Certificate machine readable code correction method and storage medium

Abstract

The application provides a certificate machine code correction method and a storage medium. The method comprises the following steps: cutting the machine code according to the certificate specification to obtain a plurality of identification objects; if one identification object has one missing character, the 731 weighting method is used to calculate and obtain the missing character according to the successfully recognized known character; if one identification object has two missing characters, the weight position and the at least two possible characters corresponding to each missing character are determined according to the identification result, wherein if the missing character is a check bit, the weight position corresponding to the missing character is set as a check bit identification value; and the 731 weighting method is used to determine each missing character according to the successfully recognized known character, the weight position and the at least two possible characters. The application can accurately and efficiently correct the missing characters when the complete machine code cannot be read.

Description

Technical Field

[0001] This application relates to the field of machine-readable documents, specifically to methods for correcting machine-readable codes on documents and storage media. Background Technology

[0002] Currently, various banks, airports, insurance companies, and other institutions in China all have a need to read machine-readable travel documents when processing business. For example, when processing check-in, airports need to read machine-readable travel documents, first reading the card number, date of birth, and expiration date, and then reading other text and photo information according to relevant regulations.

[0003] The most common method for reading machine-readable travel documents in current technology is to first obtain the entire image using optical scanning or photography, and then use recognition technology to identify the text and character information in the image. Three key elements are extracted from the machine-readable code area as the data source for decryption calculations, and then interact with the chip in the document to read the complete text information and portrait data.

[0004] However, if the document is damaged, such as when some information is blurred, the existing recognition technology will be unable to successfully identify the complete information, let alone restore the damaged or missing characters. This necessitates manual judgment by the teller or the use of other documents for verification. Consequently, processing times are long and inefficient, resulting in a poor customer experience.

[0005] When the accuracy of existing machine-readable travel document recognition technology cannot meet the needs of actual use and does not support the recognition of damaged payments, there is a need to provide a technical solution that can correct errors in machine-readable travel document information. Summary of the Invention

[0006] In view of the above problems, this application provides a method and storage medium for correcting machine-readable codes on documents, which can perform efficient and accurate correction of machine-readable codes when the complete machine-readable code cannot be read.

[0007] To achieve the above objectives, the inventors provide a method for correcting machine-readable codes on identification documents, comprising:

[0008] The machine-readable code is segmented according to the document specifications to obtain multiple identification objects;

[0009] If a recognition object has a missing character, the missing character is calculated using the 731 weighted method based on the successfully recognized known characters.

[0010] If an object to be identified has two missing characters, the weight corresponding to each missing character and at least two possible characters are determined based on the identification result. If the missing character is a check bit, its corresponding weight is set as the check bit identifier value. Based on the successfully identified known characters, the weights, and the at least two possible characters, the 731 weighted method is used to determine each missing character.

[0011] Unlike existing technologies, the above technical solution breaks down machine-readable codes into valid character segments, then uses each segment as a separate recognition object. Based on the number of missing characters, if there is only one missing character, the 731 weighted method is used directly to calculate the missing character; if there are two, the recognition result is combined with the 731 weighted method to confirm the missing character. This technical solution enables accurate calculation of missing characters during the reading of machine-readable tourist documents, correcting errors in the machine-readable code and effectively improving the success rate of recognizing missing characters, thereby increasing the work efficiency of staff.

[0012] In some embodiments, preferably, determining the weight position corresponding to each missing character and at least two corresponding possible characters based on the recognition result includes:

[0013] Based on the recognition results, a list of missing characters is established, wherein the list of missing characters includes the position of the missing character in the recognition object, its corresponding weight, and at least two possible characters.

[0014] Preferably, after establishing the list of missing characters, the method further includes:

[0015] Based on the successfully identified known characters and the list of missing characters, a character query configuration table is constructed, wherein the character query configuration table includes the known characters, the weight of each missing character and its corresponding possible character.

[0016] Preferably, the step of determining each missing character using a 731 weighted method based on the successfully identified known character, the weight position, and the at least two possible characters includes:

[0017] The validity of each column of the character query configuration table is verified using the 731 weighted method to identify each missing character.

[0018] Preferably, after establishing the list of missing characters, the method further includes:

[0019] Based on the successfully identified known characters, the possible characters corresponding to a missing character, and the weight of another missing character, a character query configuration table is constructed; wherein, the fields of the character query configuration table include known characters, the weight of the missing character and its corresponding possible character, and the weight of the other missing character.

[0020] Preferably, the missing character is a missing character that corresponds to a relatively small number of possible characters in the missing character list, or

[0021] The missing character can be any missing character.

[0022] Preferably, the step of determining each missing character using a 731 weighted method based on the successfully identified known character, the weight position, and the at least two possible characters includes:

[0023] Based on the character query configuration table, the character corresponding to the weight position of the other missing character in each column of the character query configuration table is calculated using the 731 weighted method, and the missing character corresponding to the other missing character is determined by referring to the possible characters corresponding to the other missing character in the missing character list.

[0024] Preferably, after segmenting the machine-readable code according to the document specifications to obtain multiple identification objects, the process further includes:

[0025] Perform character recognition on each object separately;

[0026] If the results of three consecutive recognitions of an object are consistent, the recognition is considered successful.

[0027] If the results of three recognitions of an object are inconsistent, it is determined that there are missing characters, and the recognition count is incremented by 1; it is then checked whether there are duplicate results. If not, the recognition count is increased until duplicate results are found.

[0028] Preferably, the document is a tourist document.

[0029] In these embodiments, each missing character can be identified in a more efficient manner while ensuring recognition accuracy, thereby greatly improving the correction efficiency of machine-readable travel document information.

[0030] The inventor also provides another technical solution:

[0031] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method for correcting code readings of identification documents.

[0032] The above description of the invention is merely an overview of the technical solution of this application. In order to enable those skilled in the art to better understand the technical solution of this application and to implement it based on the description and drawings, and to make the above-mentioned objectives and other objectives, features and advantages of this application easier to understand, the following description is provided in conjunction with the specific embodiments and drawings of this application. Attached Figure Description

[0033] The accompanying drawings are only used to illustrate the principles, implementation methods, applications, features, and effects of specific embodiments of this application and other related content, and should not be considered as limitations on this application.

[0034] In the accompanying drawings of the instruction manual:

[0035] Figure 1 This is a flowchart illustrating a document reader code correction method as described in Embodiment 1;

[0036] Figure 2 This is a schematic diagram illustrating the correction process for the presence of two missing characters in Embodiment 2. Detailed Implementation

[0037] To illustrate the possible application scenarios, technical principles, implementable specific solutions, and achievable objectives and effects of this application in detail, the following description, in conjunction with the listed specific embodiments and accompanying drawings, provides a detailed explanation. The embodiments described herein are merely illustrative of the technical solutions of this application and are therefore intended to limit the scope of protection of this application.

[0038] In this document, the term "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The term "embodiment" appearing in various places throughout the specification does not necessarily refer to the same embodiment, nor does it specifically limit its independence or connection with other embodiments. In principle, in this application, as long as there are no technical contradictions or conflicts, the technical features mentioned in each embodiment can be combined in any way to form corresponding implementable technical solutions.

[0039] Unless otherwise defined, the technical terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the use of related terms herein is merely for the purpose of describing particular embodiments and is not intended to limit this application.

[0040] In the description of this application, the term "and / or" is used to describe the logical relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A exists, B exists, and A and B exist simultaneously. Additionally, the character " / " in this document generally indicates that the preceding and following objects have an "or" logical relationship.

[0041] In this application, terms such as “first” and “second” are used only to distinguish one entity or operation from another, and do not necessarily require or imply any actual quantity, hierarchy or order between these entities or operations.

[0042] Unless otherwise specified, the use of terms such as “comprising,” “including,” “having,” or other similar expressions in this application is intended to cover non-exclusive inclusion, which does not exclude the presence of additional elements in a process, method, or product that includes the stated elements, such that a process, method, or product that includes a list of elements may include not only those defined elements but also other elements not expressly listed, or elements inherent to such a process, method, or product.

[0043] In this application, expressions such as "greater than", "less than", and "exceeding" are understood to exclude the stated number; expressions such as "above", "below", and "within" are understood to include the stated number. Furthermore, in the description of the embodiments of this application, "multiple" means two or more (including two), and similar expressions related to "multiple" are also understood in this way, such as "multiple groups" and "multiple times", unless otherwise explicitly specified.

[0044] In the description of the embodiments of this application, the space-related expressions used, such as "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "vertical," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential," indicate the orientation or positional relationship based on the orientation or positional relationship shown in the specific embodiments or drawings. They are only for the purpose of describing the specific embodiments of this application or for the reader's understanding, and do not indicate or imply that the device or component referred to must have a specific position, a specific orientation, or be constructed or operated in a specific orientation. Therefore, they should not be construed as limitations on the embodiments of this application.

[0045] Unless otherwise expressly specified or limited, the terms "installation," "connection," "linking," "fixing," and "setting," as used in the description of the embodiments of this application, should be interpreted broadly. For example, "connection" can be a fixed connection, a detachable connection, or an integral setting; it can be a mechanical connection, an electrical connection, or a communication connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be the internal connection of two components or the interaction between two components. For those skilled in the art to which this application pertains, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0046] In existing technologies, during the machine-readable code reading process of travel documents, if missing characters are encountered, automatic completion is not supported; manual judgment is required. Even if a single missing character can be identified, the success rate is very low, causing inconvenience for staff, extending processing time, and resulting in a poor customer experience. Therefore, it is necessary to incorporate a correction method into the machine-readable code reading process to address these technical problems.

[0047] Please see Figure 1 , Figure 1 This diagram illustrates a flowchart of a document reader code correction method as described in Embodiment 1, specifically including:

[0048] S1: The machine-readable code is segmented according to the document specifications to obtain multiple identification objects;

[0049] It is known that the machine-readable codes of travel documents follow the ICAO 9303 standard, and the characters in the machine-readable codes are a subset of the OCR-B character set of [ISO 1073-2]. For example, the date of birth 03 / AUG / 1981 belongs to the second valid character segment in the passport machine-readable code according to the standard, which is 8108038, where the last character 8 is the check digit for this character segment.

[0050] Therefore, by segmenting the machine-readable code into its valid character segments according to document specifications, we can obtain the corresponding identification object for each valid character segment. That is, one valid character segment is defined as one identification object. Typically, the machine-readable code in a travel document contains more than two valid character segments, thus allowing for the extraction of more than two identification objects.

[0051] In some specific implementations, during the cutting process, the location of the machine-readable code can be accurately located based on the specific document. Then, by combining the character font size in the ICAO 9303 specification, the machine-readable code of the document can be efficiently and accurately extracted before cutting. Because the identification and extraction are performed directly on a specific area, the identification range can be narrowed, improving identification efficiency and accuracy.

[0052] S2: Perform multiple recognitions on each object one by one to obtain the recognition results for each object.

[0053] Since the characters in machine-readable codes are a subset of the OCR-B character set of [ISO 1073-2], a character library corresponding to this subset can be pre-built for character recognition. Specifically, the object to be recognized can be compared with the characters in the character library to obtain the recognition result.

[0054] In some specific implementations, the rules for performing multiple identifications on each identification object are as follows:

[0055] If the recognition results of an object are consistent in three consecutive recognitions, that is, all correct characters are successfully recognized in all three recognitions and all characters are consistent, then the recognition is considered successful; output the recognition result and end the process.

[0056] If the results of three recognitions of an object are inconsistent, it is determined that there is a missing character, and the recognition count is incremented by 1. It is then checked whether there are duplicate results (i.e., whether at least two of the four character segments obtained from four recognitions are duplicates). If not, the recognition count continues to increase until duplicate results are found. The recognition results, including the recognition results (i.e., the character segments recognized each time), the position of the missing character in the object, and the recognition count, are stored, and the process proceeds to step S3, the machine-readable code correction process. The stored content, i.e., the recognition results, provides a data source for the correction process.

[0057] In some specific implementations, for each missing character in the recognition result, a correlation is established between the number of missing characters and possible characters. For example, the recognition result for the object 8?07202 (where ? represents a missing character) includes 8707202, 8107202, and 8607202. The possible characters corresponding to the missing character ? are ( , 1, 6), and correspondingly, they will be recorded in the recognition result as (2) (7, 1, 6).

[0058] As can be seen in the above specific implementation, when the number of recognition attempts is greater than 3, the corresponding recognition object needs to undergo character correction. It is understood that the setting of the recognition attempt count of 3 can be flexibly adjusted according to actual needs.

[0059] Below is the correction process for an object that is confirmed to contain missing characters during the recognition process:

[0060] S3: Determine the number of missing characters in the current recognition object;

[0061] If the currently identified object has a missing character, then execute S4;

[0062] If the current object being identified has two missing characters, then execute S5;

[0063] If the currently identified object has two or more missing characters, it is recommended to reapply for the certificate and end the process.

[0064] S4: If the object being identified has a missing character, then the missing character is calculated using the 731 weighted method based on the successfully identified known characters.

[0065] According to the ICAO 9303 standard, the machine-readable code of a travel document consists of valid character segments arranged in a predetermined order. The last character in each valid character segment is the check digit, used to verify the validity of the corresponding character segment. For example, for the document information corresponding to the birth date August 3, 1981, the character segment written into the machine-readable code would be 8108038, where 81 corresponds to the year, 08 to the month, and 03 to the day. The 7th digit, 8, is the check digit calculated using a special 731 weighted method for the character segment 810803. Simply put, the check digit is calculated based on a modulus of 10, with the number of digits in the corresponding character segment repeatedly weighted by 731 731... Specifically, the 731 weighted method is calculated as follows: from left to right, the character segment is multiplied by the weighted number at the corresponding sequential position (i.e., number of digits) for each digit of the relevant digital data element; the products of each multiplication operation are added together; the sum is divided by 10 (modulus), and the remainder is the check digit. Here, the check digit of the character segment "810803" is used as an example for explanation, that is, (8*7+1*3+0*1+8*7+0*3+3*1)=118, 118mod(10)=8, that is, the check digit is 8.

[0066] Therefore, when there is only one missing character in the object to be identified, the missing character can be calculated by forward or backward calculation using the 731 weighted method.

[0067] The following is a detailed explanation of the process of calculating and obtaining missing characters through a specific example.

[0068] The valid character segment of an object to be identified is 8707202, with the last two digits being the check digit, calculated using (8*7+7*3+0*1+7*7+2*3+0*1)mod(10). Assuming that 870720 is identified, only 8?07202 can be obtained, where the ? represents a worn-out character that cannot be identified. Therefore, using the 731 weighted method for reverse calculation, we need (8*7+?*3+0*1+7*7+2*3+0*1)mod(10)=2, which gives us ? =7, meaning the missing character of the object to be identified is 7.

[0069] In some specific implementations, after calculating the missing character, the calculation result is further verified by the recognition result of the object being identified, in order to further improve the accuracy of the correction. For example, if the recognition result for the position corresponding to the object being identified includes the possible characters 7 and 1, and the calculated result 7 is among the possible characters of the ? in the recognition result, then the correction result 7 is correct.

[0070] It is evident that when the object being identified is missing only one character, the missing character can be efficiently and accurately calculated using the 731 weighted method based on the successfully identified known characters. Furthermore, even if the missing character is a check value, it can be efficiently filled in through forward calculation. Preferably, since the check bit is not needed in practical applications, if the check bit is missing, the calculation of the missing character can be omitted to ensure that the business operation proceeds smoothly to the next step. That is, preferably, step S3 further includes: if the current object being identified has a missing character, and the missing character is a check bit, then output the successfully identified character segment and end the process.

[0071] S5: If there are two missing characters in the object to be identified, the weight corresponding to each missing character and the corresponding at least two possible characters are determined according to the identification result. If the missing character is a check bit, its corresponding weight is set as the check bit identifier value. Then, based on the successfully identified known characters, the weight and the at least two possible characters, the 731 weighted method is used to determine each missing character.

[0072] Optionally, the check bit identifier value can be *, 0, or &, or any other value that can be used to identify its corresponding bit as a check bit without participating in the 731 weighted calculation.

[0073] Specifically, in step S2, the recognition results of the object have already been stored (including successfully recognized characters and the number of bits and possible characters corresponding to each missing character). Therefore, by adding the weight corresponding to each missing character, the 731 weighted method can be used to calculate each missing character.

[0074] The following example illustrates one of several feasible calculation methods: An object 8707202 is identified, with a missing value of 870?20?. After step S2, the number of bits (4), possible characters (7,5,1,4), and weight (7) corresponding to the first missing character are obtained; the number of bits (7), possible characters (2,3), and weight (*) corresponding to the second missing character are obtained. Here, the check bit identifier is pre-set to * to identify its corresponding check bit. Therefore, combining the successfully identified known character 870?20? recorded in the identification results, eight character segment combinations can be obtained: 8707202 / 8707203 / 8705202 / 8705203 / 8701202 / 8701203 / 870420 / 870423. The validity of these eight character segments can then be verified using the 731 weighted method to confirm the valid character segments and thus determine the missing character.

[0075] Please see Figure 2 , Figure 2 This is a schematic diagram illustrating the correction process for the presence of two missing characters in Embodiment 2.

[0076] Based on the first embodiment described above, the second embodiment of this application optimizes the confirmation method for the two missing characters to speed up the confirmation process and further improve the correction efficiency.

[0077] Specifically, in this embodiment, step S5, which involves determining the weight position corresponding to each missing character and at least two possible characters based on the recognition result, specifically includes:

[0078] S51: Based on the recognition results, establish a list of missing characters;

[0079] The missing character list includes the position of the missing character in the identified object, its corresponding weight, and at least two possible characters.

[0080] Here, the data source for establishing the list of missing characters is the recognition results obtained from multiple recognitions of the object in step S2. The recognition results include the recognition outcome (i.e., the character segment recognized each time), the position of the missing character within the object, and the number of recognitions. Preferably, the recognition results also include the position of the missing character and the relationships between possible characters.

[0081] As a specific example, one representation of the missing character list of the identification object 870?20? in the above embodiment is shown in Table 1 below:

[0082]

[0083] Table 1

[0084] It is foreseeable that by establishing a list of missing characters, the correspondence between the identified object and the information of each missing character can be made clearer and less prone to errors. Therefore, the efficiency and accuracy of subsequent calculations to confirm the missing characters can be improved.

[0085] In some specific implementations, after establishing the list of missing characters, the method further includes:

[0086] S52: Construct the character query configuration table;

[0087] S53: Based on the successfully identified known characters, the list of missing characters, and the character query configuration table, use the 731 weighted method to calculate and confirm each missing character.

[0088] The character query configuration table is constructed based on the successfully identified known characters and the list of missing characters. The character query configuration table includes the known characters, the weight of each missing character, and a corresponding possible character. The character query configuration table will help further improve the error correction efficiency.

[0089] As a specific example of a character query configuration table, the character query configuration table will list the possible characters corresponding to each missing character, that is, all combinations of two missing characters and their possible characters, and then determine the missing characters by verifying their validity one by one.

[0090] For example, the character query configuration table for the identified object 870?20? in the above embodiment is shown in Table 2 below:

[0091]

[0092] Table 2

[0093] The known sum is calculated as follows: 8*7+7*3+0*1+7*? +2*3+0*1= 83+7*?, which means the known sum is 83.

[0094] Therefore, corresponding to this specific example, the specific process of S53 above can be as follows: use the 731 weighted method to verify the validity of the data in each column of the character query configuration table to determine each missing character. In other words, based on the character query configuration table described in this specific example, it is only necessary to use the 731 weighted method to verify the validity of the data in each column to obtain the value of the missing character. As shown in Table 2, calculations show that the data in column 1 is valid; therefore, it can be concluded that the fourth missing character is 7, and the seventh missing character is 2.

[0095] As another specific example of a character query configuration table, the character query configuration table only selects and lists the possible characters corresponding to one of the missing characters, and then calculates the value of another missing character using the 731 weighted algorithm. Then, it determines whether the calculated value is valid based on the list of missing characters, thereby identifying each missing character.

[0096] For example, taking the identification object 870?20? as an example, the character lookup configuration table corresponding to this specific example is shown in Table 3 below:

[0097]

[0098] Table 3

[0099] In other words, the fields of the character query configuration table in this specific example include known and known characters, the weight of the missing character and its corresponding possible character, and the weight of the other missing character.

[0100] Therefore, corresponding to this specific example, the specific process of S53 above can be as follows:

[0101] Based on the character query configuration table, the 731 weighted method is used to calculate the character corresponding to the weight of the other missing character in each column of the character query configuration table. Then, referring to the records of possible characters corresponding to the other missing character in the missing character list, the valid missing character corresponding to the other missing character is determined. Simply put, after calculating the value of the other missing character, it is only necessary to check the missing character list to determine whether the value is a possible character corresponding to this missing character; if so, it is valid; otherwise, it is invalid.

[0102] Corresponding to Table 3 above, the process of determining each missing character can be as follows: Query the first column of the character query configuration table

[83] [7][7][*][?], calculate the value of [?] to be 2, query the missing character list, the missing character corresponds to missing character number 2, which contains the value 2, therefore, (7, 2) is one of the valid combinations of "missing characters"; or continue to calculate the second column of the character query configuration table

[83] [7][5][*][?], calculate the value to be 8, which is not in the possible character set corresponding to missing character number 2, therefore, (7, 8) is not a valid combination of "missing characters"; continue to calculate the third column of the character query configuration table

[83] [7][1][1][*], calculate the value to be 0, which is not in the possible character set corresponding to missing character number 2, therefore, (7, 0) is not a valid combination of "missing characters"; continue to calculate the fourth column of the character query configuration table

[83] [7][4][*][?], calculate the value to be 1. When "Unknown character 2" is 1, it is not in the possible character set corresponding to missing character number 2. Therefore, (7, 1) is not a valid combination of "missing characters". Thus, it can be concluded that the only valid combination of "missing characters" is (7, 2).

[0103] Clearly, this specific example significantly reduces the amount of data in the character query configuration table, greatly simplifies the calculation, and significantly improves the efficiency of identifying missing characters.

[0104] Based on the specific example above, it is preferable to define the missing character as the missing character with the fewest possible corresponding characters in the missing character list. That is, the missing character list is compiled using the missing character with the fewest corresponding possible characters, thereby further simplifying the missing character list and more efficiently identifying the missing character. Therefore, Table 2 above will be simplified to Table 4 below:

[0105]

[0106] Table 4

[0107] In all embodiments of this application, the document is a machine-readable travel document, and the types of the machine-readable travel document include, but are not limited to, passports, regional passes, and regional return permits.

[0108] Based on the above two embodiments, this application also provides a computer-readable storage medium storing a computer program thereon, wherein the computer program, when executed by a processor, implements the steps of any one of the above embodiments of the document machine-readable code correction method.

[0109] Meanwhile, an electronic device is also provided, including a memory and a processor. The memory is configured to store instructions, and the processor is configured to execute the stored instructions to implement the steps of any one of the above embodiments of the document reader code correction method.

[0110] As a specific application scenario of all the embodiments described in this application:

[0111] When using a certain type of regional pass to read information at XX Bank, characters on the surface of the machine-readable code on the pass were sometimes missing, causing inconvenience to the recognition process and resulting in a certain probability of failure; this also caused inconvenience to tellers in processing transactions. The machine-readable code correction method described in any of the above embodiments of this application can effectively improve the success rate of recognition, greatly solving the problem of needing to reread the pass due to wear and tear, thereby saving tellers' time in processing transactions.

[0112] In summary, the document machine-readable code correction method and storage medium provided in this application can efficiently and accurately calculate the correct characters when machine-readable code recognition fails by recognizing and correcting the characters on the machine-readable travel document. This significantly improves the success rate of missing character recognition, provides convenience for business personnel, reduces the chance of manual intervention and repeated verification, thereby improving business processing efficiency and optimizing customer experience.

[0113] Finally, it should be noted that although the above embodiments have been described in the text and drawings of this application, this should not limit the scope of patent protection of this application. Any technical solutions that are based on the essential concept of this application and utilize the content described in the text and drawings of this application, resulting in equivalent structural or procedural substitutions or modifications, as well as the direct or indirect application of the technical solutions of the above embodiments to other related technical fields, are all included within the scope of patent protection of this application.

Claims

1. A method for correcting errors in machine-readable identification codes, characterized in that, include: The machine-readable code is segmented according to the document specifications to obtain multiple identification objects; If a recognition object has a missing character, the missing character is calculated using the 731 weighted method based on the successfully recognized known characters. If an object to be identified has two missing characters, the weight corresponding to each missing character and at least two possible characters are determined based on the identification result. If the missing character is a check bit, its corresponding weight is set as the check bit identifier value. Based on the successfully identified known characters, the weights, and the at least two possible characters, the 731 weighted method is used to determine each missing character. The step of determining the weight position corresponding to each missing character and at least two possible characters based on the recognition results includes: Based on the recognition results, a list of missing characters is established, wherein the list of missing characters includes the position of the missing character in the recognition object, its corresponding weight, and at least two possible characters; After establishing the list of missing characters, the process further includes: Based on the successfully identified known characters, the possible characters corresponding to a missing character, and the weight of another missing character, a character query configuration table is constructed; wherein, the fields of the character query configuration table include known characters, the weight of the missing character and its corresponding possible character, and the weight of the other missing character; Based on the successfully identified known characters, the weighted position, and the at least two possible characters, the 731 weighted method is used to determine each missing character, including: Based on the character query configuration table, the character corresponding to the weight position of the other missing character in each column of the character query configuration table is calculated using the 731 weighted method, and the missing character corresponding to the other missing character is determined by referring to the possible characters corresponding to the other missing character in the missing character list.

2. The method for correcting errors in machine-readable identification codes as described in claim 1, characterized in that, The missing character is a missing character that has a relatively small number of possible characters in the missing character list, or The missing character can be any missing character.

3. The method for correcting errors in machine-readable identification codes as described in claim 1, characterized in that, The process of segmenting the machine-readable code according to document specifications to obtain multiple identification objects then includes: Perform character recognition on each object separately; If the results of three consecutive recognitions of an object are consistent, the recognition is considered successful. If the results of three recognitions of an object are inconsistent, it is determined that there are missing characters, and the recognition count is incremented by 1; it is then checked whether there are duplicate results. If not, the recognition count is increased until duplicate results are found.

4. The method for correcting errors in machine-readable identification codes as described in claim 1, characterized in that, The document in question is a tourist document.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the document machine-readable code correction method as described in any one of claims 1 to 4.

Images