Batch verification method and system for border inspection stamped seals based on image processing

Abstract

The invention relates to the technical field of seal verification, in particular to an image processing-based frontier inspection stamped seal batch verification method and system, and the method comprises the steps: collecting to-be-recognized frontier inspection stamped seal images; the collected image of the border inspection stamped seal is analyzed, and the seal number and the date number of each stamped seal in the image are segmented and recognized; checking whether the identified checked seal number and date are correct or not through a data checking module; and the checked seal number and the date are correctly identified and recorded as passing verification, and the check-in module signs in a holder of the checked checked seal in the Meisha system. Through the image processing technology, the stamps can be accurately and rapidly verified in batches, verification efficiency is improved, and time and labor cost are saved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of seal verification, in particular to a batch verification method and system for border seal based on image processing. BACKGROUND

[0002] The border seal is a seal affixed to the valid travel documents of Chinese citizens (including Hong Kong, Macao and Taiwan compatriots), foreigners and residents of other regions after the entry-exit border defense inspection, which represents the state permission for the person to enter or exit the country and marks the date of entry or exit of China.

[0003] The border seal is divided into three types: exit seal (rectangle), entry seal (ellipse) and transit seal (regular hexagon), among which the exit seal and the entry seal need to be verified for the seal number and the date, and the transit seal only needs to be verified for the date. Each seal is authorized for use by only one border inspection officer at the same time, and each border inspection officer can only hold one exit seal and one entry seal at the same time according to the business needs.

[0004] The traditional seal verification is manually or by using equipment to verify the seal number and date of each seal one by one, which is time-consuming and labor-intensive, and brings great inconvenience to the management. According to the scene requirement, the present application invents a batch verification technology for border seal, which can automatically verify the collected sign-in page images in batches after segmentation and recognition, saving time and effort and improving efficiency. The batch verification system for border seal disclosed in the present application can quickly respond and accurately identify in the verification process, greatly saving the labor cost and time cost.

[0005] The sign-in page for border seal is used for the attendance management of border inspection officers, and records the seals on duty on the same day. Each sign-in page has a unique number at a fixed position, and each page contains 16 seal affixing areas. SUMMARY

[0006] In view of the above technical deficiencies, the present application provides a batch verification method and system for border seal based on image processing, which can effectively analyze the sign-in page image, segment and identify the seal number and date of each seal in the image, and quickly complete the batch verification.

[0007] The present application is implemented by the following technical solutions:

[0008] A batch verification method for border seal based on image processing is provided, which comprises the following steps:

[0009] Step S10: collecting the image of the border seal to be identified;

[0010] Step S20: analyzing the collected image of the border seal, segmenting and identifying the seal number and date of each seal in the image;

[0011] Step S30: data verification is performed to check whether the identified seal number and date are correct;

[0012] Step S40: the seal number and date are identified correctly and recorded as passing the verification, and the holder of the seal passing the verification is signed in the MESA system.

[0013] Preferably, the image of the border inspection seal to be identified in step S10 is collected by scanning the seal-in page of the terminal with a high-speed camera, obtaining image data of the seal-in page containing multiple border inspection seals, the seal-in page is used for attendance management of border inspection personnel, and records the seals of the day's duty, each seal-in page has a unique number in the upper left corner, and each page contains 16 seal areas.

[0014] Preferably, the step of analyzing the collected border inspection seal image in step S20 includes:

[0015] Seal-in page number position detection: a template matching method is used, a standard numbered binary image is used as a template, and the position of the seal-in page number is determined by matching in the seal-in page image. Since the number and the seal area have a fixed relative position, the number position can be used to assist in positioning the subsequent areas;

[0016] Seal area grid segmentation: according to the relative position relationship between the number and the seal area, each seal area is segmented into a separate image, which is convenient for subsequent processing of each seal in the grid;

[0017] Cancel seal detection: the cancel seal is a blue rectangle. By counting the number of blue pixels in each seal area in the HSV color space and setting a blue pixel number threshold, for the area with a number of blue pixels greater than the threshold, the outer contour of the blue area is further detected, and by analyzing the area of the blue contour and the number of blue pixels, it is determined whether the area is canceled;

[0018] Seal detection: each seal-in page can have up to sixteen seals, and the non-cancel seal is red. By detecting the red area in the non-cancel seal area, counting the number of red pixels and analyzing the outer contour area of the red area, it is determined whether the seal is added to the area.

[0019] Preferably, the step S20 of analyzing the collected border inspection seal image further includes judging the category of the border inspection seal, including the exit seal, the entry seal and the transit seal, all of which are red, and their corresponding shapes are rectangular, oval and regular hexagon respectively. According to the shape of the seal, the type of the seal is determined, and the step includes:

[0020] Border inspection stamp shape detection: using an ellipse detection algorithm to determine whether the entry stamp is affixed in the affixed area. For stamp areas that do not meet the ellipse algorithm determination conditions, the Hu moment and corner point number of the convex hull of the red area outer contour are calculated to distinguish between the affixed exit stamp and the affixed transit stamp area;

[0021] Normalization and rotation processing: according to the detected red stamp area, the minimum circumscribed rectangle thereof is calculated, and the same width and height are normalized. For the entry stamp, the major axis direction of the ellipse is rotated to the horizontal direction. For the exit stamp, the long side direction of the rectangle is rotated to the horizontal direction. For the transit stamp, no rotation operation is performed since it is difficult to determine the direction.

[0022] Preferably, the step S20 of segmenting and recognizing the stamp number and date number of each inspection stamp in the image comprises:

[0023] Positioning the date area and segmenting the numbers: The date area of each inspection stamp is fixed. The date area image is cropped according to the analysis of the inspection stamp, and then the date area image is binarized, noise is removed, and the image height is normalized. The minimum circumscribed rectangle is calculated and the long side is rotated to the horizontal direction. The best segmentation point in the date area is determined by horizontal and vertical projection in the binary image, and the date area image is segmented into eight single digit images. To avoid the problem that some digits are lightly colored and binarized into the background color due to uneven distribution of ink or uneven force when stamping, the date area can be divided into three subgraphs of year, month, and day for analysis. In each digit image, the connected domain is calculated, the connected domain with a small area is filtered as noise, the original aspect ratio of the digit is maintained, and the digit image is normalized to a specified size.

[0024] Positioning the stamp number area and segmenting the numbers: The transit stamp does not detect the stamp number. The exit stamp and the entry stamp both have an arrow mark in front of the stamp number. The exit stamp corresponds to a downward arrow mark, and the entry stamp corresponds to an upward arrow mark. A template matching method is used to match the lower half of the binary image of the rotated stamp with the corresponding arrow template. The stamp number area is positioned using the matched arrow position. The stamp number area image is binarized, noise is removed, and the image size is normalized. The best segmentation point in the stamp number area is determined by horizontal and vertical projection in the binary image, and the stamp number area image is segmented into four single digit images. The connected domain is calculated, the noise is filtered, and the digit image size is normalized.

[0025] Preferably, the step S30 of verifying whether the recognized inspection stamp number and date are correct through the data verification module comprises:

[0026] Digit recognition: using a pre-trained SVM model to recognize each digit corresponding to the date and the stamp number, and obtaining the stamp number and the date of each inspection stamp.

[0027] Verification and check-in: the verification stamp number corresponds to the personnel information, checks whether the date is consistent with the system date, and signs in the Masha system for the holder of the verification stamp when the verification is passed.

[0028] In addition, to achieve the above object, the application also provides a border inspection verification stamp batch verification system based on image processing, which comprises:

[0029] The border inspection verification stamp image module is used for collecting the border inspection verification stamp image to be identified.

[0030] The border inspection verification stamp image analysis and identification module is used for analyzing the collected border inspection verification stamp image, segmenting the stamp number and date number of each verification stamp in the image and identifying them.

[0031] The data verification module is used for data verification to check whether the identified verification stamp number and date are correct.

[0032] The check-in module is used for recording the correct identification of the verification stamp number and date as passing the verification, and signing in the Masha system for the holder of the verification stamp passing the verification.

[0033] In addition, to achieve the above object, the application also provides a border inspection verification stamp batch verification device based on image processing, which comprises a memory, a processor and an elliptical detection algorithm program stored in the memory and executable on the processor, wherein the elliptical detection algorithm program is used to realize the steps of the above-mentioned border inspection verification stamp batch verification method based on image processing.

[0034] In addition, to achieve the above object, the application also provides a computer program product, which comprises an elliptical detection algorithm program, and the elliptical detection algorithm program is executed by a processor to realize the above-mentioned border inspection verification stamp batch verification method based on image processing.

[0035] The advantages and effects of the application are as follows:

[0036] The border inspection verification stamp batch verification method and system based on image processing can realize batch verification of border inspection verification stamps, greatly shorten the verification time and improve the work efficiency compared with the traditional way of verifying a single verification stamp each time, and use a variety of optimization algorithms in the image segmentation and identification process, use a pre-trained SVM model in the identification of the stamp number and date, improve the accuracy of the identification of the date and stamp number of the verification stamp, and reduce the errors caused by manual verification or insufficient technology. BRIEF DESCRIPTION OF DRAWINGS

[0037] In order to make the technical solutions in the embodiments of the present application or the prior art clearer, the accompanying drawings needed in the embodiments or prior art description will be briefly introduced. Obviously, the accompanying drawings in the following description only need to be some embodiments of the present application, and other drawings can be obtained by those of ordinary skill in the art without any creative effort.

[0038] Figure 1 A flow chart of a border inspection stamp batch verification method based on image processing according to the present application.

[0039] Figure 2 A binary image of three subgraphs in the present application.

[0040] Figure 3 A departure stamp image in the present application.

[0041] Figure 4 An image of the stamp number region image normalization in the present application.

[0042] Figure 5 An image of the digital image before removing impurities in the present application.

[0043] Figure 6 An image of the digital image after removing impurities and normalization in the present application.

[0044] Figure 7 A structure schematic diagram of a border inspection stamp batch verification system based on image processing according to the present application.

[0045] Figure 8 A structure schematic diagram of a border inspection stamp batch verification electronic device based on image processing according to the present application. DETAILED DESCRIPTION

[0046] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without any creative effort belong to the scope of protection of the present application.

[0047] As shown in Figure 1 In one embodiment of the present application, a border inspection stamp batch verification method based on image processing includes the following steps:

[0048] Step S10: Collecting a border inspection stamp image to be identified.

[0049] Specifically, the step S10 collects the image of the border inspection seal to be identified, scans the seal-in page through a terminal with a high-speed camera, acquires image data of the seal-in page containing multiple border inspection seals, and the seal-in page is used for the attendance management of the border inspection personnel and records the seals of the daily on-duty. Each seal-in page has a unique number in the fixed position at the top left corner and contains 16 seal areas.

[0050] Step S20: analyzing the collected border inspection seal image, segmenting and identifying the seal number and date number of each seal in the image.

[0051] Specifically, the step S20 of analyzing the collected border inspection seal image includes:

[0052] Seal-in page number position detection: using a template matching method, a standard number binary image is used as a template to match the seal-in page number position in the seal-in page image. Since the number and the seal-in seal area have a fixed relative position, the number position can assist in positioning the subsequent areas;

[0053] Seal-in seal area square segmentation: according to the relative position relationship between the number and the seal-in seal area, each seal-in seal area is segmented into a separate image, which is convenient for subsequent processing of each square seal-in seal;

[0054] Seal-out detection: the seal-out is a blue rectangle. By counting the number of blue pixels in each seal area in the HSV color space and setting a blue pixel number threshold, the area with a number of blue pixels greater than the threshold is further detected for the outer contour of the blue area. By analyzing the area of the blue contour and the number of blue pixels, it is determined whether the area is cancelled;

[0055] Seal-in detection: each seal-in page can have up to sixteen seals. The non-cancelled seal is red. By detecting the red area in the non-cancelled seal area, counting the number of red pixels and analyzing the outer contour area of the red area, it is determined whether the seal-in seal is added in the area.

[0056] Specifically, the step S20 of analyzing the collected border inspection seal image further includes judging the category of the border inspection seal, including the exit seal, the entry seal and the transit seal, all of which are red, and their corresponding shapes are rectangular, elliptical and regular hexagonal, respectively. The seal type is determined according to the seal shape, and the step includes:

[0057] Border inspection seal shape detection: using an ellipse detection algorithm to determine whether the entry seal is added in the seal area. For the seal area that does not meet the determination condition of the ellipse algorithm, the Hu moment and the corner number of the convex hull of the red area contour are calculated to distinguish the seal area of the added exit seal and transit seal;

[0058] Normalization and rotation processing: according to the detected red seal area, the minimum circumscribed rectangle thereof is calculated, and the same width and height are normalized, the long axis direction of the oval is rotated to the horizontal direction for coarse rotation and correction for the entry seal, the long side direction of the rectangle is rotated to the horizontal direction for the exit seal, and no rotation operation is performed for the transit seal because it is difficult to determine the direction.

[0059] Specifically, the step of segmenting and recognizing the seal number and date number of each inspection seal in the image in step S20 includes:

[0060] Positioning the date area and segmenting the numbers: the date area of each inspection seal is fixed, the date area image is cropped according to the analysis of the inspection seal, and then the date area image is processed by binarization, noise removal, normalization of image height, etc., the minimum circumscribed rectangle is calculated and the long side is rotated to the horizontal direction; horizontal and vertical projections are performed in the binary image to determine the best segmentation point in the date area, and the date area image is segmented into eight single number images; in order to avoid the problem that some numbers are light in color and are binarized into the background color due to uneven distribution of ink or uneven force when stamping, the date area can be divided into three subgraphs of year, month and day for analysis, the binarization graphs of the three subgraphs are as shown in Figure 2 , which avoids the problem that some numbers are light in color and are binarized into the background color due to uneven distribution of ink or uneven force when stamping; the connected domains in each number image are calculated, the connected domains with small area are filtered out as noise, and the original aspect ratio of the numbers is kept unchanged, and the number image is normalized to a specified size;

[0061] Positioning the seal number area and segmenting the numbers: the transit seal does not detect the seal number, and the exit seal and the entry seal have arrow marks in front of the seal number; the exit seal corresponds to the downward arrow mark as shown in Figure 3 , and the entry seal corresponds to the upward arrow mark; the template matching method is used to match the lower half of the binary image of the corrected seal with the corresponding arrow template, and the seal number area is positioned by using the matched arrow position; the seal number area image is binarized, noise is removed, and the image size is normalized as shown in Figure 4 ; horizontal and vertical projections are performed in the binary image to determine the best segmentation point in the seal number area, and the seal number area image is segmented into four single number images; the connected domains in each number image are calculated, and the connected domains with small area are filtered out as noise; the original aspect ratio of the numbers is kept unchanged, and the number image is normalized to a specified size as shown in Figure 5 , before removing impurities, as shown in Figure 6 , after removing impurities and normalization.

[0062] Step S30: data verification is performed to verify whether the recognized inspection seal number and date are correct.

[0063] Specifically, in step S30, the data verification module verifies whether the identified seal number and date of the seal are correct, and the step includes:

[0064] Digit recognition: using a pre-trained SVM model to identify each digit corresponding to the date and seal number of the seal, to obtain the seal number and date of each seal;

[0065] Verification and check-in: verifying the personnel information corresponding to the seal number, checking whether the date is consistent with the system date, and checking in the Meisha system for the holder of the seal when the verification is passed.

[0066] Step S40: record the seal number and date as passing the verification if they are correctly identified, and check in the Meisha system for the holder of the seal that has passed the verification.

[0067] In addition, the present application also provides a border inspection seal batch verification system based on image processing, please refer to Figure 7 The border inspection seal batch verification system based on image processing comprises:

[0068] A border inspection seal image module for collecting border inspection seal images to be identified;

[0069] A border inspection seal image analysis and identification module for analyzing the collected border inspection seal images, segmenting and identifying the seal number digits and date digits of each seal in the images;

[0070] A data verification module for data verification to verify whether the identified seal number and date of the seal are correct;

[0071] A check-in module for recording the seal number and date as passing the verification if they are correctly identified, and checking in the Meisha system for the holder of the seal that has passed the verification.

[0072] The border inspection seal batch verification system based on image processing provided by the present application adopts the border inspection seal batch verification method based on image processing in the above embodiment, which can solve the technical problem of low efficiency of the traditional border inspection seal verification method. Compared with the prior art, the border inspection seal batch verification system based on image processing provided by the present application has the same beneficial effects as the border inspection seal batch verification method based on image processing provided by the above embodiment, and other technical features in the border inspection seal batch verification system based on image processing are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0073] The application provides a kind of based on image processing's border inspection stamp batch verification equipment, the kind of based on image processing's border inspection stamp batch verification equipment described in the application includes: at least one processor;And, at least one processor communication connection's memory;Wherein, memory has the instruction that can be executed at least one processor, instruction is executed at least one processor, to make at least one processor can execute the kind of based on image processing's border inspection stamp batch verification method in the embodiment one described above.

[0074] Reference is made below Figure 8 It shows the structure diagram of a kind of based on image processing's border inspection stamp batch verification equipment suitable for being used to realize the embodiment of the application.A kind of based on image processing's border inspection stamp batch verification equipment in the embodiment of the application can include but not limited to mobile terminal such as mobile phone, notebook computer, digital broadcast receiver, PDA (Personal Digital Assistant: personal digital assistant), PAD (Portable Application Description: tablet computer), PMP (Portable Media Player: portable multimedia player) and so on and fixed terminal such as digital TV, desktop computer and so on. Figure 8 The based on image processing's border inspection stamp batch verification equipment shown is only an example, should not bring any limit to the function and use range of the embodiment of the application.

[0075] Figure 8The image processing-based border inspection stamp batch verification device shown can include a processing system 1001 (e.g., a central processing unit, a graphics processing unit, etc.) that can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage system 1003 into a random access memory (RAM) 1004. In the RAM 1004, various programs and data required for the operation of the image processing-based border inspection stamp batch verification device are also stored. The processing system 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input system 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output system 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; the storage system 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication system 1009. The communication system 1009 can allow the image processing-based border inspection stamp batch verification device to communicate with other devices wirelessly or by wire to exchange data. Although an image processing-based border inspection stamp batch verification device having various systems is shown in the figure, it should be understood that all the systems shown are not required to be implemented or possessed. More or fewer systems can be alternatively implemented or possessed.

[0076] In particular, according to embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network through a communication system, or installed from the storage system 1003, or installed from the ROM 1002. When the computer program is executed by the processing system 1001, the above-mentioned functions defined in the methods of the embodiments of the present disclosure are performed.

[0077] The application provides a batch verification equipment for border inspection stamps based on image processing, adopts the batch verification method for border inspection stamps based on image processing in the above embodiment, and can solve the technical problem of low efficiency of the traditional border inspection stamp verification method. Compared with the prior art, the batch verification equipment for border inspection stamps based on image processing has the same beneficial effects as the batch verification method for border inspection stamps based on image processing, and other technical features in the batch verification equipment for border inspection stamps based on image processing are the same as those in the above embodiment, which will not be repeated here.

[0078] Parts of the application can be realized by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0079] The application also provides a computer program product, which comprises a computer program. When the computer program is executed by a processor, the steps of the batch verification method for border inspection stamps based on image processing are realized.

[0080] The computer program product provided by the application can solve the technical problem of low efficiency of the traditional border inspection stamp verification method. Compared with the prior art, the computer program product provided by the application has the same beneficial effects as the batch verification method for border inspection stamps based on image processing, which will not be repeated here.

[0081] Obviously, those skilled in the art can make various modifications and variations to the application without departing from the spirit and scope of the application. Thus, if these modifications and variations of the application belong to the scope of the claims of the application and their equivalents, the application also intends to include these modifications and variations.

Claims

1. An image processing-based border inspection stamp batch verification method, characterized in that, The method comprises the following steps: Step S10: Collecting the image of the border inspection stamp to be identified; Step S20: Analyzing the collected border inspection stamp image, segmenting and identifying the stamp number and date number of each inspection stamp in the image; Step S30: Data verification, checking whether the identified inspection stamp number and date are correct; Step S40: If the inspection stamp number and date are correctly identified, it is recorded as passing the verification, and the holder of the inspection stamp that passes the verification signs in the Meisha system.

2. The image processing-based border inspection stamp batch verification method according to claim 1, characterized in that, In step S10, the image of the border inspection stamp to be identified is collected by scanning the inspection stamp sign-in page through a terminal with a high-speed camera, obtaining the sign-in page image data of the border inspection stamp, and each sign-in page has a unique number in the upper left corner. Each page contains 16 stamping areas.

3. The image processing-based border inspection stamp batch verification method of claim 1, wherein, In step S20, the step of analyzing the collected border inspection stamp image comprises: Sign-in page number position detection: Using template matching method, taking a standard number binary image as a template, matching in the sign-in page image to determine the position of the sign-in page number; Inspection stamp stamping area grid segmentation: According to the relative position relationship between the number and the inspection stamp stamping area, the grid where each inspection stamp stamping area is located is segmented into a separate image; Cancelling stamp detection: The cancellation stamp is a blue rectangle. By counting the number of blue pixels in each stamping area in the HSV color space and setting a blue pixel number threshold, for the area with a number of blue pixels greater than the threshold, further detect the outer contour of the blue area, and by analyzing the area of the blue contour and the number of blue pixels, it is judged whether the area is cancelled; Stamping inspection stamp detection: Non-cancellation stamp is red. By detecting the red area in the non-cancellation stamping area, counting the number of red pixels and analyzing the outer contour area of the red area, it is determined whether the inspection stamp is stamped in the area.

4. The image processing-based border inspection stamp batch verification method of claim 1, wherein, In step S20, the analysis of the collected border inspection stamp image further comprises judging the category of the border inspection stamp, including the exit stamp, the entry stamp and the transit stamp, all of which are red, and their corresponding shapes are rectangle, ellipse and regular hexagon respectively. According to the shape of the stamp, the type of the stamp is determined, and the steps include: Border inspection stamp shape detection: Use the ellipse detection algorithm to determine whether the entry stamp is stamped in the stamping area. For the stamp area that does not meet the judgment condition of the ellipse algorithm, the Hu moment and the number of corner points of the convex hull of the red area contour are calculated to distinguish the stamp area of the stamped exit stamp and the stamped transit stamp; Normalization and rotation processing: According to the detected red stamp area, calculate its minimum bounding rectangle, and normalize it to the same width and height. For the entry stamp, rotate the long axis of the ellipse to the horizontal direction, for the exit stamp, rotate the long side of the rectangle to the horizontal direction, and for the transit stamp, do not perform rotation operation.

5. The image processing-based border inspection stamp batch verification method of claim 1, wherein, In step S20, the step of segmenting and identifying the stamp number and date number of each inspection stamp in the image comprises: Positioning date area and segmenting numbers: The date area of each verification stamp is fixed, the date area image is cropped according to the analysis of the verification stamp, and then the date area image is binarized, noise is removed, the image height is normalized, the minimum bounding rectangle is calculated and the long side is rotated to the horizontal direction; the horizontal and vertical projections are performed in the binary image to determine the best segmentation point in the date area, and the date area image is segmented into eight single number images; the date area is divided into three sub-images of year, month and day for analysis; the connected domains are calculated in each number image, the connected domains with small area are filtered as noise, the original aspect ratio of the number is kept unchanged, and the number image is normalized to a specified size; Positioning stamp number area and segmenting numbers: The transit stamp does not detect the stamp number, and the exit stamp and the entry stamp have arrow marks in front of the stamp number. The exit stamp corresponds to a downward arrow mark, and the entry stamp corresponds to an upward arrow mark. The template matching method is used to match the lower half of the binary image of the rotated stamp with the corresponding arrow template, and the position of the matched arrow is used to locate the stamp number area. The stamp number area image is binarized, noise is removed, and the image size is normalized. The horizontal and vertical projections are performed in the binary image to determine the best segmentation point in the stamp number area, and the stamp number area image is segmented into four single number images. The connected domains are calculated, the noise is filtered, and the number image size is normalized.

6. The image processing-based border inspection stamp batch verification method of claim 1, wherein, The step S30 verifies whether the recognized stamp number and date of the verification stamp are correct through a data verification module, and the step includes: Number recognition: The pre-trained SVM model is used to recognize each number corresponding to the date and the stamp number, to obtain the stamp number and the date of each verification stamp; Verification and check-in: The personnel information corresponding to the stamp number is verified, the date is checked whether it is consistent with the system date, and when the verification is passed, the person holding the verification stamp is checked in the Meisha system.

7. An image processing-based border inspection stamp batch verification system, characterized in that, The batch verification system of the border inspection verification stamp based on image processing includes: A border inspection verification stamp image module is configured to collect border inspection verification stamp images to be recognized. A border inspection verification stamp image analysis and recognition module is configured to analyze the collected border inspection verification stamp images, segment and recognize the stamp number and date of each verification stamp in the images. A data verification module is configured to verify whether the recognized stamp number and date of the verification stamp are correct. A check-in module is configured to record the correct recognition of the stamp number and date of the verification stamp as passing the verification, and check in the person holding the verification stamp that passes the verification in the Meisha system.

8. An image processing-based border inspection stamp batch verification device, characterized by, The batch verification equipment of the border inspection verification stamp based on image processing includes: A memory, a processor, and a batch verification program of the border inspection verification stamp based on image processing stored on the memory and executable on the processor, wherein the batch verification program of the border inspection verification stamp based on image processing is executed by the processor to implement the batch verification method of the border inspection verification stamp based on image processing in any one of claims 1 to 6.

9. A computer program product, characterised in that, The computer program product comprises an image processing-based border inspection stamp batch verification program, and the image processing-based border inspection stamp batch verification program, when executed by a processor, implements the image processing-based border inspection stamp batch verification method in any one of claims 1 to 6.

Images