A method, device, equipment and readable storage medium for checking disconnected wiring

By applying the disassembly and wiring verification method based on the scale-invariant feature conversion algorithm in industry, we automatically crop and identify image text, and solve the problems of low manual verification efficiency and poor accuracy, and realize efficient and accurate disassembly and wiring verification, reducing costs .

CN114037711BInactive Publication Date: 2024-11-08WUHAN UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111235428.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-10-22
Publication Date
2024-11-08
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

In industry, when manually checking the wiring of the cabinet, the identification errors are caused due to abnormal cognitive and low efficiency, resulting in safety hazards and high costs.

Method used

The wiring disassembly checking method based on the scale-invariant feature conversion algorithm is used to obtain the images before and after disassembly, calculate the affine transformation matrix, crop and identify text information, and automatically determine whether there are errors in the wiring disassembly process.

Benefits of technology

Improve the accuracy and efficiency of wiring disassembly and check, reduce labor costs, and reduce error identification and verification time.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114037711B_ABST
    Figure CN114037711B_ABST
Patent Text Reader

Abstract

The present application relates to a method, device, equipment and readable storage medium for checking the disconnection of the wires, including obtaining a pre-disconnection image and a post-connection image; determining a first feature point set of the pre-disconnection image and a second feature point set of the post-connection image based on a scale-invariant feature conversion algorithm, and converting the first feature point set and the second feature point set into a first array and a second array respectively; calculating an affine transformation matrix according to the first array and the second array; detecting whether the photographing range of the pre-disconnection image is smaller than the photographing range of the post-connection image; if so, determining a range to be cropped of the post-connection image based on the affine transformation matrix and the pre-disconnection image and cropping the post-connection image; respectively recognizing the text in the pre-disconnection image and the cropped wiring image, obtaining a first character recognition result and a second character recognition result, and then determining whether there is an error in the disconnection process. The present application can improve the accuracy and efficiency of disconnection of the wires and reduce labor costs.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of industrial scene technology, and in particular to a disconnected wire verification method, device, equipment and readable storage medium. Background Art

[0002] With the development of industry and the emergence of large-scale complex human-machine systems, negligence and errors caused by human factors are becoming increasingly difficult to ignore. Industrial fields represented by the nuclear industry are particularly affected, and such omissions can easily cause safety hazards and serious losses.

[0003] In industry, for the scenario of rewiring and comparing a large number of dense and complex cabinet wiring, the traditional method uses manual comparison to check the changed wiring. That is, the staff holds the wiring guidance document, and carefully finds the corresponding wiring and operates it according to the guidance document during the wiring removal process, and checks the wiring again before and after the wiring is removed according to the guidance document to see if it is correct. This method has the following problems: First, due to abnormalities in the human cognitive process, such as forgetfulness, lack of attention and negligence, it is easy for manual recognition errors to occur when checking more complex and dense multiple lines; second, it takes a long time to manually find the target wiring, and it is necessary for manual review and comparison based on the guidance document twice, which leads to low efficiency and high labor costs. Summary of the invention

[0004] The present application provides a disconnected wire verification method, device, equipment and readable storage medium to solve the problems of poor accuracy, low efficiency and high labor cost caused by manual identification in the related art.

[0005] In a first aspect, a disconnected wire verification method is provided, comprising the following steps:

[0006] Obtain images before and after stitches are removed;

[0007] Based on the scale-invariant feature conversion algorithm, a first feature point set of the image before stitches are removed and a second feature point set of the image after stitches are connected are determined respectively, the first feature point set is converted into a first array, and the second feature point set is converted into a second array;

[0008] Calculate an affine transformation matrix according to the first array and the second array;

[0009] Check whether the photographing range of the image before stitch removal is smaller than the photographing range of the image after stitching;

[0010] If so, determining the to-be-cropped range of the image after stitching based on the affine transformation matrix and the image before stitching removal, and performing a cropping process on the image after stitching based on the to-be-cropped range to obtain a cropped stitching image;

[0011] Recognize the text in the image before stitch removal to obtain a first character recognition result, and recognize the text in the cropped stitch image to obtain a second character recognition result;

[0012] It is determined whether there is an error in the unbinding process based on the first character recognition result and the second character recognition result.

[0013] In some embodiments, the first feature point set includes a plurality of first feature points and a descriptor vector corresponding to each first feature point, and the second feature point set includes a plurality of second feature points and a descriptor vector corresponding to each second feature point.

[0014] In some embodiments, determining the to-be-cropped range of the image after stitching based on the affine transformation matrix and the image before stitching removal includes:

[0015] The to-be-cropped range of the stitched image is calculated based on the affine transformation matrix and the first array of the pre-stitch-removal image.

[0016] In some embodiments, the recognizing the text in the image before stitch removal to obtain a first character recognition result, and recognizing the text in the cropped stitch image to obtain a second character recognition result, include:

[0017] Recognize the characters in the image before stitches are removed based on optical character recognition technology to obtain a first character recognition result of the image before stitches are removed, wherein the first character recognition result includes a first character position, a first line division result, and a first character recognition result of each character in the image before stitches are removed;

[0018] The text in the cropped wiring image is recognized based on optical character recognition technology to obtain a second character recognition result of the cropped wiring image, wherein the second character recognition result includes a second character position, a second line branch result, and a second text recognition result of each text in the cropped wiring image.

[0019] In some embodiments, determining whether there is an error in the disconnection process based on the first character recognition result and the second character recognition result includes:

[0020] Displaying the first character recognition result by row according to the first row division result to obtain a plurality of unstitching row display objects, and displaying the second character recognition result by row according to the second row division result to obtain a plurality of connecting row display objects;

[0021] Comparing each stitch removal row display object with a connection row display object corresponding to the stitch removal row display object based on the first character position, the first text recognition result, the second character position and the second text recognition result to obtain a comparison result;

[0022] It is determined whether there is an error in the wiring disconnection process according to the comparison result.

[0023] In some embodiments, after the step of determining whether there is an error in the wiring disconnection process based on the first character recognition result and the second character recognition result, the method further includes:

[0024] The judgment result of whether there is an error in the wiring removal process is displayed visually.

[0025] In some embodiments, after the step of detecting whether the photographing range of the image before stitches are removed is smaller than the photographing range of the image after stitches are connected, the method further includes:

[0026] If not, determining a to-be-cropped range of the image before suture removal based on the affine transformation matrix and the image after suture removal, and performing a cropping process on the image before suture removal based on the to-be-cropped range to obtain a cropped suture removal image;

[0027] Recognize the text in the cropped stitch-removed image to obtain a third character recognition result, and recognize the text in the stitch-removed image to obtain a fourth character recognition result;

[0028] It is determined whether there is an error in the wire removal process based on the third character recognition result and the fourth character recognition result.

[0029] In a second aspect, a disconnected wire checking device is provided, comprising:

[0030] An image acquisition unit, which is used to acquire images before and after stitches are removed;

[0031] An image registration unit, which is used to determine a first feature point set of the image before suture removal and a second feature point set of the image after suture connection based on a scale-invariant feature conversion algorithm, convert the first feature point set into a first array, and convert the second feature point set into a second array;

[0032] A transformation and cropping unit, which is used to calculate an affine transformation matrix according to the first array and the second array; detect whether the photographing range of the image before stitches are removed is smaller than the photographing range of the image after stitches are connected; if so, determine the to-be-cropped range of the image after stitches are connected based on the affine transformation matrix and the image before stitches are removed, and crop the image after stitches based on the to-be-cropped range to obtain a cropped stitching image;

[0033] A character recognition unit, which is used to recognize the characters in the image before stitch removal to obtain a first character recognition result, and recognize the characters in the cropped stitch image to obtain a second character recognition result;

[0034] The wire stripping checking unit is used to determine whether there is an error in the wire stripping process based on the first character recognition result and the second character recognition result.

[0035] In a third aspect, a disassembled wire verification device is provided, comprising: a memory and a processor, wherein the memory stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement the aforementioned disassembled wire verification method.

[0036] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer storage medium stores computer instructions, and when the computer instructions are executed by a computer, the computer executes the aforementioned disconnection wire verification method.

[0037] The beneficial effects brought about by the technical solution provided by the present application include: not only can the accuracy and efficiency of disconnection wiring verification be effectively improved, but also labor costs can be reduced.

[0038] The present application provides a method, device, equipment and readable storage medium for checking the wiring after the wiring is removed, including obtaining a pre-stitch removal image and a post-stitch connection image; determining a first feature point set of the pre-stitch removal image and a second feature point set of the post-stitch connection image based on a scale-invariant feature conversion algorithm, converting the first feature point set into a first array, and converting the second feature point set into a second array; calculating an affine transformation matrix according to the first array and the second array; detecting whether the photographing range of the pre-stitch removal image is smaller than the photographing range of the post-stitch connection image; if so, determining a to-be-cropped range of the post-stitch connection image based on the affine transformation matrix and the pre-stitch removal image, and cropping the post-stitch connection image based on the to-be-cropped range to obtain a cropped wiring image; recognizing text in the pre-stitch removal image to obtain a first character recognition result, and recognizing text in the cropped wiring image to obtain a second character recognition result; and determining whether there is an error in the wiring removal process based on the first character recognition result and the second character recognition result. The present application reduces the possibility of image mismatching through a scale-invariant feature conversion algorithm, improves the stability of image features, and detects whether the wiring is correct by comparing the text information in the two images, thereby quickly finding out incorrect wiring without manual verification. This can not only effectively improve the accuracy of wiring verification, but also reduce the time consumption and labor cost of wiring verification. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0040] Figure 1A schematic diagram of a process flow of a disconnected wire verification method provided in an embodiment of the present application;

[0041] Figure 2 A schematic diagram of the structure of a disconnected wire checking device provided in an embodiment of the present application;

[0042] Figure 3 A schematic diagram of the structure of a disconnected wire checking device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0044] The embodiments of the present application provide a disconnected wire verification method, device, equipment and readable storage medium, which can solve the problems of poor accuracy, low efficiency and high labor cost caused by manual identification in the related art.

[0045] Figure 1 A method for checking disconnected wires provided in an embodiment of the present application includes the following steps:

[0046] Step S10: acquiring an image before stitch removal and an image after stitch connection;

[0047] Exemplarily, in an embodiment of the present application, the camera function in a smart tool such as a mobile phone or tablet can be used to capture the image before stitch removal (for the convenience and simplicity of description, the image before stitch removal will be referred to as img1 hereinafter), as well as the image after stitch removal and reconnection at the same position (for the convenience and simplicity of description, the image after stitch removal will be referred to as img2 hereinafter) and save them; and the present application can obtain img1 and img2 from the smart tool in a limited or wireless manner, save the paths of img1 and img2 in img_dir, and then obtain img1 and img2 in sequence.

[0048] Step S20: determining a first feature point set of the image before stitches are removed and a second feature point set of the image after stitches are connected based on a scale-invariant feature conversion algorithm, converting the first feature point set into a first array, and converting the second feature point set into a second array;

[0049] The first feature point set includes a plurality of first feature points and a descriptor vector corresponding to each first feature point, and the second feature point set includes a plurality of second feature points and a descriptor vector corresponding to each second feature point;

[0050] For example, in the embodiment of the present application, SIFT (Scale-invariant feature transform) included in the opencv (cross-platform computer vision and machine learning software library) library is used for image registration. SIFT is a machine vision algorithm used to detect and describe local features in images. It searches for extreme points in the spatial scale and extracts their position, scale, and rotation invariants.

[0051] Specifically, take the image registration process of img1 as an example: SIFT first uses the Gaussian blur algorithm to obtain the scale space of img1 and find multiple scale and rotation invariant interest points; then selects local extreme points in the preset space where each interest point is located as candidate points for key points, and obtains multiple candidate points. Since some candidate points may be relatively difficult to identify or susceptible to noise interference, each candidate point can be located by the information of pixels near the candidate point, the size of the candidate point, and the main curvature of the candidate point, thereby eliminating edge candidate points located on the edge or susceptible to noise interference. The remaining candidate points are key points, forming a key point list kp1;

[0052] Then, the position and scale of each key point are accurately determined through the fitting function, and one or more directions are determined for each key point based on the local features of the image where the key point is located; for example, after calculating the value and direction of the gradient between a key point and its adjacent pixels, a histogram with 36 bars in units of 10 degrees is established for the key point, and each adjacent pixel is added to the histogram of the key point according to its value and direction. Finally, the direction of the maximum value in the histogram is the direction of the key point. It can be seen that a key point will generate a feature point with position, scale, and direction. Therefore, a series of feature points will be generated in img1 and form the first A feature point set; for each feature point, a descriptor vector des1 is established, the information of the feature point is expressed by a vector, and feature point matching is performed, wherein the feature point matching process is as follows: for each feature point in img1, the descriptor vector is used to find the two nearest feature points in img2 whose corresponding Euclidean distance is less than the set threshold, and then the matching that satisfies the conditions is selected by comparing the ratio of the nearest neighbor distance to the next nearest neighbor distance with another empirical threshold, and after traversal, the corresponding feature point in img2 is found for each feature point in img1 that has a matching that satisfies the conditions; finally, the first feature point is converted into an array and the first array is obtained. Since the processing method and steps for obtaining the second feature point set and the second array of img2 are the same as those of img1, they will not be repeated here.

[0053] Step S30: Calculate an affine transformation matrix according to the first array and the second array;

[0054] Exemplarily, in an embodiment of the present application, the first array and the second array are respectively sets of img1 feature points and img2 feature points that meet the conditions, and multiple matches can be obtained through feature point matching, that is, point pairs formed by multiple first feature points in the first array and second feature points in the second array; then, the correspondence between the points in the first array and the second array is expressed by the homography matrix, that is, the required affine transformation matrix; wherein the homography matrix is ​​a point-to-point mapping, which can accurately indicate the exact position of a point corresponding to a point on another image.

[0055] Step S40: Detect whether the photographing range of the image before stitches are removed is smaller than the photographing range of the image after stitches are connected; if so, determine the to-be-cropped range of the image after stitches are connected based on the affine transformation matrix and the image before stitches are removed, and perform a cropping process on the image after stitches are connected based on the to-be-cropped range to obtain a cropped stitching image;

[0056] The to-be-cropped range of the stitched image is calculated based on the affine transformation matrix and the first array of the pre-stitch-removal image.

[0057] Exemplarily, in the embodiment of the present application, if the photographing range of img1 is smaller than the photographing range of img2, then the affine transformation matrix is ​​applied to img1, that is, the to-be-cropped range of img2 is calculated according to the affine transformation matrix and the first array of img1, and img2 is cropped according to the to-be-cropped range to remove the irrelevant wiring area in img2 to prevent interference with the recognition result, and a cropped wiring image is obtained (for the convenience and simplicity of description, the cropped wiring image will be referred to as img2_dec hereinafter), and the transformed img1 is still saved as img1;

[0058] Step S50: recognizing the text in the image before stitch removal to obtain a first character recognition result, and recognizing the text in the cropped stitch image to obtain a second character recognition result;

[0059] Specifically, the text in the image before stitches are removed is recognized based on the optical character recognition technology to obtain a first character recognition result of the image before stitches are removed, the first character recognition result including a first character position of each text in the image before stitches are removed, a first line division result, and a first text recognition result; the text in the cropped wiring image is recognized based on the optical character recognition technology to obtain a second character recognition result of the cropped wiring image, the second character recognition result including a second character position of each text in the cropped wiring image, a second line division result, and a second text recognition result;

[0060] By way of example, in an embodiment of the present application, the text recognition method of img1 is taken as an example: based on OCR (Optical Character Recognition) technology, img1 is subjected to image preprocessing, layout analysis, character cutting, character recognition, layout restoration, and proofreading; wherein OCR refers to the process in which an electronic device checks characters printed on paper, determines their shapes by detecting dark and light patterns, and then uses character recognition methods to translate the shapes into computer text.

[0061] In the image preprocessing stage, image binarization and denoising are performed on img1 to improve the actual image data of img1, enhance specific image features, and thus improve the image quality of img1; in the layout analysis section, img1 is divided into lines according to the wire number positions in img1 to obtain the line division results; in the character cutting stage, each line in img1 is divided into words to obtain the character positions of each word; in the character recognition stage, each cut character is identified by feature extraction to obtain the text recognition results of each word; according to the line division results, character positions and text recognition results, Get the character recognition results of each line in img1; in the layout recovery stage, output each line of character recognition results to a text file according to the character position, line division results, and recognition results; in the proofreading stage, correct each line of character recognition results, and after correction, you can get the accurate first character recognition result of img1. It is explained that in this process, it is allowed to modify the character recognition results interactively; then save the first character recognition result containing information such as text box position, text content, confidence, etc. as a list result1, and save the text content in the form of a text file to the specified save path. Since the processing method and steps for obtaining the second character recognition result of img2 are the same as those of img1, they will not be repeated here.

[0062] Step S60: determining whether there is an error in the disconnection process based on the first character recognition result and the second character recognition result.

[0063] Specifically, the first character recognition result is displayed row by row according to the first row branch result to obtain a plurality of stitch removal row display objects, and the second character recognition result is displayed row by row according to the second row branch result to obtain a plurality of connection row display objects; each stitch removal row display object is compared with the connection row display object corresponding to the stitch removal row display object based on the first character position, the first text recognition result, the second character position and the second text recognition result to obtain a comparison result; and whether there is an error in the connection removal process is determined based on the comparison result.

[0064] Exemplarily, in an embodiment of the present application, the first character recognition result of img1 and the second character recognition result of img2 are both output in the form of rows, then img1 can obtain multiple stitch row display objects, and img2 can obtain multiple connection row display objects, and the first character position and the first text recognition result in each stitch row display object and the second character position and the second text recognition result in the connection row display object corresponding to the stitch row display object are compared respectively. If the first character position is inconsistent with the second character position or the first text recognition result is inconsistent with the second text recognition result, it means that an error occurred in the stitch row removal process; if the first character position is the same as the second character position and the first text recognition result is consistent with the second text recognition result, it means that the stitch row removal is correct.

[0065] Furthermore, in the embodiment of the present application, after the step of determining whether there is an error in the wiring disconnection process based on the first character recognition result and the second character recognition result, the following step is also included: visually displaying the determination result of whether there is an error in the wiring disconnection process.

[0066] For example, in this embodiment, in order to enable the staff to know whether the wiring is correct or not at the first time and intuitively, the judgment result of whether there is an error in the wiring process will be displayed visually. For example, if an error occurs in the wiring process, "wiring error" will be displayed as the result; if the wiring is correct, "wiring correct" will be displayed as the result to prompt the staff whether the wiring is successful. It should be noted that the visual display can be an electronic display screen or a smart display tool such as a mobile phone or a tablet. The specific display tool can be determined according to actual needs and is not limited here.

[0067] Furthermore, in an embodiment of the present application, if the photographing range of the image before stitches are removed is larger than the photographing range of the image after stitches are connected, the range to be cropped of the image before stitches are removed is determined based on the affine transformation matrix and the image after stitches are connected, and the image before stitches are cropped based on the range to be cropped to obtain a cropped stitch-removed image; the text in the cropped stitch-removed image is recognized to obtain a third character recognition result, and the text in the image after stitches are connected is recognized to obtain a fourth character recognition result; based on the third character recognition result and the fourth character recognition result, it is determined whether there is an error in the stitch-removing process. Since the processing methods and steps for cropping the image before stitches are removed, the third character recognition result, the fourth character recognition result, and the determination of whether there is an error in the stitch-removing process are the same as the principles of steps S40 to S60 in the above-mentioned embodiment, they will not be repeated here.

[0068] It can be seen that the present application reduces the possibility of image misalignment matching through a scale-invariant feature conversion algorithm, improves the stability of image features, and completes high-quality processing of images in a shorter time. It detects whether the wiring is correct by comparing the text information in the two images, thereby quickly finding out the wrong wiring and promptly remedying the adverse effects caused by the wrong wiring. Therefore, an image comparison and registration method based on computer vision technology is used, and intelligent verification is used instead of manual comparison, with the aim of greatly reducing the time consumption of wiring verification, while reducing the error rate of wiring verification, thereby effectively improving the accuracy and efficiency of wiring verification, and reducing labor costs.

[0069] See also Figure 2 As shown, the embodiment of the present application also provides a disconnected wire checking device, comprising:

[0070] An image acquisition unit, which is used to acquire images before and after stitches are removed;

[0071] An image registration unit, which is used to determine a first feature point set of the image before suture removal and a second feature point set of the image after suture connection based on a scale-invariant feature conversion algorithm, convert the first feature point set into a first array, and convert the second feature point set into a second array;

[0072] A transformation and cropping unit, which is used to calculate an affine transformation matrix according to the first array and the second array; detect whether the photographing range of the image before stitches are removed is smaller than the photographing range of the image after stitches are connected; if so, determine the to-be-cropped range of the image after stitches are connected based on the affine transformation matrix and the image before stitches are removed, and crop the image after stitches based on the to-be-cropped range to obtain a cropped stitching image;

[0073] A character recognition unit, which is used to recognize the characters in the image before stitch removal to obtain a first character recognition result, and recognize the characters in the cropped stitch image to obtain a second character recognition result;

[0074] The wire stripping checking unit is used to determine whether there is an error in the wire stripping process based on the first character recognition result and the second character recognition result.

[0075] It can be seen that although it is inevitable to make mistakes when manually disconnecting and wiring, the staff can use smart tools such as mobile phones and this application to efficiently check whether the disconnection and wiring are correct, reduce the tendency of human errors, and repair the errors at the same time, thereby reducing losses, so as to achieve the purpose of reducing the labor cost of disconnection and wiring verification and improving the accuracy and efficiency of disconnection and wiring verification; therefore, this application conducts real-time automatic and intelligent prevention and control and management of human disconnection and wiring errors, which has practical significance and good application prospects.

[0076] Furthermore, in an embodiment of the present application, the first feature point set includes multiple first feature points and a descriptor vector corresponding to each first feature point, and the second feature point set includes multiple second feature points and a descriptor vector corresponding to each second feature point.

[0077] Furthermore, in the embodiment of the present application, the transformation and cropping unit is specifically used for:

[0078] The to-be-cropped range of the stitched image is calculated based on the affine transformation matrix and the first array of the pre-stitch-removal image.

[0079] Furthermore, in the embodiment of the present application, the text recognition unit is specifically used for:

[0080] Recognize the characters in the image before stitches are removed based on optical character recognition technology to obtain a first character recognition result of the image before stitches are removed, wherein the first character recognition result includes a first character position, a first line division result, and a first character recognition result of each character in the image before stitches are removed;

[0081] The text in the cropped wiring image is recognized based on optical character recognition technology to obtain a second character recognition result of the cropped wiring image, wherein the second character recognition result includes a second character position, a second line branch result, and a second text recognition result of each text in the cropped wiring image.

[0082] Furthermore, in the embodiment of the present application, the disconnected wire checking unit is specifically used for:

[0083] Displaying the first character recognition result by row according to the first row division result to obtain a plurality of unstitching row display objects, and displaying the second character recognition result by row according to the second row division result to obtain a plurality of connecting row display objects;

[0084] Comparing each stitch removal row display object with a connection row display object corresponding to the stitch removal row display object based on the first character position, the first text recognition result, the second character position and the second text recognition result to obtain a comparison result;

[0085] It is determined whether there is an error in the wiring disconnection process according to the comparison result.

[0086] Furthermore, in an embodiment of the present application, the device also includes a display unit, which is used to visually display the determination result of whether there is an error in the wiring disconnection process.

[0087] Furthermore, in an embodiment of the present application, the transformation and cropping unit is also used to: if not, determine the range to be cropped of the image before stitch removal based on the affine transformation matrix and the image after stitching, and crop the image before stitch removal based on the range to be cropped to obtain a cropped stitch removal image; the text recognition unit is also used to: recognize the text in the cropped stitch removal image to obtain a third character recognition result, and recognize the text in the image after stitching to obtain a fourth character recognition result; the stitch removal verification unit is also used to: determine whether there is an error in the stitch removal process based on the third character recognition result and the fourth character recognition result.

[0088] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described device and each unit can refer to the corresponding process in the aforementioned embodiment of the disconnection wiring verification method, and will not be repeated here.

[0089] The apparatus provided in the above embodiment may be implemented in the form of a computer program. The computer program may be Figure 3 The disconnect wiring shown is checked to be running on the device.

[0090] An embodiment of the present application also provides a disconnected wire verification device, comprising: a memory, a processor and a network interface connected via a system bus, wherein at least one instruction is stored in the memory, and the at least one instruction is loaded and executed by the processor to implement all or part of the steps of the aforementioned disconnected wire verification method.

[0091] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 3The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0092] The processor may be a CPU, or other general-purpose processors, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, etc. The processor is the control center of a computer device, and uses various interfaces and lines to connect various parts of the entire computer device.

[0093] The memory can be used to store computer programs and / or modules. The processor realizes various functions of the computer device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a video playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as video data, image data, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device or other volatile solid-state storage device.

[0094] The present application example also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, all or part of the steps of the aforementioned disconnection wire verification method are implemented.

[0095] The embodiment of the present application implements all or part of the aforementioned process, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of each of the above methods when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.

[0096] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, servers or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program codes.

[0097] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0098] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0099] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0100] The above description is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent 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 application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest range consistent with the principles and novel features applied for herein.

Claims

1. A disconnected wire verification method, characterized in that: The following steps are involved: Obtain images before and after stitches are removed; Based on the scale-invariant feature conversion algorithm, a first feature point set of the image before stitches are removed and a second feature point set of the image after stitches are connected are determined respectively, the first feature point set is converted into a first array, and the second feature point set is converted into a second array; Calculate an affine transformation matrix according to the first array and the second array; Check whether the photographing range of the image before stitch removal is smaller than the photographing range of the image after stitching; If so, determining the to-be-cropped range of the image after stitching based on the affine transformation matrix and the image before stitching removal, and performing a cropping process on the image after stitching based on the to-be-cropped range to obtain a cropped stitching image; Recognize the text in the image before stitch removal to obtain a first character recognition result, and recognize the text in the cropped stitch image to obtain a second character recognition result; Determining whether there is an error in the unwinding process based on the first character recognition result and the second character recognition result; The step of recognizing the text in the image before stitch removal to obtain a first character recognition result and recognizing the text in the cropped stitch image to obtain a second character recognition result includes: Recognize the characters in the image before stitches are removed based on optical character recognition technology to obtain a first character recognition result of the image before stitches are removed, wherein the first character recognition result includes a first character position, a first line division result, and a first character recognition result of each character in the image before stitches are removed; Recognize the characters in the cropped wiring image based on optical character recognition technology to obtain a second character recognition result of the cropped wiring image, wherein the second character recognition result includes a second character position of each character in the cropped wiring image, a second line division result, and a second character recognition result; The determining whether there is an error in the wiring disconnection process based on the first character recognition result and the second character recognition result includes: Displaying the first character recognition result by row according to the first row division result to obtain a plurality of unstitching row display objects, and displaying the second character recognition result by row according to the second row division result to obtain a plurality of connecting row display objects; Comparing each stitch removal row display object with a connection row display object corresponding to the stitch removal row display object based on the first character position, the first text recognition result, the second character position and the second text recognition result to obtain a comparison result; It is determined whether there is an error in the wiring disconnection process according to the comparison result.

2. The disconnected wire checking method according to claim 1, characterized in that: The first feature point set includes a plurality of first feature points and a descriptor vector corresponding to each first feature point, and the second feature point set includes a plurality of second feature points and a descriptor vector corresponding to each second feature point.

3. The disconnected wire checking method according to claim 1, characterized in that: The determining of a to-be-cropped range of the image after stitching based on the affine transformation matrix and the image before stitching removal includes: The to-be-cropped range of the stitched image is calculated based on the affine transformation matrix and the first array of the pre-stitch-removal image.

4. The disconnected wire checking method according to claim 1, characterized in that: After the step of determining whether there is an error in the wiring disconnection process based on the first character recognition result and the second character recognition result, the method further includes: The judgment result of whether there is an error in the wiring removal process is displayed visually.

5. The disconnected wire checking method according to claim 1, characterized in that: After the step of detecting whether the photographing range of the image before stitches are removed is smaller than the photographing range of the image after stitches are connected, the method further includes: If not, determining a to-be-cropped range of the image before suture removal based on the affine transformation matrix and the image after suture removal, and performing a cropping process on the image before suture removal based on the to-be-cropped range to obtain a cropped suture removal image; Recognize the text in the cropped stitch-removed image to obtain a third character recognition result, and recognize the text in the stitch-removed image to obtain a fourth character recognition result; It is determined whether there is an error in the wire removal process based on the third character recognition result and the fourth character recognition result.

6. A disconnected wire checking device, characterized in that: include: An image acquisition unit, which is used to acquire images before and after stitches are removed; An image registration unit, which is used to determine a first feature point set of the image before suture removal and a second feature point set of the image after suture connection based on a scale-invariant feature conversion algorithm, convert the first feature point set into a first array, and convert the second feature point set into a second array; A transformation and cropping unit, which is used to calculate an affine transformation matrix according to the first array and the second array; detect whether the photographing range of the image before stitches are removed is smaller than the photographing range of the image after stitches are connected; if so, determine the to-be-cropped range of the image after stitches are connected based on the affine transformation matrix and the image before stitches are removed, and crop the image after stitches based on the to-be-cropped range to obtain a cropped stitching image; A character recognition unit, which is used to recognize the characters in the image before stitch removal to obtain a first character recognition result, and recognize the characters in the cropped stitch image to obtain a second character recognition result; a wire removal checking unit, which is used to determine whether there is an error in the wire removal process based on the first character recognition result and the second character recognition result; The character recognition unit is specifically used for: Recognize the characters in the image before stitches are removed based on optical character recognition technology to obtain a first character recognition result of the image before stitches are removed, wherein the first character recognition result includes a first character position, a first line division result, and a first character recognition result of each character in the image before stitches are removed; Recognize the characters in the cropped wiring image based on optical character recognition technology to obtain a second character recognition result of the cropped wiring image, wherein the second character recognition result includes a second character position of each character in the cropped wiring image, a second line division result, and a second character recognition result; The disconnection and wiring verification unit is specifically used for: Displaying the first character recognition result by row according to the first row division result to obtain a plurality of unstitching row display objects, and displaying the second character recognition result by row according to the second row division result to obtain a plurality of connecting row display objects; Comparing each stitch removal row display object with a connection row display object corresponding to the stitch removal row display object based on the first character position, the first text recognition result, the second character position and the second text recognition result to obtain a comparison result; It is determined whether there is an error in the wiring disconnection process according to the comparison result.

7. A disconnected wire checking device, characterized in that: include: A memory and a processor, wherein the memory stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement the disconnected wire verification method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a computer, the computer is enabled to execute the disconnected wire checking method according to any one of claims 1 to 5.