A method, system, device, and storage medium for checking the state of a pressing plate

Abstract

The present invention discloses a method, system, device and storage medium for checking the state of pressure plates, which relates to the technical field of power equipment. The pressure plate name, standard on / off state, pressure plate template frame and its position information of each pressure plate in the pressure plate state panel diagram are extracted. The pressure plate name, actual on / off state, pressure plate detection frame and its position information of each pressure plate in the pressure plate captured image are identified. Combining the position information of each pressure plate template frame and pressure plate detection frame, and the text similarity between the pressure plate name corresponding to each pressure plate template frame and the pressure plate name corresponding to each pressure plate detection frame, the pressure plate captured image is processed to match the pressure plate template frame and pressure plate detection frame in the same row and the same column. Even when the pressure plate captured image is blurred or blocked, the pressure plate template frame and pressure plate detection frame can be accurately corresponded one by one, providing support for checking the state of the pressure plate. According to whether the standard on / off state of the pressure plate corresponding to the pressure plate template frame is consistent with the actual on / off state of the pressure plate detection frame, the state check of the pressure plate is automatically completed.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment, and particularly to a method, system, device and storage medium for checking the state of pressure plates. Background Art

[0002] With the continuous increase of power demand, the importance of the safe and stable operation of substations has become increasingly prominent. The secondary protection panel in a substation can quickly cut off faulty equipment when a fault occurs in the power system, ensuring the safe operation of the substation. The pressure plate is an important component in the secondary protection panel, and whether its switching state is normal directly affects whether the function of the secondary protection panel takes effect. Therefore, it is very necessary to check the state of the pressure plate.

[0003] At present, manual checking is often used to check the state of pressure plates. However, there are many pressure plates in a substation, and the manual checking method has the defects of high labor intensity, low work efficiency, and easy omission and misjudgment.

[0004] Another method is to use image recognition technology to identify the name and actual switching state of the pressure plate from the pressure plate image captured by a camera, and check the state of the pressure plate by judging whether the actual switching state of the pressure plate is consistent with the standard switching state corresponding to the pressure plate with this name. However, affected by various factors such as shooting angle, light, and obstacle occlusion, the recognition accuracy of the name of the pressure plate may be affected, and then the standard switching state corresponding to the pressure plate cannot be accurately found, resulting in incorrect checking of the pressure plate state and affecting the safe operation of the entire substation. Summary of the Invention

[0005] The purpose of the present invention is to provide a method, system, device and storage medium for checking the state of pressure plates, which can automatically check the state of pressure plates and still ensure the accuracy of checking the state of pressure plates even when the captured image of the pressure plate is blurred or blocked.

[0006] To solve the above technical problems, the present invention provides a method for checking the state of pressure plates, including:

[0007] extracting the name, standard switching state, pressure plate template frame corresponding to each pressure plate, and the position information of each pressure plate template frame of each pressure plate in the substation from the obtained pressure plate state panel diagram;

[0008] identifying the name, actual switching state, pressure plate detection frame corresponding to each pressure plate, and the position information of each pressure plate detection frame of each pressure plate included in the captured image of the pressure plate;

[0009] According to the position information of each platen template frame, the position information of each platen detection frame, and the text similarity between the platen name of the platen corresponding to each platen template frame and the platen name of the platen corresponding to each platen detection frame, the platen captured image is processed so that the number of rows and columns of the platen detection frame included in the platen captured image is consistent with the number of rows and columns of the platen template frame included in the platen status disk image, and the platen template frame and the platen detection frame corresponding to the same row and column are matched;

[0010] For each pressing plate, whether the insertion and retraction state of the pressing plate is normal is determined based on whether the actual insertion and retraction state of the pressing plate detection frame corresponding to the pressing plate is consistent with the standard insertion and retraction state of the pressing plate template frame corresponding to the pressing plate.

[0011] Optionally, processing the platen shot image according to the position information of each platen template frame, the position information of each platen detection frame, and the text similarity between the platen name of the platen corresponding to each platen template frame and the platen name of the platen corresponding to each platen detection frame includes:

[0012] According to the position information of each platen template frame, each platen template frame located in the same row in the platen status disk diagram is divided into the same template row, and the total number of template rows of the platen status disk diagram is determined;

[0013] According to the position information of each platen detection frame, each platen detection frame located in the same row in the platen captured image is divided into the same detection row, and the total number of detection rows of the platen captured image is determined;

[0014] When the total number of template rows is less than the total number of detection rows, according to the text similarity between the platen name of the platen corresponding to each platen template frame and the platen name of the platen corresponding to each platen detection frame, the detection rows that meet the row matching condition are determined from each detection row, and other detection rows that do not meet the row matching condition are eliminated, so that the total number of detection rows of the platen captured image is equal to the total number of template rows;

[0015] For a template row and a detection row corresponding to the same row, when the number of platen template frames included in the template row is less than the number of platen detection frames included in the detection row, according to the text similarity between the platen name of the platen corresponding to each platen template frame and the platen name of the platen corresponding to each platen detection frame, each platen detection frame that meets the detection frame matching condition is determined from the detection row, and other platen detection frames that do not meet the detection frame matching condition are eliminated, so that the number of platen detection frames included in each detection row of the platen captured image is equal to the number of platen template frames included in the template row corresponding to the same row;

[0016] When the number of rows and columns of the platen template frames included in the platen state disk surface diagram is exactly the same as the number of rows and columns of the platen detection frames included in the platen captured image, the platen template frames and platen detection frames corresponding to the same row and the same column are matched.

[0017] Optionally, determining the detection rows that meet the row matching condition from each detection row according to the text similarity between the platen names of the platens corresponding to each platen template frame and the platen names of the platens corresponding to each platen detection frame includes:

[0018] Determine a CTC text similarity product matrix according to the platen names of the platens corresponding to each platen template frame and the platen names of the platens corresponding to each platen detection frame; wherein, the number of rows of the CTC text similarity product matrix is equal to the total number of template rows, the number of columns of the CTC text similarity product matrix is equal to the total number of detection rows, and each element in the CTC text similarity product matrix represents the product of the CTC text similarities between the platen names corresponding to each platen template frame in this template row and the platen names corresponding to each platen detection frame in this detection row;

[0019] Use the dynamic programming algorithm to select the detection rows that meet the row matching condition from each detection row included in the platen captured image, wherein the number of selected detection rows is equal to the total number of template rows, and the row matching condition is that the total matching value between the selected detection rows and all template rows is the largest, wherein the total matching value is the product of the elements corresponding to the selected detection rows and each template row in the CTC text similarity product matrix.

[0020] Optionally, determining each platen detection frame that meets the detection frame matching condition from this detection row according to the text similarity between the platen names of the platens corresponding to each platen template frame and the platen names of the platens corresponding to each platen detection frame includes:

[0021] For each platen template frame in the current template row, determine the CTC text similarity between this platen template frame and each platen detection frame in the same row according to the platen names of the platens corresponding to each platen template frame and the platen names of the platens corresponding to each platen detection frame, and obtain a CTC text similarity matrix;

[0022] Wherein, the number of rows of the CTC text similarity matrix is the number of platen template frames included in the current template row, the number of columns of the CTC text similarity matrix is the number of platen detection frames included in the detection row in the same row as the current template row, and each element of the CTC text similarity matrix represents the CTC text similarity between the platen name corresponding to this platen template frame and the platen name corresponding to this platen detection frame;

[0023] Use the dynamic programming algorithm to select the pressure plate detection frames that meet the detection frame matching conditions from each pressure plate detection frame. Among them, the number of selected pressure plate detection frames is equal to the number of pressure plate template frames included in the current template row, and the detection frame matching condition is that the product of the CTC text similarities between the pressure plate names corresponding to the selected pressure plate detection frames and the pressure plate names corresponding to each pressure plate template frame in the current template row is the largest.

[0024] Optionally, after determining the total number of detection rows and the total number of template rows, it further includes:

[0025] When the total number of template rows is greater than the total number of detection rows, or when the number of pressure plate template frames included in the template row corresponding to the same row is greater than the number of pressure plate detection frames included in the detection row, generate a prompt message for prompting to reshoot the pressure plate image.

[0026] Optionally, the extraction of the pressure plate names, standard switching states, pressure plate template frames corresponding to each pressure plate, and the position information of each pressure plate template frame of each substation from the obtained pressure plate status panel diagram includes:

[0027] Extract the pressure plate template frames that meet the preset parsing conditions from the pressure plate status panel diagram. The preset parsing conditions include that each pressure plate template frame must contain a set of symbols for representing the standard switching state of the pressure plate and a text box for indicating the pressure plate name;

[0028] For each pressure plate template frame, take the text in the text box within the pressure plate template frame as the pressure plate name corresponding to the pressure plate template frame, determine the standard switching state of the corresponding pressure plate according to the symbols in the pressure plate template frame, and take the coordinates of the preset points of the pressure plate template frame as the position information of the pressure plate template frame; among them, the standard switching state includes the input state and the output state.

[0029] Optionally, the recognition of the pressure plate names, actual switching states, pressure plate detection frames corresponding to each pressure plate, and the position information of each pressure plate detection frame included in the pressure plate image includes:

[0030] Use the target neural network to recognize the pressure plate image to determine the actual switching states of each pressure plate, the corresponding pressure plate nameplates, the corresponding pressure plate detection frames, and the position information of each pressure plate detection frame;

[0031] Among them, the actual switching state includes the input state and the output state. Each pressure plate detection frame corresponding to each pressure plate includes the appearance image of the pressure plate and the pressure plate nameplate corresponding to the pressure plate. Take the coordinates of the preset points of each pressure plate detection frame as the position information of the pressure plate detection frame;

[0032] Use the text recognition neural network to recognize each pressure plate nameplate to determine the pressure plate names of each pressure plate.

[0033] To solve the above technical problems, the present invention also provides a platen status verification system, including:

[0034] A panel diagram information extraction unit, configured to extract the platen name, standard switching status, a platen template frame corresponding to each platen, and the position information of each platen template frame of each platen in the substation from the obtained platen status panel diagram;

[0035] A platen image information extraction unit, configured to identify the platen name, actual switching status, a platen detection frame corresponding to each platen, and the position information of each platen detection frame included in the platen captured image;

[0036] A matching unit, configured to process the platen captured image according to the position information of each platen template frame, the position information of each platen detection frame, and the text similarity between the platen name corresponding to the platen template frame and the platen name corresponding to the platen detection frame corresponding to each platen, so that the number of rows and columns of the platen detection frames included in the platen captured image is consistent with the number of rows and columns of the platen template frames included in the platen status panel diagram, and match the platen template frames and platen detection frames corresponding to the same row and the same column;

[0037] A status detection unit, configured to determine whether the switching status of each platen is normal according to whether the actual switching status of the platen detection frame corresponding to the platen is consistent with the standard switching status of the platen template frame corresponding to the platen for each platen.

[0038] To solve the above technical problems, the present invention also provides a platen status verification device, including:

[0039] A memory, configured to store a computer program;

[0040] A processor, configured to implement the steps of any one of the above platen status verification methods when executing the computer program.

[0041] To solve the above technical problems, the present invention also provides a storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of any one of the above platen status verification methods are implemented.

[0042] The beneficial effects of the present invention are to provide a method, system, device and storage medium for checking the state of pressure plates, including extracting the pressure plate names, standard on / off states, pressure plate template frames and their position information in the pressure plate state panel diagram. Then, identify the pressure plate names, actual on / off states, pressure plate detection frames and their position information in the pressure plate captured image. Next, combine the position information of each pressure plate template frame and pressure plate detection frame, as well as the text similarity between the pressure plate names corresponding to each pressure plate template frame and the pressure plate names corresponding to each pressure plate detection frame, to process the pressure plate captured image, so that the number of rows and columns of the pressure plate detection frames included in the pressure plate captured image is exactly the same as the number of rows and columns of the pressure plate template frames included in the pressure plate state panel diagram, and match the pressure plate template frames and pressure plate detection frames corresponding to the same row and the same column. Even when the pressure plate captured image is blurred or blocked, the pressure plate template frames and pressure plate detection frames can be accurately corresponded one by one, providing strong support for subsequent pressure plate state checking. Finally, automatically complete the checking of the pressure plate state according to whether the standard on / off state of the pressure plate template frame corresponding to the pressure plate is consistent with the actual on / off state of the pressure plate detection frame. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the prior art and the embodiments. Obviously, the following described drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0044] Figure 1 It is a flowchart of a method for checking the state of pressure plates provided by the present invention.

[0045] Figure 2 It is a pressure plate state panel diagram provided by the present invention.

[0046] Figure 3 It is a pressure plate captured image provided by the present invention.

[0047] Figure 4 It is a pressure plate captured image provided by the present invention after removing the wrong detection rows and wrong pressure plate detection frames.

[0048] Figure 5 It is another flowchart of a method for checking the state of pressure plates provided by the present invention.

[0049] Figure 6 It is a structural schematic diagram of a system for checking the state of pressure plates provided by the present invention.

[0050] Figure 7 It is a structural schematic diagram of a device for checking the state of pressure plates provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0051] The core of the present invention is to provide a method, system, device and storage medium for checking the state of pressure plates, which can automatically check the state of pressure plates and ensure the accuracy of pressure plate state checking even when the captured image of the pressure plate is blurred or blocked.

[0052] To make the objectives, 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 accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0053] Please refer to Figure 1 , Figure 1 which is a flowchart of a method for checking the state of pressure plates provided by the present invention. The method includes:

[0054] S101. Extract the pressure plate names, standard on / off states, pressure plate template frames corresponding to each pressure plate, and the position information of each pressure plate template frame of each pressure plate in the substation from the obtained pressure plate state panel diagram.

[0055] The pressure plate state panel Figure 1 is generally provided by units such as equipment manufacturers or power companies, which records the pressure plate names of each pressure plate in the substation and the standard on / off states corresponding to each pressure plate when the substation operates normally. And in order to facilitate subsequent checking of the pressure plate state to determine whether the standard on / off state and the actual on / off state corresponding to the same pressure plate are consistent by combining the pressure plate name and the pressure plate position, the present invention also divides out the pressure plate template frames corresponding to each pressure plate from the pressure plate state panel diagram, and reflects the position information of the pressure plate through the position information of the pressure plate template frame.

[0056] Please refer to Figure 2 , Figure 2 which is a pressure plate state panel diagram provided by the present invention. The relevant information corresponding to the pressure plates in two rows and eight columns is recorded in this panel diagram, including the pressure plate names of these pressure plates and the symbols used to represent the standard on / off states of each pressure plate. In the panel diagram, the pressure plate is usually represented by two circles aligned vertically, and two vertical lines are combined to represent the standard on / off state of the pressure plate. When two parallel vertical lines are included, the standard on / off state of the pressure plate is the on state; otherwise, the standard on / off state of the pressure plate is the off state. Take Figure 2Taking the shown panel diagram as an example, the template frame corresponding to each pressure plate includes the text box of the pressure plate name of the pressure plate and a group of symbols used to represent the standard input / output state of the pressure plate. The position information of the template frame of the pressure plate can be the coordinates of its center point or the coordinates of any other point, as well as the length and width information, etc. The present invention does not make special limitations on this.

[0057] Please refer to Figure 5 , Figure 5 which is another flowchart of a method for checking the state of a pressure plate provided by the present invention. The information extracted from the panel diagram of the pressure plate state can also be stored in a database for retrieval when checking the pressure plate state. And unless the panel diagram of the pressure plate state is updated, it is not necessary to re-extract the information in the panel diagram of the pressure plate state every time the method for checking the pressure plate state is executed.

[0058] As for how to specifically extract the pressure plate name, standard input / output state, the template frame of the pressure plate and its position information of each pressure plate from the panel diagram of the pressure plate, it will be described in subsequent embodiments and will not be elaborated here.

[0059] S102. Identify the pressure plate name, actual input / output state, the pressure plate detection frame corresponding to each pressure plate, and the position information of each pressure plate detection frame included in the captured image of the pressure plate.

[0060] Please refer to Figure 3 , Figure 3 which is a captured image of a pressure plate provided by the present invention. The appearance of the pressure plate when its actual input / output state is the input state is significantly different from its appearance when its actual input / output state is the output state. Therefore, the actual input / output state of each pressure plate can be determined by identifying the captured image of the pressure plate. As Figure 3 shown, each pressure plate corresponds to a pressure plate nameplate, and the pressure plate name of each pressure plate can be determined by identifying the pressure plate nameplate.

[0061] Similarly, in order to facilitate the subsequent checking of the pressure plate state, and to be able to jointly determine whether the standard input / output state and the actual input / output state corresponding to the same pressure plate are consistent by combining the pressure plate name and the pressure plate position, the present invention also divides the captured image of the pressure plate into pressure plate detection frames corresponding to each pressure plate one by one, and reflects the position information of the pressure plate through the position information of the pressure plate detection frame.

[0062] As for how to specifically identify the pressure plate name, actual input / output state of each pressure plate, and the pressure plate detection frame and its position information from the captured image of the pressure plate, it will be described in subsequent embodiments and will not be elaborated here.

[0063] S103. According to the position information of each pressure plate template frame, the position information of each pressure plate detection frame, and the text similarity between the pressure plate names corresponding to the pressure plate template frames and the pressure plate names corresponding to the pressure plate detection frames, process the pressure plate captured image so that the number of rows and columns of the pressure plate detection frames included in the pressure plate captured image is the same as the number of rows and columns of the pressure plate template frames included in the pressure plate status panel diagram, and match the pressure plate template frames and the pressure plate detection frames corresponding to the same row and the same column.

[0064] According to the position information of the pressure plate template frame, the row information and column information of the pressure plate template frame in the pressure plate status panel diagram can be determined (that is, which row and which column of the pressure plate status panel diagram the pressure plate template frame is located in), and thus the row information and column information of the corresponding pressure plate are determined. According to the position information of the pressure plate detection frame, the row information and column information of the pressure plate detection frame in the pressure plate captured image can be determined, and thus the row information and column information of the pressure plate corresponding to this pressure plate detection frame are determined.

[0065] In theory, when the number of rows and columns of the pressure plate detection rows included in the pressure plate captured image is exactly the same as the number of rows and columns of the pressure plate template rows included in the pressure plate status panel diagram, it can be considered that each pressure plate detection frame in the pressure plate captured image corresponds one-to-one to each pressure plate template frame in the pressure plate status panel diagram, and the pressure plate template frame and the pressure plate detection frame with the same row information and column information (that is, the pressure plate template frame and the pressure plate detection frame corresponding to the same row and the same column) correspond to the same pressure plate, and the two match each other.

[0066] Therefore, if it is determined according to the position information of each pressure plate template frame and the position information of each pressure plate detection frame that the number of rows and columns of the pressure plate detection rows included in the pressure plate captured image is exactly the same as the number of rows and columns of the pressure plate template rows included in the pressure plate status panel diagram, there is no need to process the pressure plate captured image, directly match the pressure plate template frames and the pressure plate detection frames corresponding to the same row and the same column, and perform the subsequent steps of checking the pressure plate status. Moreover, the method of matching the pressure plate template frames and the pressure plate detection frames according to the position information avoids the inaccurate problem that exists when checking the pressure plate status according to the pressure plate name when the pressure plate captured image is blurred or blocked, thus providing strong support for the subsequent checking of the pressure plate status.

[0067] Of course, in practical applications, the pressure plate captured image may include other components in addition to the pressure plates, resulting in incorrect pressure plate detection frames. At this time, the number of rows of the pressure plate detection frames included in the pressure plate captured image may be different from the number of rows of the pressure plate template frames included in the pressure plate status panel diagram, or the total number of pressure plate detection frames corresponding to the same row may be different from the total number of pressure plate template frames. In this case, it is impossible to accurately complete the matching of the pressure plate template frames and the pressure plate detection frames only through the position information of each pressure plate template frame and the position information of each pressure plate detection frame.

[0068] Therefore, the present invention further introduces the text similarity between the name of the pressing plate corresponding to each pressing plate template frame and the name of the pressing plate corresponding to each pressing plate detection frame, processes the captured image of the pressing plate, and eliminates the incorrect pressing plate detection frames, so that the number of rows and columns of the pressing plate detection rows included in the processed captured image of the pressing plate is exactly the same as the number of rows and columns of the pressing plate template rows included in the pressing plate status panel diagram, and then performs matching according to the position information. Similarly, it can avoid the inaccurate problem that exists when checking the pressing plate status according to the pressing plate name when the captured image of the pressing plate is blurred or blocked.

[0069] It can be seen that in the case where there are incorrect pressing plate detection frames in the captured image of the pressing plate, according to the position information of each pressing plate template frame, the position information of each pressing plate detection frame, and the text similarity between the name of the pressing plate corresponding to each pressing plate template frame and the name of the pressing plate corresponding to each pressing plate detection frame, this situation can be recognized and the incorrect pressing plate detection frames can be eliminated, providing strong support for subsequent checking of the pressing plate status.

[0070] In addition, in actual applications, some pressing plates may be missing in the captured image of the pressing plate. At this time, the user is prompted to re - capture the image of the pressing plate, and after obtaining a new captured image of the pressing plate, each step of the pressing plate status checking method provided by the present invention is executed again. This situation will be specifically described later and will not be elaborated here for the time being.

[0071] S104. For each pressing plate, determine whether the switching - on / off state of the pressing plate is normal according to whether the actual switching - on / off state of the pressing plate detection frame corresponding to the pressing plate is consistent with the standard switching - on / off state of the pressing plate template frame corresponding to the pressing plate.

[0072] After matching each pressing plate template frame with each pressing plate detection frame, determine whether the switching - on / off state of the corresponding pressing plate is normal according to whether the actual switching - on / off state of the pressing plate detection frame is consistent with the standard switching - on / off state of the pressing plate template frame corresponding to the pressing plate. Specifically, when the actual switching - on / off state corresponding to the pressing plate is consistent with the standard switching - on / off state, it is determined that the switching - on / off state of the pressing plate is normal; if not, it is determined that the switching - on / off state of the pressing plate is abnormal.

[0073] In summary, the present invention provides a method for verifying the state of pressure plates. First, the pressure plate names, standard on / off states, pressure plate template frames and their position information of each pressure plate in the pressure plate state panel diagram are extracted. Then, the pressure plate names, actual on / off states, pressure plate detection frames and their position information of each pressure plate in the captured image of the pressure plate are identified. Furthermore, by combining the position information of each pressure plate template frame and each pressure plate detection frame, and the text similarity between the pressure plate name corresponding to each pressure plate template frame and the pressure plate name corresponding to each pressure plate detection frame, the captured image of the pressure plate is processed so that the number of rows and columns of the pressure plate detection frames included in the captured image of the pressure plate is exactly the same as the number of rows and columns of the pressure plate template frames included in the pressure plate state panel diagram, and the pressure plate template frames and pressure plate detection frames corresponding to the same row and the same column are matched. Even when the captured image of the pressure plate is blurred or blocked, the pressure plate template frames and pressure plate detection frames can be accurately corresponded one by one, providing strong support for subsequent verification of the pressure plate state. Finally, according to whether the standard on / off state of the pressure plate corresponding to the pressure plate template frame is consistent with the actual on / off state of the pressure plate detection frame, the verification of the pressure plate state is automatically completed.

[0074] In order to make the number of rows and columns of the pressure plate detection frames included in the captured image of the pressure plate the same as the number of rows and columns of the pressure plate template frames included in the pressure plate state panel diagram, it is necessary to remove the incorrect pressure plate detection frames in the captured image of the pressure plate. The process is described below.

[0075] As an optional embodiment, processing the captured image of the pressure plate according to the position information of each pressure plate template frame, the position information of each pressure plate detection frame, and the text similarity between the pressure plate name corresponding to each pressure plate template frame and the pressure plate name corresponding to each pressure plate detection frame includes:

[0076] According to the position information of each pressure plate template frame, the pressure plate template frames in the same row in the pressure plate state panel diagram are divided into the same template row, and the total number of template rows of the pressure plate state panel diagram is determined;

[0077] According to the position information of each pressure plate detection frame, the pressure plate detection frames in the same row in the captured image of the pressure plate are divided into the same detection row, and the total number of detection rows of the captured image of the pressure plate is determined;

[0078] When the total number of template rows is less than the total number of detection rows, according to the text similarity between the pressure plate name corresponding to each pressure plate template frame and the pressure plate name corresponding to each pressure plate detection frame, the detection rows that meet the row matching condition are determined from each detection row, and the other detection rows that do not meet the row matching condition are removed, so that the total number of detection rows of the captured image of the pressure plate is equal to the total number of template rows;

[0079] For the template row and the detection row corresponding to the same line, when the number of platen template frames included in the template row is less than the number of platen detection frames included in the detection row, based on the text similarity between the platen names corresponding to the platen template frames and the platen names corresponding to the platen detection frames, each platen detection frame that meets the detection frame matching condition is determined from the detection row, and other platen detection frames that do not meet the detection frame matching condition are excluded, so that the number of platen detection frames included in each detection row of the platen captured image is equal to the number of platen template frames included in the template row corresponding to the same line;

[0080] When the number of rows and columns of the platen template frames included in the platen status panel diagram is exactly the same as the number of rows and columns of the platen detection frames included in the platen captured image, the platen template frames and the platen detection frames corresponding to the same row and the same column are matched.

[0081] First, based on the position information of each platen template frame and the position information of each platen detection frame, it is determined whether there are incorrect platen detection frames in the platen captured image. Specifically, it can be determined by judging whether the number of rows of the platen captured image is greater than the number of rows of the platen status panel diagram and whether the number of columns of the platen captured image is greater than the number of columns of the platen status panel diagram.

[0082] Specifically, first, according to the position information of each platen template frame, the platen template frames located in the same row in the platen status panel diagram are divided into the same template row, and the total number of template rows of the platen status panel diagram is determined. The same is true for the platen captured image, where each platen detection frame located in the same row is divided into the same detection row, and the total number of detection rows of the platen captured image is determined.

[0083] As a specific implementation manner, the position information of the platen template frame is the coordinate of the specified point of the platen template frame (such as the coordinate of the center point of the platen template frame). Therefore, the platen template frames with the same ordinate are divided into the same template row. The position information of the platen detection frame and the division method of the detection row are the same, and will not be elaborated here.

[0084] In addition, in practical applications, the present invention can use a target neural network to identify each platen detection frame in the platen captured image, but the platen detection frames output by the target neural network are disordered. The present invention uses the position information of each platen detection frame to arrange the disordered platen detection frames.

[0085] If the total number of template rows in the pressure plate status panel diagram is less than the total number of detected rows in the pressure plate captured image, it proves that there are redundant detected rows in the pressure plate captured image, and each pressure plate detection frame within the detected rows is an incorrect pressure plate detection frame. The text similarity between the incorrect pressure plate detection frame and the correct pressure plate detection frame is relatively low. Based on this, the present invention determines the detected rows that meet the row matching condition from each detected row according to the text similarity between the pressure plate names corresponding to each pressure plate template frame and the pressure plate names corresponding to each pressure plate detection frame, and eliminates the other detected rows that do not meet the row matching condition, so that the total number of detected rows in the pressure plate captured image is equal to the total number of template rows. The row matching condition can be set according to actual needs, and the present invention does not make specific limitations. A setting method of the row matching condition is provided later, which will not be elaborated here for the time being.

[0086] If the total number of template rows in the pressure plate status panel diagram is equal to the total number of detected rows in the pressure plate captured image, but for the template row and the detected row corresponding to the same row, the number of pressure plate template frames included in the template row is less than the number of pressure plate detection frames included in the detected row, it proves that there are incorrect pressure plate detection frames in the detected row. Similarly, the text similarity between the incorrect pressure plate detection frame and the correct pressure plate detection frame is relatively low. Based on this, the present invention determines each pressure plate detection frame that meets the detection frame matching condition from the detected row according to the text similarity between the pressure plate names corresponding to each pressure plate template frame and the pressure plate names corresponding to each pressure plate detection frame, and eliminates the other pressure plate detection frames that do not meet the detection frame matching condition, so that the number of pressure plate detection frames included in each detected row of the pressure plate captured image is equal to the number of pressure plate template frames included in the template row corresponding to the same row. A setting method of the detection frame matching condition is provided later, which will not be elaborated here for the time being.

[0087] After the above operations, all incorrect pressure plate detection frames in the pressure plate captured image are eliminated, so that the number of rows and columns of the pressure plate template frames included in the pressure plate status panel diagram is exactly the same as the number of rows and columns of the pressure plate detection frames included in the pressure plate captured image. At this time, the pressure plate template frames and the pressure plate detection frames corresponding to the same row and the same column are matched, providing a basis for subsequent pressure plate status verification.

[0088] The process of eliminating incorrect detected rows in the pressure plate captured image will be described below.

[0089] As an optional embodiment, determining the detected rows that meet the row matching condition from each detected row according to the text similarity between the pressure plate names corresponding to each pressure plate template frame and the pressure plate names corresponding to each pressure plate detection frame includes:

[0090] Determine the CTC text similarity product matrix according to the pressing plate names corresponding to the pressing plate template frames and the pressing plate names corresponding to the pressing plate detection frames; wherein, the number of rows of the CTC text similarity product matrix is equal to the total number of template rows, the number of columns of the CTC text similarity product matrix is equal to the total number of detection rows, and each element in the CTC text similarity product matrix represents the product of the CTC text similarities between the pressing plate names corresponding to the pressing plate template frames in this template row and the pressing plate names corresponding to the pressing plate detection frames in this detection row;

[0091] Use the dynamic programming algorithm to select the detection rows that meet the row matching condition from each detection row included in the pressing plate captured image, wherein the number of selected detection rows is equal to the total number of template rows, and the row matching condition is that the total matching value between the selected detection rows and all template rows is the largest, wherein the total matching value is the product of the elements corresponding to the selected detection rows and each template row in the CTC text similarity product matrix.

[0092] Assume that the total number of template rows of the pressing plate state panel diagram is A, and the total number of detection rows of the unprocessed pressing plate captured image is B, and B is greater than A. Determine the CTC text similarity product values between each template row and each detection row according to the text similarity between the pressing plate names corresponding to the pressing plate template frames and the pressing plate names corresponding to the pressing plate detection frames, that is, obtain A*B CTC text similarity product values, and form them into a CTC text similarity product matrix. The number of rows of the CTC text similarity product matrix is equal to the total number of template rows, and the number of columns of the CTC text similarity product matrix is equal to the total number of detection rows.

[0093] Assume that Score(An*Bn) represents the CTC text similarity product value between the nth template row and the nth detection row, and Score(An*Bn) is equal to the product of the CTC text similarities between each pressing plate template frame in the nth template row and each pressing plate detection frame in the nth detection row. The CTC text similarity between each pressing plate template frame and each pressing plate detection frame is determined according to the pressing plate name corresponding to this pressing plate template frame and the pressing plate name corresponding to this pressing plate detection frame.

[0094] After determining the CTC text similarity product matrix, use the dynamic programming algorithm to select A detection rows from each detection row, so that the total matching value between these A detection rows and A template rows is the largest. In this embodiment, the row matching condition is that the total matching value between the selected A detection rows and A template rows is the largest. The total matching value is the product of the elements corresponding to the selected detection rows and each template row in the CTC text similarity product matrix.

[0095] If the number of press plate detection frames included in the detection row corresponding to the same row is equal to the number of press plate verification frames included in the template row, the matching of the press plate detection frame and the press plate template frame can be directly performed; if not, continue to execute the subsequent steps of removing the redundant press plate detection frames.

[0096] In summary, by using the text similarity between the press plate names of the press plates corresponding to each press plate template frame and the press plate names of the press plates corresponding to each press plate detection frame, the incorrect detection rows in the press plate captured image are removed. This method has high reliability and serves as the basis for subsequent press plate status verification.

[0097] The process of removing the incorrect press plate detection frames in the press plate captured image will be described below.

[0098] As an optional embodiment, according to the text similarity between the press plate names of the press plates corresponding to each press plate template frame and the press plate names of the press plates corresponding to each press plate detection frame, each press plate detection frame that meets the detection frame matching condition is determined from the detection row, including:

[0099] For each press plate template frame in the current template row, according to the press plate names of the press plates corresponding to each press plate template frame and the press plate names of the press plates corresponding to each press plate detection frame, the CTC text similarity between this press plate template frame and each press plate detection frame in the same row is determined to obtain a CTC text similarity matrix;

[0100] Among them, the number of rows of the CTC text similarity matrix is the number of press plate template frames included in the current template row, the number of columns of the CTC text similarity matrix is the number of press plate detection frames included in the detection row in the same row as the current template row, and each element of the CTC text similarity matrix represents the CTC text similarity between the press plate name corresponding to this press plate template frame and the press plate name corresponding to this press plate detection frame;

[0101] The dynamic programming algorithm is used to select the press plate detection frames that meet the detection frame matching condition from each press plate detection frame. Among them, the number of selected press plate detection frames is equal to the number of press plate template frames included in the current template row, and the detection frame matching condition is that the product of the CTC text similarities between the press plate names corresponding to the selected press plate detection frames and the press plate names corresponding to each press plate template frame in the current template row is the largest.

[0102] For the template row and the detection row corresponding to the same line, assume that the template row includes A platen template frames, the detection row includes B platen detection frames, and B is greater than A. For each platen template frame in the current template row, according to the platen names of the platens corresponding to each platen template frame and the platen names of the platens corresponding to each platen detection frame, determine the CTC text similarity between this platen template frame and each platen detection frame in the same line, that is, obtain A*B CTC text similarities, and form them into a CTC text similarity matrix. The number of rows of the CTC text similarity matrix is A, and the number of columns is B. Each element of the CTC text similarity matrix represents the CTC text similarity between the platen name corresponding to this platen template frame and the platen name corresponding to this platen detection frame.

[0103] After determining the CTC text similarity matrix, use the dynamic programming algorithm to select A platen detection frames from each platen detection frame, so that the product of the CTC text similarities between these A platen detection frames and the A platen template frames is the largest, and these A platen detection frames are the platen detection frames that meet the detection frame matching conditions selected.

[0104] Please refer to Figure 4 and Figure 5 , Figure 4 is the platen photographing image after removing the incorrect detection rows and incorrect platen detection frames provided by the present invention. Figure 5 is another flowchart of a method for checking the platen state provided by the present invention. After removing the incorrect detection rows and incorrect platen detection frames, the total number of detection rows of the platen photographing image is equal to the total number of template rows of the platen state disk diagram, and the number of platen detection frames included in the detection row in the same line is equal to the number of platen template frames included in the template row. Then, the platen detection frames and platen template frames in the same row and the same column can be matched.

[0105] In summary, using the text similarity between the platen names of the platens corresponding to each platen template frame and the platen names of the platens corresponding to each platen detection frame to remove the incorrect platen detection frames in the platen photographing image, this method has high reliability and lays a foundation for subsequent platen state checking.

[0106] As an optional embodiment, after determining the total number of detection rows and the total number of template rows, it further includes:

[0107] When the total number of template rows is greater than the total number of detection rows, or when the number of platen template frames included in the template row corresponding to the same line is greater than the number of platen detection frames included in the detection row, generate a prompt message for prompting to re-take the platen photographing image.

[0108] As described above, in practical applications, some pressure plates may be missed in the images captured by the pressure plate camera. In this case, the total number of template rows in the pressure plate status panel diagram is greater than the total number of detected rows in the pressure plate camera image, and / or the number of pressure plate template frames included in the template row corresponding to the same row is greater than the number of pressure plate detection frames included in the detected row. At this time, a prompt message for prompting to re-capture the pressure plate camera image is generated to prompt the user to re-capture the pressure plate camera image, and after obtaining a new pressure plate camera image, each step of the pressure plate status verification method provided by the present invention can be executed again.

[0109] The specific process of extracting relevant information of each pressure plate from the pressure plate status panel diagram will be described below.

[0110] As an optional embodiment, extracting the pressure plate name, standard input / output state, pressure plate template frame corresponding to each pressure plate, and position information of each pressure plate template frame of each pressure plate in the substation from the obtained pressure plate status panel diagram includes:

[0111] Extracting pressure plate template frames that meet the preset parsing conditions from the pressure plate status panel diagram. The preset parsing conditions include that each pressure plate template frame must contain a set of symbols for representing the standard input / output state of the pressure plate and a text box for indicating the pressure plate name;

[0112] For each pressure plate template frame, taking the text in the text box within the pressure plate template frame as the pressure plate name of the pressure plate corresponding to the pressure plate template frame, determining the standard input / output state of the corresponding pressure plate according to the symbols in the pressure plate template frame, and taking the coordinates of the preset point position of the pressure plate template frame as the position information of the pressure plate template frame; wherein, the standard input / output state includes the input state and the output state.

[0113] As Figure 2 shown in the pressure plate status panel diagram, each pressure plate is represented by two vertically aligned circles, and the standard input / output state of the pressure plate is represented by combining two vertical lines. Each pressure plate also corresponds to a text box. Based on this, in this embodiment, each pressure plate template frame must contain a set of symbols for representing the standard input / output state of the pressure plate (such as Figure 2 the two vertically aligned circles and two vertical lines in

[0114] As a specific implementation manner, the coordinates of the circles corresponding to each pressure plate, the coordinates of each vertical line, and the content and coordinates of each text box can be extracted from the pressure plate status panel diagram in excel format through VBA code, and the pressure plate template frames corresponding to each pressure plate can be extracted according to the above preset parsing conditions.

[0115] The process of identifying relevant information of each pressure plate from the images taken of the pressure plates will be described below.

[0116] As an alternative embodiment, identifying the pressure plate names, actual switching states, pressure plate detection frames corresponding to each pressure plate, and position information of each pressure plate detection frame included in the images taken of the pressure plates includes:

[0117] Using a target neural network to identify the images taken of the pressure plates to determine the actual switching states, corresponding pressure plate nameplates, corresponding pressure plate detection frames, and position information of each pressure plate detection frame;

[0118] Among them, the actual switching state includes the input state and the withdrawal state. The pressure plate detection frame corresponding to each pressure plate includes the appearance image of the pressure plate and the pressure plate nameplate corresponding to the pressure plate. The coordinates of the preset points of each pressure plate detection frame are used as the position information of the pressure plate detection frame;

[0119] Using a text recognition neural network to identify each pressure plate nameplate to determine the pressure plate name of each pressure plate.

[0120] Please refer to Figure 3 , Figure 3 , which is an image of the pressure plates provided by the present invention. When the actual switching state of the pressure plate is the input state, its appearance is significantly different from that when its actual switching state is the withdrawal state. Therefore, in this embodiment, a target neural network is used to identify the images taken of the pressure plates to determine the actual switching states, corresponding pressure plate nameplates, corresponding pressure plate detection frames, and position information of each pressure plate detection frame. The appearance image of each pressure plate and the pressure plate nameplate corresponding to the pressure plate are respectively divided into different pressure plate detection frames. A text recognition neural network is used to identify each pressure plate nameplate to determine the pressure plate name of each pressure plate.

[0121] Please refer to Figure 6 , Figure 6 , which is a schematic structural diagram of a pressure plate state verification system provided by the present invention. The pressure plate state verification system includes:

[0122] A panel diagram information extraction unit 601, configured to extract the pressure plate names, standard switching states, pressure plate template frames corresponding to each pressure plate, and position information of each pressure plate template frame of each pressure plate in the substation from the obtained pressure plate state panel diagram;

[0123] A pressure plate image information extraction unit 602, configured to identify the pressure plate names, actual switching states, pressure plate detection frames corresponding to each pressure plate, and position information of each pressure plate detection frame included in the images taken of the pressure plates;

[0124] A matching unit 603, configured to process the pressed plate captured image according to the position information of each pressed plate template frame, the position information of each pressed plate detection frame, and the text similarity between the pressed plate names corresponding to the pressed plate template frames and the pressed plate names corresponding to the pressed plate detection frames, so that the number of rows and columns of the pressed plate detection frames included in the pressed plate captured image is the same as the number of rows and columns of the pressed plate template frames included in the pressed plate status panel diagram, and match the pressed plate template frames and the pressed plate detection frames corresponding to the same row and the same column;

[0125] A status detection unit 604, configured to determine whether the withdrawal status of each pressed plate is normal according to whether the actual withdrawal status of the pressed plate detection frame corresponding to the pressed plate is consistent with the standard withdrawal status of the pressed plate template frame corresponding to the pressed plate.

[0126] For a detailed introduction to the pressed plate status verification system provided by the present invention, please refer to the embodiments of the above-mentioned pressed plate status verification method, and the present invention will not be elaborated here.

[0127] Please refer to Figure 7 , Figure 7 FIG. is a schematic structural diagram of a pressed plate status verification device provided by the present invention. The pressed plate status verification device includes:

[0128] A memory 701, configured to store a computer program;

[0129] A processor 702, configured to implement the steps of any of the above-mentioned pressed plate status verification methods when executing the computer program.

[0130] For a detailed introduction to the pressed plate status verification device provided by the present invention, please refer to the embodiments of the above-mentioned pressed plate status verification method, and the present invention will not be elaborated here.

[0131] The present invention further provides a storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned pressed plate status verification methods are implemented.

[0132] For a detailed introduction to the storage medium provided by the present invention, please refer to the embodiments of the above-mentioned pressed plate status verification method, and the present invention will not be elaborated here.

[0133] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. It should also be noted that in this specification, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, article or device. Without further limitation, an element defined by the statement "comprising a..." does not exclude the presence of additional identical elements in the process, article or device comprising the element.

[0134] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for checking the state of a pressing plate, characterized in that, Including: Extracting the name of each pressure plate, the standard on / off state, the pressure plate template frame corresponding to each pressure plate, and the position information of each pressure plate template frame of the substation from the obtained pressure plate state panel diagram; Identifying the name of each pressure plate, the actual on / off state, the pressure plate detection frame corresponding to each pressure plate, and the position information of each pressure plate detection frame included in the pressure plate captured image; According to the position information of each pressure plate template frame, dividing the pressure plate template frames in the same row in the pressure plate state panel diagram into the same template row, and determining the total number of template rows of the pressure plate state panel diagram; According to the position information of each pressure plate detection frame, dividing the pressure plate detection frames in the same row in the pressure plate captured image into the same detection row, and determining the total number of detection rows of the pressure plate captured image; When the total number of template rows is less than the total number of detection rows, determining the CTC text similarity product value between each template row and each detection row according to the text similarity between the name of the pressure plate corresponding to each pressure plate template frame and the name of the pressure plate corresponding to each pressure plate detection frame, and forming a CTC text similarity product matrix; The CTC text similarity product value is equal to the product of the CTC text similarities between each pressure plate template frame in the current template row and each pressure plate detection frame in the current detection row; Using the dynamic programming algorithm to select the detection rows that meet the row matching condition from each detection row included in the pressure plate captured image, and eliminating the detection rows that do not meet the row matching condition; the number of selected detection rows is equal to the total number of template rows, and the row matching condition is that the total matching value between the selected detection row and all template rows is the largest, and the total matching value is the product of the elements corresponding to the selected detection row and each template row in the CTC text similarity product matrix; When the number of pressure plate template frames included in the template row corresponding to the same row is less than the number of pressure plate detection frames included in the detection row, determining the CTC text similarity between the name of the pressure plate corresponding to each pressure plate template frame in the current template row and the name of the pressure plate corresponding to each pressure plate detection frame in the current detection row; using the dynamic programming algorithm to select the pressure plate detection frames that meet the detection frame matching condition from each pressure plate detection frame, and eliminating the pressure plate detection frames that do not meet the detection frame matching condition; wherein, the number of selected pressure plate detection frames is equal to the number of pressure plate template frames included in the current template row, and the detection frame matching condition is that the product of the CTC text similarities between the name of the pressure plate corresponding to the selected pressure plate detection frame and the name of the pressure plate corresponding to each pressure plate template frame in the current template row is the largest; When the number of rows and columns of the pressure plate template frames included in the pressure plate state panel diagram is exactly the same as the number of rows and columns of the pressure plate detection frames included in the pressure plate captured image, matching the pressure plate template frames and the pressure plate detection frames corresponding to the same row and the same column; For each pressure plate, determining whether the on / off state of the pressure plate is normal according to whether the actual on / off state of the pressure plate detection frame corresponding to the pressure plate is consistent with the standard on / off state of the pressure plate template frame corresponding to the pressure plate; 2. The method for checking the state of the pressing plate according to claim 1, wherein After determining the total number of detection rows and the total number of template rows, it further includes: When the total number of template rows is greater than the total number of detection rows, or when the number of pressure plate template frames included in the template row corresponding to the same row is greater than the number of pressure plate detection frames included in the detection row, a prompt message for prompting to re-take the pressure plate image is generated.

3. The method for checking the state of the pressing plate according to claim 1, characterized in that Extracting the pressure plate name, standard switching state, pressure plate template frame corresponding to each pressure plate, and position information of each pressure plate template frame of each pressure plate in the substation from the obtained pressure plate status panel diagram includes: Extracting the pressure plate template frames that meet the preset parsing conditions from the pressure plate status panel diagram, where the preset parsing conditions include that each pressure plate template frame must contain a set of symbols for representing the standard switching state of the pressure plate and a text box for indicating the pressure plate name; For each pressure plate template frame, taking the text in the text box within the pressure plate template frame as the pressure plate name of the pressure plate corresponding to the pressure plate template frame, determining the standard switching state of the corresponding pressure plate according to the symbols in the pressure plate template frame, and taking the coordinates of the preset point position of the pressure plate template frame as the position information of the pressure plate template frame; wherein, the standard switching state includes the input state and the withdrawal state.

4. The press plate state verification method according to claim 1, wherein, Identifying the pressure plate name, actual switching state, pressure plate detection frame corresponding to each pressure plate, and position information of each pressure plate detection frame included in the pressure plate image includes: Using a target neural network to identify the pressure plate image to determine the actual switching state, corresponding pressure plate nameplate, corresponding pressure plate detection frame, and position information of each pressure plate detection frame of each pressure plate; Wherein, the actual switching state includes the input state and the withdrawal state, each pressure plate detection frame corresponding to a pressure plate includes the appearance image of the pressure plate and the pressure plate nameplate corresponding to the pressure plate, and taking the coordinates of the preset point position of each pressure plate detection frame as the position information of the pressure plate detection frame; Using a text recognition neural network to identify each pressure plate nameplate to determine the pressure plate name of each pressure plate.

5. A platen state verification system, characterized in that, Including: A panel diagram information extraction unit for extracting the pressure plate name, standard switching state, pressure plate template frame corresponding to each pressure plate, and position information of each pressure plate template frame of each pressure plate in the substation from the obtained pressure plate status panel diagram; A pressure plate image information extraction unit for identifying the pressure plate name, actual switching state, pressure plate detection frame corresponding to each pressure plate, and position information of each pressure plate detection frame included in the pressure plate image; A matching unit for processing the pressure plate image according to the position information of each pressure plate template frame, the position information of each pressure plate detection frame, and the text similarity between the pressure plate name of the pressure plate corresponding to each pressure plate template frame and the pressure plate name of the pressure plate corresponding to each pressure plate detection frame, so that the number of rows and columns of the pressure plate detection frames included in the pressure plate image is consistent with the number of rows and columns of the pressure plate template frames included in the pressure plate status panel diagram, and matching the pressure plate template frames and the pressure plate detection frames corresponding to the same row and the same column; A state detection unit for determining whether the switching state of each pressure plate is normal according to whether the actual switching state of the pressure plate detection frame corresponding to the pressure plate is consistent with the standard switching state of the pressure plate template frame corresponding to the pressure plate for each pressure plate; The matching unit is specifically used for: According to the position information of each platen template frame, divide the platen template frames in the same row in the platen status panel diagram into the same template row, and determine the total number of template rows in the platen status panel diagram; According to the position information of each platen detection frame, divide the platen detection frames in the same row in the platen captured image into the same detection row, and determine the total number of detection rows in the platen captured image; When the total number of template rows is less than the total number of detection rows, determine the CTC text similarity product value between each template row and each detection row according to the text similarity between the platen names of the platens corresponding to each platen template frame and the platen names of the platens corresponding to each platen detection frame, and form a CTC text similarity product matrix; The CTC text similarity product value is equal to the product of the CTC text similarities between each platen template frame in the current template row and each platen detection frame in the current detection row; Use the dynamic programming algorithm to select the detection rows that meet the row matching condition from each detection row included in the platen captured image, and eliminate the detection rows that do not meet the row matching condition; the number of selected detection rows is equal to the total number of template rows, and the row matching condition is that the total matching value between the selected detection row and all template rows is the largest, and the total matching value is the product of the elements corresponding to the selected detection row and each template row in the CTC text similarity product matrix; When the number of platen template frames included in the template row corresponding to the same row is less than the number of platen detection frames included in the detection row, determine the CTC text similarity between the platen names of the platens corresponding to each platen template frame in the current template row and the platen names of the platens corresponding to each platen detection frame in the current detection row; use the dynamic programming algorithm to select the platen detection frames that meet the detection frame matching condition from each platen detection frame, and eliminate the platen detection frames that do not meet the detection frame matching condition; among them, the number of selected platen detection frames is equal to the number of platen template frames included in the current template row, and the detection frame matching condition is that the product of the CTC text similarities between the platen names corresponding to the selected platen detection frames and the platen names corresponding to each platen template frame in the current template row is the largest; When the number of rows and columns of the platen template frames included in the platen status panel diagram is exactly the same as the number of rows and columns of the platen detection frames included in the platen captured image, match the platen template frames and platen detection frames corresponding to the same row and the same column.

6. A pressing plate state verification device, characterized in that, Comprising: A memory for storing a computer program; A processor for implementing the steps of the platen status verification method according to any one of claims 1 to 4 when executing the computer program.

7. A storage medium, characterized in that, A computer program is stored on the storage medium, and when the computer program is executed by the processor, the steps of the platen status verification method according to any one of claims 1 to 4 are implemented.

Images