 (en) | Method for the optical detection of symbols | |
| CN113283439B (en) | Intelligent counting method, device and system based on image recognition | |
| CN113723467A (en) | Sample collection method, device and equipment for defect detection | |
| CN112837384A (en) | Vehicle marking method and device and electronic equipment | |
| CN115908988B (en) | Defect detection model generation method, device, equipment and storage medium | |
| CN115546219B (en) | Detection plate type generation method, plate card defect detection method, device and product | |
| CN113936002A (en) | Period extraction method and device, computer equipment and readable storage medium | |
| CN115713750A (en) | Lane line detection method and device, electronic equipment and storage medium | |
| CN115588196A (en) | Pointer type instrument reading method and device based on machine vision | |
| CN116993654A (en) | Camera module defect detection method, device, equipment, storage medium and product | |
| CN114882470A (en) | Vehicle-mounted anti-collision early warning method and device, computer equipment and storage medium | |
| CN114092542A (en) | Bolt measuring method and system based on two-dimensional vision | |
| CN115393838A (en) | Pointer instrument reading identification method and device, electronic equipment and storage medium | |
| Vázquez-Fernández et al. | A machine vision system for the calibration of digital thermometers | |
| CN111898641A (en) | Target model detection device, electronic equipment and computer readable storage medium | |
| CN111582262A (en) | Segment type liquid crystal picture content identification method, device, equipment and storage medium | |
| CN110942058A (en) | Instrument data reading method based on CCD machine vision recognition |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 610000 No. 270, floor 2, No. 8, Jinxiu street, Wuhou District, Chengdu, Sichuan Applicant after: Chengdu shuzhilian Technology Co.,Ltd. Address before: 610000 No.2, 4th floor, building 1, Jule Road intersection, West 1st section of 1st ring road, Wuhou District, Chengdu City, Sichuan Province Applicant before: CHENGDU SHUZHILIAN TECHNOLOGY Co.,Ltd. |