Payment screenshot recognition method, device, equipment, storage medium and program product

Abstract

The present invention discloses a payment screenshot recognition method, device, equipment, storage medium and program product. The method comprises: determining a payment screenshot image to be recognized according to an image recognition request; determining image information of the payment screenshot image to be recognized, and obtaining a first image judgment result; if the first image judgment result is a normal screenshot image, performing text recognition on the payment screenshot image to be recognized, and obtaining a second image judgment result according to the text recognition result; if the second image judgment result is a normal screenshot image and meets a preset image type judgment condition, extracting a keyword area image in the payment screenshot image to be recognized based on a preset keyword to be recognized; performing character recognition on the keyword area image, and detecting whether the recognized characters meet a preset character alignment judgment condition; if so, determining that the payment screenshot image to be recognized is a normal payment screenshot image.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a payment screenshot recognition method, device, equipment, storage medium and program product. Background Art

[0002] With the popularity of mobile payment, payment screenshots have become a common transaction voucher. However, due to the ease of forgery of payment screenshots, it also brings certain security risks to online payment activities: criminals may tamper with key information such as payment amount, payment time or order number, thereby committing fraud or other illegal activities. However, in the prior art, the means of detecting forgery of payment screenshots are relatively limited, mainly relying on manual review or simple image processing technology. These methods have obvious deficiencies in accuracy and efficiency, especially in payment security, especially in verifying the authenticity of payment screenshots.

[0003] Therefore, how to quickly and accurately verify the authenticity of payment screenshots to avoid affecting the security of payment transactions due to forged payment screenshots has become an urgent problem to be solved. Summary of the invention

[0004] The present invention provides a payment screenshot recognition method, device, equipment, storage medium and program product to improve the recognition accuracy and efficiency of payment screenshots, thereby improving the security and reliability of payment transactions.

[0005] According to one aspect of the present invention, a payment screenshot recognition method is provided, comprising:

[0006] Determine the payment screenshot image to be identified according to the obtained image recognition request;

[0007] Determine the image width, image height and image grayscale information of the payment screenshot image to be identified, and judge whether the payment screenshot image to be identified is a normal screenshot image according to the image width, image height and image grayscale information, to obtain a first image judgment result;

[0008] If the first image judgment result is that the payment screenshot image to be identified is a normal screenshot image, text recognition is performed on the payment screenshot image to be identified, and based on the text recognition result, it is determined whether the payment screenshot image to be identified is a normal screenshot image to obtain a second image judgment result;

[0009] If the second image judgment result is that the payment screenshot image to be identified is a normal screenshot image, and the payment screenshot image to be identified meets the preset image type judgment condition, then based on the preset keywords to be identified, extracting a keyword area image in the payment screenshot image to be identified;

[0010] Performing character recognition on the keyword region image, and detecting whether the recognized characters meet a preset character alignment judgment condition;

[0011] If so, it is determined that the payment screenshot image to be identified is a normal payment screenshot image.

[0012] According to another aspect of the present invention, a payment screenshot recognition device is provided, comprising:

[0013] A payment screenshot to be identified determining module, used to determine the payment screenshot image to be identified according to the acquired image recognition request;

[0014] A first judgment module is used to determine the image width, image height and image grayscale information of the payment screenshot image to be identified, and judge whether the payment screenshot image to be identified is a normal screenshot image according to the image width, image height and image grayscale information, to obtain a first image judgment result;

[0015] A second judgment module is used for, if the first image judgment result is that the payment screenshot image to be identified is a normal screenshot image, performing text recognition on the payment screenshot image to be identified, and judging whether the payment screenshot image to be identified is a normal screenshot image according to the text recognition result, to obtain a second image judgment result;

[0016] A keyword area image extraction module, configured to extract a keyword area image in the payment screenshot image to be identified based on a preset keyword to be identified, if the second image judgment result is that the payment screenshot image to be identified is a normal screenshot image and the payment screenshot image to be identified meets a preset image type judgment condition;

[0017] A character recognition module, used to perform character recognition on the keyword area image and detect whether the recognized characters meet a preset character alignment judgment condition;

[0018] The normal payment screenshot determination module is used to determine that the payment screenshot image to be identified is a normal payment screenshot image if the detected and recognized characters meet a preset character alignment judgment condition.

[0019] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0020] at least one processor; and

[0021] a memory communicatively connected to the at least one processor; wherein,

[0022] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the payment screenshot recognition method described in any embodiment of the present invention.

[0023] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the payment screenshot recognition method described in any embodiment of the present invention when executed.

[0024] According to another aspect of the present invention, a computer program product is provided, the computer program product comprising a computer program, and the computer program, when executed by a processor, implements the payment screenshot recognition method described in any embodiment of the present invention.

[0025] The technical solution of the embodiment of the present invention determines the image information of the payment screenshot image to be identified and obtains the first image judgment result; if the first image judgment result is a normal screenshot image, text recognition is performed on the image content of the payment screenshot image to be identified and a second image judgment result is obtained; if the second image judgment result is a normal screenshot image and the payment screenshot image to be identified meets the preset image type judgment condition, the keyword area image in the payment screenshot image to be identified is extracted; character recognition is performed on the keyword area image, and if the detected and identified characters meet the preset character alignment judgment condition, the payment screenshot image to be identified is determined to be a normal payment screenshot image. This technical solution can accurately identify and verify the authenticity of the payment screenshot by identifying the image information and image content of the payment screenshot to be identified, thereby ensuring the security and reliability of the payment transaction.

[0026] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0028] Figure 1 is a flow chart of a payment screenshot recognition method provided according to Embodiment 1 of the present invention;

[0029] Figure 2is a screenshot of a payment interface of different payment types provided according to the first embodiment of the present invention;

[0030] Figure 3 is a flow chart of a payment screenshot recognition method provided according to Embodiment 2 of the present invention;

[0031] Figure 4 is a structural schematic diagram of a payment screenshot recognition device provided according to Embodiment 3 of the present invention;

[0032] Figure 5 It is a structural schematic diagram of an electronic device that implements the payment screenshot recognition method of an embodiment of the present invention. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0034] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0035] Embodiment 1

[0036] Figure 1 A flowchart of a payment screenshot recognition method is provided for the first embodiment of the present invention. This embodiment is applicable to the case of verifying the authenticity of a payment screenshot. The method can be performed by a payment screenshot recognition device. The payment screenshot recognition device can be implemented in the form of hardware and / or software. The payment screenshot recognition device can be configured in an electronic device. Figure 1 As shown, the method includes:

[0037] S110. Determine the payment screenshot image to be recognized according to the acquired image recognition request.

[0038] The image recognition request may be a request for image recognition of a payment screenshot image, and the image type of the payment screenshot image to be recognized may be "tiff (Tagged Image File Format)", "jpg (Joint Photographic Experts Group)", "png (Portable Network Graphics)", or "bmp (Bitmap)".

[0039] Specifically, the image recognition request is parsed to determine whether the requested data type is included in the data types of "tif", "jpg", "png" and "bmp".

[0040] Furthermore, after determining that the data type of the requested data is data of the type such as "tif", "jpg", "png" or "bmp", the requested data may be converted into image data.

[0041] S120. Determine the image width, image height, and image grayscale information of the payment screenshot image to be identified, and determine whether the payment screenshot image to be identified is a normal screenshot image based on the image width, image height, and image grayscale information, to obtain a first image determination result.

[0042] The image width may refer to the size of the image in the horizontal direction; the image height may refer to the size of the image in the vertical direction, and may be expressed in units of pixels, inches, or points, etc. For example, the image aspect ratio of the payment screenshot image to be identified may be calculated based on the image width and image height of the payment screenshot image to be identified. For example, a 1920x1080 pixel image may be expressed as a width of 1920 pixels, a height of 1080 pixels, and an aspect ratio of 16:9.

[0043] The image grayscale information may represent the information of each pixel in the image obtained by performing a grayscale value calculation method on the payment screenshot image to be identified. The grayscale value calculation method may include an average value method or a maximum and minimum value method, which may be preset by a technician according to actual needs, and this embodiment does not impose any specific restrictions on this.

[0044] Specifically, it can be determined whether the aspect ratio of the payment screenshot image to be identified meets the standard of normal image aspect ratio. For example, the standard of normal image aspect ratio can be 16:9, 18:9 or 20:9, which can be determined by technicians based on experience. Exemplarily, the aspect ratio of the payment screenshot image to be identified can be compared with the standard of normal image aspect ratio. If the aspect ratio of the payment screenshot image to be identified can be 18:9, it can be determined that the payment screenshot image to be identified is a normal screenshot image; if the aspect ratio of the payment screenshot image to be identified is 20:10, it can be determined that the payment screenshot image to be identified is an abnormal screenshot image.

[0045] Furthermore, after screening the payment screenshot images to be identified according to their aspect ratios, it is also possible to determine whether the screening payment screenshot images to be identified are normal based on pixel information in the grayscale image of the payment screenshot images to be identified.

[0046] It should be noted that after secondary processing of the payment screenshot image, such as taking a photo or scanning, the payment screenshot image may contain abnormal pixels due to the influence of light. Therefore, the number of discretely distributed abnormal pixels in the payment screenshot image to be identified can be determined based on the image grayscale information of the payment screenshot image to be identified, or the number of abnormal pixels that seriously deviate from the image grayscale mean can be determined. Determine whether the number of abnormal pixels is greater than the set mean of abnormal pixels; if so, determine that the payment screenshot image to be identified is an abnormal screenshot image; if not, determine that the payment screenshot image to be identified is a normal screenshot image.

[0047] S130. If the first image judgment result is that the payment screenshot image to be identified is a normal screenshot image, text recognition is performed on the payment screenshot image to be identified, and based on the text recognition result, it is determined whether the payment screenshot image to be identified is a normal screenshot image to obtain a second image judgment result.

[0048] Among them, text recognition can specifically be to extract the text content in the payment screenshot image to be recognized. Specifically, the text content of the payment screenshot image to be recognized can be extracted by text recognition technology such as OCR (Optical Character Recognition) or spectral character recognition technology. The technology for extracting this content can be pre-set by the technician according to actual needs, and this embodiment does not make specific restrictions on this.

[0049] Optionally, text recognition is performed on the payment screenshot image to be identified, and based on the text recognition result, it is determined whether the payment screenshot image to be identified is a normal screenshot image to obtain a second image judgment result, including: performing text recognition on the payment screenshot image to be identified to obtain the number of characters and character pixel coordinates of the characters contained in the payment screenshot image to be identified; if the number of characters meets the preset character number threshold judgment condition, then based on the character pixel coordinates, based on the horizontal pixel range threshold and the vertical pixel range threshold, it is determined whether the corresponding character is a tilted character to obtain a character tilt judgment result; based on the character request judgment result, the second image judgment result is determined.

[0050] The number of characters may be the number of content characters used to represent the payment activity obtained by performing text recognition on the payment screenshot image to be recognized. The content characters may include payment time, transaction order number, transaction status, etc.

[0051] Specifically, the character quantity threshold judgment condition can be used to judge whether the number of content characters representing the payment activity meets the number of content characters required to complete a payment activity, such as the payment time and transaction number, or the payment time, transaction number and transaction status, etc., to determine that a payment activity is completed. Based on this, it can be determined whether the number of characters contained in the payment screenshot image to be identified meets the preset character quantity threshold judgment condition.

[0052] The character pixel coordinates may be the position coordinates of the content characters used to represent the payment activity in the text recognition result in the payment screenshot to be recognized. Specifically, during the text recognition process, the pixel point coordinate set of the characters included in the payment screenshot image to be recognized may be obtained to obtain the pixel point coordinate set corresponding to each character, that is, the position coordinate set of each content character in the payment screenshot to be recognized.

[0053] For example, Figure 2The payment screenshot a shown in the figure may include the characters: current status: payment successful, payment time: August 26, 2024 19:49:01, transaction number: 420000239120240826300353710 and merchant number: 7895152439145867. Then, according to the pixel point coordinate set corresponding to each character obtained in the text recognition, it can be determined whether the coordinate value of the topmost pixel point of each character is within the preset threshold range, such as less than 10 pixels, it can be determined that the horizontal pixel range threshold is met; it can also be determined according to whether the pixel point coordinate value at the leftmost end of each character is within the preset threshold range, such as less than 5 pixels, it can be determined that the vertical pixel range threshold is met. In this regard, the horizontal pixel range threshold and the vertical pixel range threshold can be set by the technician according to actual experience, or automatically set according to the character tilt check rule, and this embodiment does not make specific restrictions.

[0054] S140. If the second image judgment result is that the payment screenshot image to be identified is a normal screenshot image, and the payment screenshot image to be identified meets the preset image type judgment condition, then based on the preset keywords to be identified, extract the keyword area image in the payment screenshot image to be identified.

[0055] The image type determination condition may be used to determine the payment method screenshot type corresponding to the payment screenshot image to be identified based on the position information and character information of the content characters representing the payment activity in the text recognition result, such as Figure 2 As shown, payment screenshot a and payment screenshot b belong to screenshot image types under different payment methods.

[0056] Furthermore, the payment methods that meet the image type judgment condition can be set as method A and method B. If the payment method to which the payment screenshot image to be identified belongs is method A or method B, it is determined that the payment screenshot image to be identified meets the preset image type judgment condition.

[0057] The keywords to be identified may be text content used to represent payment activity information, and may specifically include text content such as payment amount, current status, payment time, transaction number, order number, merchant number, and merchant order number. For example, if a keyword area image can be extracted from payment screenshot a, then a keyword area image containing transaction amount, current status, payment time, transaction number, and merchant number can be extracted.

[0058] S150: Perform character recognition on the keyword region image, and detect whether the recognized characters meet a preset character alignment judgment condition.

[0059] Specifically, the keyword content to be identified in the keyword area image can be identified, such as character information such as transaction number: 420000239120240826300353710 and merchant number: 7895152439145867. Further, it can be determined whether each character information meets the character alignment judgment condition according to the pixel coordinate information corresponding to each character information.

[0060] S160: If yes, determine that the payment screenshot image to be identified is a normal payment screenshot image.

[0061] Optionally, before determining that the payment screenshot image to be identified is a normal payment screenshot image, it also includes: extracting key characters from the payment screenshot image to be identified to obtain at least one reference keyword and keyword coordinates of each reference keyword; if there are reference keywords belonging to the same keyword type, determining the keyword quantity of the reference keywords belonging to the same keyword type; if the keyword quantity meets the preset keyword quantity threshold judgment condition, determining the pixel distance between any two reference keywords for the keyword coordinates of any two reference keywords; judging whether the payment screenshot image to be identified is a normal screenshot image based on the pixel distance between any two reference keywords; if so, determining that the payment screenshot image to be identified is a normal payment screenshot image.

[0062] Among them, the reference keywords can be text content representing payment activity information in the payment screenshot to be identified, such as payment time, transfer time, transaction time or payment time, etc., all of which can be the same type of keywords used to represent the completion time of the payment activity represented in the payment screenshot to be identified; such as order number, transaction number, consumption number, transfer number, consumption number, etc., all of which can be the same type of keywords used to represent the number of the payment activity represented in the payment screenshot to be identified.

[0063] Specifically, the keyword quantity threshold judgment condition may be to determine whether there is one and only one keyword of the same type representing the payment activity information in the payment screenshot to be identified. For example, if only reference keywords such as payment time and order number, or transfer time and order number are identified, then it can be determined that the number of keywords meets the preset keyword quantity threshold judgment condition; if reference keywords such as payment time, transaction time and order number, or transfer time, transfer order number and order number are identified, then it can be determined that the number of keywords does not meet the preset keyword quantity threshold judgment condition.

[0064] The pixel distance may be the distance between the bottom pixel coordinates and the top pixel coordinates of any two different reference keywords that are preset, and may be preset by a technician based on experience. Figure 2 The payment time and transaction number in the payment screenshot a shown in , and the calculated pixel distance between the payment time and the transaction number can be 20 pixels. The pixel distance preset for the corresponding reference keyword under the payment method is also 20 pixels, so it can be determined that the payment screenshot a is a normal payment screenshot.

[0065] Optionally, before determining that the payment screenshot image to be identified is a normal payment screenshot image, it also includes: performing preset field extraction on the payment screenshot image to be identified to obtain a target field corresponding to the preset field and a target field value corresponding to the target field; judging whether the target field and the target field value meet the judgment condition of the same data row according to the character coordinates of the target field and the character coordinates of the target field value; if so, determining that the payment screenshot image to be identified is a normal payment screenshot image.

[0066] Among them, the preset fields can be text content representing payment activities, such as payment time, transfer time, transaction time, payment time, order number, transaction order number, consumption order number, transfer order number and consumption order number, etc., which can be pre-set by technical personnel.

[0067] Among them, the target field can be the text content representing the payment activity identified from the payment screenshot to be identified. The target field value can be used to represent the data content related to the payment activity. For example, the target fields and target field values ​​such as payment time: 2024-08-16 20:18:56, merchant order number: 17238107305722402451000 can be identified, and it can be determined that the target field and the target field value meet the data mapping condition; it can also be identified that the target fields and the target field values ​​such as payment time: 17238107305722402451000, merchant order number: 2024-08-16 20:18:56 can be identified, and it can be determined that the target field and the target field value do not meet the data mapping condition.

[0068] Continuing with the above example, if the payment time is the target field, the target field value is: 2024-08-16 20:18:56. When the target field and the target field value are identified as belonging to the same data row, the character coordinates of each character in the target field and the character coordinates of the target field value are obtained. If the character coordinates of each character in the target field and the character coordinates of its corresponding target field value are within the preset coordinate range, it can be determined that the target field and the field of its corresponding target field value belong to the same data row and meet the judgment condition of the same data row; if the character coordinates of each character in the target field and the character coordinates of its corresponding target field value are not within the preset coordinate range, it can be determined that the target field and the field of its corresponding target field value do not belong to the same data row and do not meet the judgment condition of the same data row.

[0069] Optionally, before determining that the payment screenshot image to be identified is a normal payment screenshot image, it also includes: extracting key fields from the payment screenshot image to be identified, and if there are an order number field and a payment date field in the payment screenshot image to be identified, extracting the order number from the order number field to obtain the order number date; comparing the order number date and the payment date field for consistency, if they are consistent, determining that the payment screenshot image to be identified is a normal payment screenshot image.

[0070] For example, if the extracted target field and target field value can be: payment time: 2024-08-16 20:18:56, order number: 2024081622001451181414320900 and other fields, then the order number date can be determined as "20240816" based on the order number, which is consistent with the payment date field "2024-08-16", thereby determining that the payment screenshot is a normal payment screenshot.

[0071] In an optional scheme of the present embodiment, it can be combined with one or more optional schemes of the present embodiment. Before determining that the payment screenshot image to be identified is a normal payment screenshot image, it also includes: performing barcode image recognition on the payment screenshot image to be identified, if there is a barcode image, then performing barcode parsing on the barcode image to obtain the barcode date; identifying the digital date in the barcode image adjacent area in the payment screenshot image to be identified, if there is a digital date, then comparing the barcode date with the digital date for consistency; if they are consistent, determining that the payment screenshot image to be identified is a normal payment screenshot image.

[0072] The barcode image may be a symbol image that is generated after the payment activity is completed and records the payment completion time, and the digital date may be the date when the barcode image is generated.

[0073] Specifically, the barcode analysis of the barcode image may be to analyze and obtain the barcode date recorded in the barcode image, and compare the consistency with the digital date.

[0074] Furthermore, the barcode date recorded in the barcode image may be compared with the payment time for consistency. If they are consistent, the payment screenshot image to be identified is determined to be a normal payment screenshot image.

[0075] The technical solution of the embodiment of the present invention determines the image information of the payment screenshot image to be identified and obtains the first image judgment result; if the first image judgment result is a normal screenshot image, text recognition is performed on the image content of the payment screenshot image to be identified and a second image judgment result is obtained; if the second image judgment result is a normal screenshot image and the payment screenshot image to be identified meets the preset image type judgment condition, the keyword area image in the payment screenshot image to be identified is extracted; character recognition is performed on the keyword area image, and when the preset character alignment judgment condition is met between the detected characters, the payment screenshot image to be identified is determined to be a normal payment screenshot image. This technical solution can accurately identify and verify the authenticity of the payment screenshot to be identified by identifying the image information and image content of the payment screenshot to be identified, thereby ensuring the security and reliability of the payment transaction.

[0076] Embodiment 2

[0077] Figure 3 This is a flow chart of a payment screenshot recognition method provided in Embodiment 2 of the present invention. This embodiment is optimized based on the above embodiment.

[0078] Furthermore, the step of "performing character recognition on the keyword area image, and detecting whether the recognized characters satisfy the preset character alignment judgment conditions" is optimized by adding the step of "determining the horizontal character projection of each character in the keyword area image on the horizontal area, and the vertical character projection on the vertical area; based on the horizontal area projection of each character in the keyword area image, removing special characters from each character, and detecting whether each character satisfies the preset character horizontal alignment judgment conditions based on the horizontal area projection of each removed character; if so, detecting whether each character satisfies the preset character vertical alignment judgment conditions based on the vertical area projection of each character in the keyword area image." to improve the method of judging whether each character is aligned. Figure 3 As shown, the method includes:

[0079] S210: Determine the payment screenshot image to be recognized according to the acquired image recognition request.

[0080] S220. Determine the image width, image height, and image grayscale information of the payment screenshot image to be identified, and determine whether the payment screenshot image to be identified is a normal screenshot image based on the image width, image height, and image grayscale information, to obtain a first image determination result.

[0081] S230. If the first image judgment result is that the payment screenshot image to be identified is a normal screenshot image, text recognition is performed on the payment screenshot image to be identified, and based on the text recognition result, it is determined whether the payment screenshot image to be identified is a normal screenshot image to obtain a second image judgment result.

[0082] S240. If the second image judgment result is that the payment screenshot image to be identified is a normal screenshot image, and the payment screenshot image to be identified meets the preset image type judgment condition, then based on the preset keywords to be identified, extract the keyword area image in the payment screenshot image to be identified.

[0083] S250: Determine a horizontal character projection of each character in the keyword region image on the horizontal region and a vertical character projection on the vertical region.

[0084] Among them, the horizontal character projection can be to calculate the sum of pixels of each character in the horizontal direction to determine the distribution of each character in the horizontal area; the vertical character projection can be to calculate the sum of pixels of each character in the vertical direction to determine the distribution of each character in the vertical area.

[0085] Specifically, the sum of pixels of each character in each keyword region image in the horizontal region and the vertical region may be calculated according to the result of text recognition.

[0086] S260, based on the horizontal area projection of each character in the keyword area image, special characters in each character are eliminated, and based on the horizontal area projection of each eliminated character, whether the characters meet the preset character horizontal direction alignment judgment condition is detected.

[0087] Among them, the special characters may be characters that have an impact on the calculation of the sum of pixels on the horizontal projection area of ​​the characters, and may specifically include characters such as “-”, “,”, “.”, etc.

[0088] Specifically, after removing the special characters, the sum of the pixels of the remaining characters in the horizontal projection area can be calculated, and the average value of the character spacing in the horizontal projection area can be obtained according to the sum of the pixels. The specific method for calculating the average value of the character spacing can be as follows:

[0089] Space1 = sum(X1,X2,..X n ) / n.

[0090] Among them, Space1 can be used to represent the average value of character spacing; X1, X2, .. X n It can be used to represent the character spacing value corresponding to each character in the horizontal projection area; n can be used to represent the number of characters in the horizontal projection area.

[0091] Specifically, it is possible to determine whether the characters meet the horizontal alignment condition based on the calculated average value of the character spacing and the maximum and minimum values ​​of the character spacing. For example, it is possible to determine whether the range of the absolute difference between the maximum and minimum values ​​of the character spacing and the calculated average value of the character spacing is less than 10%, that is, |maximum or minimum value - average value| / average value < 10%, to determine whether the characters are aligned in the horizontal direction.

[0092] S270: If yes, then detect whether the characters meet a preset character vertical alignment judgment condition based on the vertical area projection of each character in the keyword area image.

[0093] Specifically, the sum of the pixels of each character in the vertical area in the keyword area image may be used to determine whether each character satisfies the judgment condition of being aligned in the vertical direction.

[0094] Optionally, based on the vertical area projection of each character in the keyword area image, it is detected whether each character satisfies a preset character vertical alignment judgment condition, including: determining the spacing distance between each character based on the vertical area projection of each character in the keyword area image; determining the maximum distance and the minimum distance among each spacing distance, and determining the distance mean of each spacing distance; based on the maximum distance, the minimum distance and the distance mean, detecting whether each character satisfies a preset character vertical alignment judgment condition.

[0095] Specifically, the spacing distances between the characters can be obtained based on the pixel values ​​of the characters in the vertical projection area in the acquired keyword area image, and the maximum and minimum values ​​of the spacing distances between the characters can also be determined.

[0096] Furthermore, the average of the character spacing distances can be determined according to the obtained spacing distances between the characters. The specific calculation method of the average of the character spacing distances can be as follows:

[0097] Space2 = sum(Y1,Y2,..Y m ) / m.

[0098] Among them, Space2 can be used to represent the mean distance between characters; Y1, Y2, .. Y m It can be the spacing distance between each character on the vertical projection area; and m can be the number of characters on the vertical projection area.

[0099] It should be noted that the calculation method of the average character spacing and the mean character spacing distance can be obtained by technicians based on the collected sample data and statistics of the character spacing rules under the same situation. This embodiment does not impose specific restrictions on this.

[0100] Specifically, it is possible to detect whether the preset character vertical alignment judgment conditions are met between the characters based on the calculated mean value of the spacing distance and the relationship between the maximum and minimum values ​​of the spacing distances of the characters. For example, it is possible to determine whether the difference between the maximum value and the minimum value is greater than a first threshold value; it is also possible to determine whether the difference between the maximum value and the mean value is greater than a second threshold value; and it is also possible to determine whether the difference between the mean value and the minimum value is greater than a third threshold value, so as to determine whether the spacing distance values ​​of the characters are within a normal range in the vertically projected area, wherein the first threshold value, the second threshold value and the third threshold value can be set by the technician based on experience.

[0101] Optionally, the spacing distance between each character is determined based on the vertical area projection of each character in the keyword area image, including: obtaining the sample spacing mean in the screenshot recognition scenario to which the keyword area image belongs; if there is a first character among the characters in the keyword area image that meets a preset spacing reduction condition, then based on a preset spacing reduction rule, the spacing distance between each first character is updated according to the spacing distance between the first characters and the sample spacing mean; and if there is a second character among the characters in the keyword area image that meets a preset spacing increase condition, then based on a preset spacing increase rule, the spacing distance between each second character is updated according to the spacing distance between the second characters and the sample spacing mean.

[0102] The first character may be a character that directly affects the spacing distance of the characters in the keyword area in the vertical area, such as "1" or "11". The distance length of the "average of sample spacing" may be reduced by the left and right spacing distances of the character "1", and then the normal spacing distance may be used for processing.

[0103] Among them, the second character can be a character group that affects the spacing distance of the vertical area projection. For example, it can be the character "7" and there are small data and the character "," behind it. In this case, the left and right spacing distances of "7" can be increased by the distance length of the "sample spacing mean" and then processed according to the normal spacing distance.

[0104] Furthermore, if there is no character "1" in the keyword area, or there is no small data and character "," after the character "7", the characters in the keyword area can be directly projected in the vertical area according to the normal spacing distance.

[0105] S280: If yes, determine that the payment screenshot image to be identified is a normal payment screenshot image.

[0106] The technical solution of the embodiment of the present invention determines the image information of the payment screenshot image to be identified and obtains the first image judgment result; if the first image judgment result is a normal screenshot image, the image content of the payment screenshot image to be identified is subjected to text recognition, and a second image judgment result is obtained; if the second image judgment result is a normal screenshot image, and the payment screenshot image to be identified meets the preset image type judgment condition, the keyword area image in the payment screenshot image to be identified is extracted. Further, the horizontal character projection of each character in the keyword area image on the horizontal area and the vertical character projection on the vertical area are determined, and it is determined whether the identified characters meet the preset character alignment condition, so as to realize the authenticity verification of the payment screenshot image. The technical solution can identify the image information and image content of the payment screenshot to be identified, specifically, it can judge whether the characters in the screenshot image to be identified are aligned, and use this to perform image forgery detection, and can accurately identify and verify the authenticity of the payment screenshot, thereby ensuring the security and reliability of the payment transaction.

[0107] Embodiment 3

[0108] Figure 4 This is a schematic diagram of the structure of a payment screenshot recognition device provided by Embodiment 3 of the present invention. Figure 4 As shown, the device comprises:

[0109] The payment screenshot to be identified determining module 310 is used to determine the payment screenshot image to be identified according to the acquired image recognition request.

[0110] The first judgment module 320 is used to determine the image width, image height and image grayscale information of the payment screenshot image to be identified, and judge whether the payment screenshot image to be identified is a normal screenshot image based on the image width, image height and image grayscale information to obtain a first image judgment result.

[0111] The second judgment module 330 is used to perform text recognition on the payment screenshot image to be identified if the first image judgment result is that the payment screenshot image to be identified is a normal screenshot image, and judge whether the payment screenshot image to be identified is a normal screenshot image based on the text recognition result to obtain a second image judgment result.

[0112] The keyword area image extraction module 340 is used to extract the keyword area image in the payment screenshot image to be identified based on the preset keywords to be identified if the second image judgment result is that the payment screenshot image to be identified is a normal screenshot image and the payment screenshot image to be identified meets the preset image type judgment conditions.

[0113] The character recognition module 350 is used to perform character recognition on the keyword region image and detect whether the recognized characters meet a preset character alignment judgment condition.

[0114] The normal payment screenshot determination module 360 ​​is used to determine that the payment screenshot image to be identified is a normal payment screenshot image if the detected and recognized characters meet a preset character alignment judgment condition.

[0115] Optionally, the second determination module 330 is specifically configured to:

[0116] Perform text recognition on the payment screenshot image to be identified to obtain the number of characters and character pixel coordinates of the characters contained in the payment screenshot image to be identified; if the number of characters meets the preset character number threshold judgment condition, judge whether the corresponding character is an inclined character based on the character pixel coordinates, based on the horizontal pixel range threshold and the vertical pixel range threshold, and obtain the character inclination judgment result; determine the second image judgment result based on the character request judgment result.

[0117] Optionally, the normal payment screenshot determination module 360 ​​is specifically used to:

[0118] Perform key character extraction on the payment screenshot image to be identified to obtain at least one reference keyword and keyword coordinates of each reference keyword; if there are reference keywords belonging to the same keyword type, determine the keyword quantity of the reference keywords belonging to the same keyword type; if the keyword quantity meets the preset keyword quantity threshold judgment condition, determine the pixel distance between any two reference keywords for the keyword coordinates of any two reference keywords; based on the pixel distance between any two reference keywords, determine whether the payment screenshot image to be identified is a normal screenshot image; if so, determine that the payment screenshot image to be identified is a normal payment screenshot image.

[0119] Optionally, the normal payment screenshot determination module 360 ​​is further used to:

[0120] Perform preset field extraction on the payment screenshot image to be identified to obtain a target field corresponding to the preset field and a target field value corresponding to the target field; determine whether the target field and the target field value meet the judgment condition of the same data row based on the character coordinates of the target field and the character coordinates of the target field value; if so, determine that the payment screenshot image to be identified is a normal payment screenshot image.

[0121] Optionally, the normal payment screenshot determination module 360 ​​is further configured to:

[0122] Key fields are extracted from the payment screenshot image to be identified. If an order number field and a payment date field exist in the payment screenshot image to be identified, order number extraction is performed on the order number field to obtain the order number date; the order number date and the payment date field are compared for consistency. If they are consistent, it is determined that the payment screenshot image to be identified is a normal payment screenshot image.

[0123] Optionally, the normal payment screenshot determination module 360 ​​is further configured to:

[0124] Perform barcode image recognition on the payment screenshot image to be identified. If a barcode image exists, perform barcode parsing on the barcode image to obtain a barcode date. Identify the digital date in the area adjacent to the barcode image in the payment screenshot image to be identified. If a digital date exists, compare the barcode date with the digital date for consistency. If they are consistent, determine that the payment screenshot image to be identified is a normal payment screenshot image.

[0125] Optionally, the character recognition module 350 includes a character projection unit.

[0126] Optionally, a character projection unit is used to determine a horizontal character projection of each character in the keyword area image on a horizontal area, and a vertical character projection on a vertical area.

[0127] Optionally, the character projection unit includes a horizontal area projection subunit and a vertical area projection subunit.

[0128] Optionally, a horizontal area projection subunit is used to remove special characters from each character according to the horizontal area projection of each character in the keyword area image, and detect whether the characters meet the preset character horizontal alignment judgment conditions according to the horizontal area projection of each removed character.

[0129] Optionally, a vertical area projection subunit is used to detect whether the preset character horizontal alignment judgment conditions are met between the characters based on the vertical area projection of each character in the keyword area image when detecting whether the preset character horizontal alignment judgment conditions are met between the characters.

[0130] Optionally, a vertical area projection subunit is used to:

[0131] Determine the spacing distance between each character based on the vertical area projection of each character in the keyword area image; determine the maximum distance and the minimum distance among each spacing distance, and determine the distance mean of each spacing distance; based on the maximum distance, the minimum distance and the distance mean, detect whether the characters meet the preset character vertical alignment judgment condition.

[0132] Optionally, the vertical area projection subunit is further used for:

[0133] Obtain the sample interval mean in the screenshot recognition scenario to which the keyword area image belongs; if there is a first character among the characters in the keyword area image that meets the preset interval reduction condition, then update the interval distance between the first characters based on the preset interval reduction rule according to the interval distance between the first characters and the sample interval mean; and if there is a second character among the characters in the keyword area image that meets the preset interval increase condition, then update the interval distance between the second characters based on the preset interval increase rule according to the interval distance between the second characters and the sample interval mean.

[0134] The payment screenshot recognition device provided in the embodiment of the present invention can execute the payment screenshot recognition method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0135] Embodiment 4

[0136] Figure 5 A schematic diagram of an electronic device 40 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0137] like Figure 5As shown, the electronic device 40 includes at least one processor 41, and a memory connected to the at least one processor 41, such as a read-only memory (ROM) 42, a random access memory (RAM) 43, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 41 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 42 or the computer program loaded from the storage unit 48 to the random access memory (RAM) 43. In the RAM 43, various programs and data required for the operation of the electronic device 40 can also be stored. The processor 41, the ROM 42, and the RAM 43 are connected to each other through a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0138] A number of components in the electronic device 40 are connected to the I / O interface 45, including: an input unit 46, such as a keyboard, a mouse, etc.; an output unit 47, such as various types of displays, speakers, etc.; a storage unit 48, such as a disk, an optical disk, etc.; and a communication unit 49, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 49 allows the electronic device 40 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0139] The processor 41 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 41 executes the various methods and processes described above, such as the payment screenshot recognition method.

[0140] In some embodiments, the payment screenshot recognition method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 48. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 40 via the ROM 42 and / or the communication unit 49. When the computer program is loaded into the RAM 43 and executed by the processor 41, one or more steps of the payment screenshot recognition method described above may be performed. Alternatively, in other embodiments, the processor 41 may be configured to execute the payment screenshot recognition method in any other appropriate manner (e.g., by means of firmware).

[0141] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0142] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0143] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0144] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0145] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0146] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0147] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0148] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A payment screenshot recognition method, characterized in that: include: Determine the payment screenshot image to be identified according to the obtained image recognition request; Determine the image width, image height and image grayscale information of the payment screenshot image to be identified, and judge whether the payment screenshot image to be identified is a normal screenshot image according to the image width, image height and image grayscale information, to obtain a first image judgment result; If the first image judgment result is that the payment screenshot image to be identified is a normal screenshot image, text recognition is performed on the payment screenshot image to be identified, and based on the text recognition result, it is determined whether the payment screenshot image to be identified is a normal screenshot image to obtain a second image judgment result; If the second image judgment result is that the payment screenshot image to be identified is a normal screenshot image, and the payment screenshot image to be identified meets the preset image type judgment condition, then based on the preset keywords to be identified, extracting a keyword area image in the payment screenshot image to be identified; Performing character recognition on the keyword region image, and detecting whether the recognized characters meet a preset character alignment judgment condition; If so, it is determined that the payment screenshot image to be identified is a normal payment screenshot image.

2. The method according to claim 1, characterized in that: The performing text recognition on the payment screenshot image to be recognized, and judging whether the payment screenshot image to be recognized is a normal screenshot image according to the text recognition result, to obtain a second image judgment result, includes: Performing text recognition on the payment screenshot image to be recognized to obtain the number of characters and character pixel coordinates of the characters contained in the payment screenshot image to be recognized; If the number of characters meets the preset character number threshold judgment condition, then judging whether the corresponding character is an inclined character based on the character pixel coordinates, the horizontal pixel range threshold and the vertical pixel range threshold, and obtaining a character inclination judgment result; A second image judgment result is determined according to the character tilt judgment result.

3. The method according to claim 1, characterized in that Before determining that the payment screenshot image to be identified is a normal payment screenshot image, the method further includes: Extract key characters from the payment screenshot image to be identified to obtain at least one reference keyword and keyword coordinates of each reference keyword; If there are reference keywords belonging to the same keyword type, determining the keyword quantity of the reference keywords belonging to the same keyword type; If the number of keywords meets the preset keyword number threshold judgment condition, then for the keyword coordinates of any two reference keywords, determine the pixel distance between any two reference keywords; According to the pixel distance between any two reference keywords, determining whether the payment screenshot image to be identified is a normal screenshot image; If so, it is determined that the payment screenshot image to be identified is a normal payment screenshot image.

4. The method according to claim 1, characterized in that: Before determining that the payment screenshot image to be identified is a normal payment screenshot image, the method further includes: Extracting a preset field from the payment screenshot image to be identified to obtain a target field corresponding to the preset field and a target field value corresponding to the target field; According to the character coordinates of the target field and the character coordinates of the target field value, judging whether the target field and the target field value satisfy a judgment condition of the same data row; If so, it is determined that the payment screenshot image to be identified is a normal payment screenshot image.

5. The method according to claim 1, characterized in that Before determining that the payment screenshot image to be identified is a normal payment screenshot image, the method further includes: Extract key fields from the payment screenshot image to be identified. If the payment screenshot image to be identified contains an order number field and a payment date field, extract the order number from the order number field to obtain the order number date. The order number date and the payment date fields are compared for consistency. If they are consistent, it is determined that the payment screenshot image to be identified is a normal payment screenshot image.

6. The method according to claim 5, characterized in that Before determining that the payment screenshot image to be identified is a normal payment screenshot image, the method further includes: Performing barcode image recognition on the payment screenshot image to be recognized, and if a barcode image exists, performing barcode analysis on the barcode image to obtain a barcode date; Identify the digital date in the vicinity of the barcode image in the payment screenshot image to be identified, and if a digital date exists, compare the barcode date with the digital date for consistency; If they are consistent, it is determined that the payment screenshot image to be identified is a normal payment screenshot image.

7. The method according to claim 1, characterized in that The performing character recognition on the keyword region image and detecting whether the recognized characters meet a preset character alignment judgment condition includes: Determine a horizontal character projection of each character in the keyword region image on a horizontal region, and a vertical character projection on a vertical region; According to the horizontal area projection of each character in the keyword area image, special characters in each character are eliminated, and according to the horizontal area projection of each eliminated character, whether the characters meet the preset character horizontal direction alignment judgment condition; If so, then based on the vertical area projection of each character in the keyword area image, it is detected whether each character satisfies a preset character vertical alignment judgment condition.

8. The method according to claim 7, characterized in that The step of detecting whether the characters meet a preset character vertical alignment judgment condition based on the vertical area projection of each character in the keyword area image includes: Determining the spacing between the characters according to the vertical area projection of the characters in the keyword area image; Determine the maximum distance and the minimum distance among the interval distances, and determine the distance mean of the interval distances; According to the maximum distance, the minimum distance and the distance mean, it is detected whether the characters meet the preset character vertical alignment judgment condition.

9. The method according to claim 8, characterized in that The step of determining the spacing between the characters according to the vertical area projection of the characters in the keyword area image comprises: Obtaining a sample interval mean value in a screenshot recognition scenario to which the keyword region image belongs; If there is a first character satisfying a preset spacing reduction condition among the characters in the keyword region image, updating the spacing distance between the first characters based on a preset spacing reduction rule according to the spacing distance between the first characters and the sample spacing mean; and If there is a second character satisfying a preset spacing increase condition among the characters in the keyword area image, the spacing distance between the second characters is updated based on a preset spacing increase rule according to the spacing distance between the second characters and the sample spacing mean.

10. A payment screenshot recognition device, characterized in that: include: A payment screenshot to be identified determining module, used to determine the payment screenshot image to be identified according to the acquired image recognition request; A first judgment module is used to determine the image width, image height and image grayscale information of the payment screenshot image to be identified, and judge whether the payment screenshot image to be identified is a normal screenshot image according to the image width, image height and image grayscale information, to obtain a first image judgment result; A second judgment module is used for, if the first image judgment result is that the payment screenshot image to be identified is a normal screenshot image, performing text recognition on the payment screenshot image to be identified, and judging whether the payment screenshot image to be identified is a normal screenshot image according to the text recognition result, to obtain a second image judgment result; A keyword area image extraction module, configured to extract a keyword area image in the payment screenshot image to be identified based on a preset keyword to be identified, if the second image judgment result is that the payment screenshot image to be identified is a normal screenshot image and the payment screenshot image to be identified meets a preset image type judgment condition; A character recognition module, used to perform character recognition on the keyword area image and detect whether the recognized characters meet a preset character alignment judgment condition; The normal payment screenshot determination module is used to determine that the payment screenshot image to be identified is a normal payment screenshot image if the detected and recognized characters meet a preset character alignment judgment condition.

11. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the payment screenshot recognition method described in any one of claims 1-9.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the payment screenshot recognition method described in any one of claims 1-9 when executed.

13. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, implements the payment screenshot recognition method according to any one of claims 1-9.

Images