A blockchain-based electronic certificate management system and method
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING SIECAN TECH CO LTD
- Filing Date
- 2024-09-29
- Publication Date
- 2026-06-26
Smart Images
Figure CN119338760B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of blockchain technology, and in particular to a blockchain-based electronic certificate management system and method. Background Technology
[0002] Using electronic certificates can effectively improve work efficiency in actual work processes. In addition, managing electronic certificates through blockchain technology can further ensure the management efficiency and security of electronic certificates. However, current blockchain-based electronic certificate management methods often fail to determine the corresponding electronic certificate storage method based on the image quality of each certificate image uploaded by the user, resulting in low integrity of the stored certificate information. Therefore, how to ensure the integrity of the stored certificate information while ensuring the efficiency of certificate information upload is a problem that urgently needs to be solved by those skilled in the art.
[0003] Chinese Patent Publication No. CN116720824A discloses a blockchain-based electronic certificate repository management system and method. The system includes: an acquisition module for acquiring target electronic certificates and storing them in a corresponding preset blockchain to obtain an electronic certificate repository; a verification module for verifying the access requests of acquired users and obtaining verified target access requests; a visualization module for determining the accessed electronic certificates in the electronic certificate repository based on the target access request and display processing rules, and visually displaying them; and an access restriction module for determining whether a user is a malicious user, and if so, restricting the malicious user's access for a preset time period. However, this solution suffers from the following problems: it cannot determine the appropriate certificate storage method based on the image quality of each certificate image to be processed in the actual work scenario, resulting in low integrity of the stored certificate information and consequently low work efficiency in the actual work process. Summary of the Invention
[0004] To address this issue, the present invention provides a blockchain-based electronic certificate management system and method to overcome the problem that existing technologies cannot determine the appropriate certificate storage method based on the image quality of each certificate image to be processed in the actual work scenario, resulting in low integrity of the stored certificate information.
[0005] To achieve the above objectives, the present invention provides a blockchain-based electronic certificate management system, comprising:
[0006] The image analysis module is used to detect the brightness distribution uniformity and sharpness reference value of each certificate image to be processed, and to determine the image quality category based on the brightness distribution uniformity and sharpness reference value.
[0007] The storage analysis module, which is connected to the image analysis module, is used to determine the certificate storage method according to the image quality category of each certificate image to be processed;
[0008] A character processing module, which is connected to the storage and analysis module, is used to perform character recognition and determine the character processing method based on the proportion of the lost area within the character region.
[0009] The association analysis module, which is connected to the character processing module, is used to determine the association coefficient between each stored preferred certificate image and the preferred certificate image, so as to determine the associated certificate image;
[0010] The region analysis module, which is connected to the character processing module, is used to determine whether to perform region filling for the lost region or to adjust the short side length and long side length of the character region.
[0011] The certificate storage module is connected to the image analysis module, the storage analysis module, and the character processing module, respectively, and is used to store the preferred certificate images and their character information for each electronic certificate.
[0012] Furthermore, the image quality categories include:
[0013] A class of quality images whose brightness distribution uniformity is greater than the preset brightness distribution uniformity and whose sharpness reference value is greater than the preset sharpness reference value;
[0014] A Class II quality image whose brightness distribution uniformity is less than or equal to a preset brightness distribution uniformity value or whose sharpness reference value is less than or equal to a preset sharpness reference value.
[0015] Furthermore, for a single certificate to be uploaded, the certificate storage method is as follows: the storage analysis module determines the preferred certificate image based on the quality coefficient of each type of quality image, or the storage analysis module determines the preferred certificate image based on the quality coefficient of each certificate image to be processed, and the character processing module performs character recognition on the preferred certificate image.
[0016] Furthermore, the character recognition process performed by the character processing module includes:
[0017] Characters are extracted from the selected certificate images, and the corresponding character regions for each character are divided.
[0018] For unrecognized character regions, loss region detection is performed, and the character processing method is determined based on the proportion of loss region within the character region in order to identify unrecognized characters.
[0019] Furthermore, for a single character, if the proportion of the lost region in the corresponding character area is greater than the preset proportion of the lost region, the character recognition method includes:
[0020] If the character region is within the preset region, the character processing module determines the character information of the character region based on the character information of the same preset region in the associated certificate image;
[0021] If the character area is not within the preset area, the character processing module sends an image quality warning to the user who uploaded the corresponding character.
[0022] Furthermore, for a preferred certificate image to be stored, the association analysis module determines the associated certificate image based on the association coefficient between each stored preferred certificate image and the preferred certificate image.
[0023] The correlation coefficient is determined based on the similarity between the certificate information of each stored preferred certificate image and the certificate information of the identified preferred certificate image, as well as the certificate interval time.
[0024] Furthermore, for a single character, if the proportion of the lost region of the corresponding character area is less than or equal to the preset proportion of the lost region, the character processing module determines the character recognition method based on the reference interval distance of the lost region within the character area and the difference value of the interval distance.
[0025] The difference between the reference interval distance and the interval distance is determined based on the interval distance between adjacent loss regions within the character region.
[0026] Furthermore, if the reference interval distance of the lost area within the corresponding character area is less than or equal to the preset reference distance and the interval distance difference value is less than or equal to the preset distance difference value, the area analysis module determines whether to fill the lost area based on whether the character shape in the character area other than the lost area is symmetrical about the vertical or horizontal central axis of the corresponding character area.
[0027] Furthermore, if the reference interval distance of the corresponding character region is greater than the preset reference distance or the difference value of the interval distance is greater than the preset difference value, the region analysis module determines whether to increase or adjust the short side length and long side length of the corresponding character region based on the number of edge loss regions.
[0028] The increase in the length of the short side and the length of the long side is positively correlated with the number of edge loss regions. This invention also provides a method for applying the aforementioned blockchain-based electronic certificate management system, comprising:
[0029] Image quality category is determined based on brightness distribution uniformity and sharpness reference values;
[0030] The storage method for the certificates and licenses is determined based on the image quality category of each image to be processed.
[0031] The certificate storage method is to determine the preferred certificate image based on the quality coefficient of each type of quality image, or to determine the preferred certificate image based on the quality coefficient of each certificate image to be processed and perform character recognition on the preferred certificate image.
[0032] The character processing method is determined based on the proportion of the lost region within the character area and the distribution of the lost region.
[0033] The character processing method is to determine the character recognition method based on whether the corresponding character region is within a preset region or the reference interval distance of the lost region within the character region and the difference value of the interval distance;
[0034] The preferred image of the certificate to be uploaded is stored in the preset certificate directory. If it contains character information, the preferred image and its character information are stored together in the same preset certificate directory.
[0035] Compared with the prior art, the beneficial effects of the present invention are that the technical solution of the present invention determines the image quality category based on the uniformity of brightness distribution and the sharpness reference value, and determines the certificate storage method based on the image quality category of each certificate image to be processed, ensuring that the determined certificate storage method conforms to the actual working scenario, and ensuring the integrity of the stored certificate information while ensuring the efficiency of certificate information upload. The present invention improves the integrity of the acquired certificate information.
[0036] Furthermore, in this invention, when there are images of a certain quality among the images of the certificates to be uploaded, the preferred certificate image is determined based on the quality coefficient of each image of that quality. This improves the efficiency of the certificate information uploading process and ensures the integrity of the certificate information stored in the system, avoiding information loss during subsequent certificate use and thus preventing low work efficiency.
[0037] Furthermore, in this invention, when all the certificate images to be uploaded are of Class II quality, a preferred certificate image is determined based on the quality coefficient of each certificate image, and character recognition is performed on the preferred certificate image. The preferred certificate image and its character information are stored together. By storing certificate information in conjunction with the certificate image through character information, the integrity of certificate information can be effectively improved.
[0038] Furthermore, in this invention, the character processing method is determined based on the proportion of the lost region within the character area, and a targeted character recognition method is further selected based on whether the character area is in a preset area and the distribution state of the lost region, so that the character recognition method conforms to the actual application scenario, thereby improving the efficiency of the character recognition process. This invention improves the uploading efficiency of certificate information while ensuring the integrity and validity of the certificate information stored in the system. Attached Figure Description
[0039] Figure 1 This is a module connection diagram of the blockchain-based electronic certificate management system of the present invention;
[0040] Figure 2This is a flowchart illustrating how the present invention determines the certificate storage method based on the image quality category of each certificate image to be processed;
[0041] Figure 3 This is a flowchart illustrating how the character processing method is determined based on the proportion of the lost region within the character area according to the present invention.
[0042] Figure 4 This is a schematic diagram of the blockchain-based electronic certificate management method of the present invention. Detailed Implementation
[0043] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.
[0044] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.
[0045] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.
[0046] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.
[0047] Please see Figures 1 to 3 As shown, the present invention provides a blockchain-based electronic certificate management system, comprising:
[0048] The image analysis module is used to detect the brightness distribution uniformity and sharpness reference value of each certificate image to be processed, and to determine the image quality category based on the brightness distribution uniformity and sharpness reference value.
[0049] The storage analysis module, which is connected to the image analysis module, is used to determine the certificate storage method according to the image quality category of each certificate image to be processed;
[0050] A character processing module, which is connected to the storage and analysis module, is used to perform character recognition and determine the character processing method based on the proportion of the lost area within the character region.
[0051] The association analysis module, which is connected to the character processing module, is used to determine the association coefficient between each stored preferred certificate image and the preferred certificate image, so as to determine the associated certificate image;
[0052] The region analysis module, which is connected to the character processing module, is used to determine whether to perform region filling for the lost region or to adjust the short side length and long side length of the character region.
[0053] The certificate storage module is connected to the image analysis module, the storage analysis module, and the character processing module, respectively, and is used to store preferred certificate images and their character information for each electronic certificate.
[0054] In this invention, the image of the certificate to be processed is an image taken by the user and uploaded to the system. The certificate to be uploaded is the certificate that the user needs to store in the blockchain-based electronic certificate management system described in this invention. In this invention, the certificates are all inspection and quarantine certificates for meat products.
[0055] Specifically, the image quality categories include:
[0056] A class of quality images where the brightness distribution uniformity is greater than the preset brightness distribution uniformity and the sharpness reference value is greater than the preset sharpness reference value;
[0057] A Class II quality image whose brightness distribution uniformity is less than or equal to a preset brightness distribution uniformity value or whose sharpness reference value is less than or equal to a preset sharpness reference value.
[0058] The brightness distribution uniformity is determined based on the maximum and minimum brightness values of each certificate image to be processed. The brightness distribution uniformity is the ratio of the difference between the maximum and minimum brightness values to the sum of the maximum and minimum brightness values. The sharpness reference value is determined based on the number of pixels and noise intensity of each certificate image to be processed. The sharpness reference value is the natural logarithm of the product of the number of pixels and the noise intensity.
[0059] The preset brightness distribution uniformity and preset clarity reference value can be set by the user according to actual needs and historical records. The higher the user's requirement for the integrity of the stored preferred certificate images, the larger the preset brightness distribution uniformity value and the smaller the preset clarity reference value. A method for determining the preset brightness distribution uniformity value is provided, which is the average value of the brightness distribution uniformity of each preferred certificate image without stored character information in the historical records that meet the user's requirement for the integrity of the stored certificate information. A method for determining the preset clarity reference value is provided, which is the average value of the clarity reference value of each preferred certificate image without stored character information in the historical records that meet the user's requirement for the integrity of the stored certificate information.
[0060] Specifically, for a single certificate to be uploaded, the certificate storage method is as follows: the storage analysis module determines the preferred certificate image based on the quality coefficient of each type of quality image, or the storage analysis module determines the preferred certificate image based on the quality coefficient of each certificate image to be processed, and the character processing module performs character recognition on the preferred certificate image.
[0061] If there is a Class I quality image among the certificate images to be uploaded, the storage and analysis module determines the preferred certificate image based on the quality coefficient of each Class I quality image and stores the preferred certificate image in the certificate storage module. If all the certificate images to be uploaded are Class II quality images, the storage and analysis module determines the preferred certificate image based on the quality coefficient of each certificate image, performs character recognition on the preferred certificate image, and stores the preferred certificate image and its character information together in the certificate storage module.
[0062] Images with higher quality coefficients are designated as priority images. These quality coefficients are determined based on the brightness distribution uniformity and sharpness reference values of each image. The quality coefficient is the sum of the products of the brightness distribution uniformity, the sharpness reference value, and their corresponding influence coefficients. Users can set the values of the influence coefficients corresponding to the brightness distribution uniformity and sharpness reference values according to their actual needs. The smaller the influence of wrinkles or lighting on the image after the user selects the preferred image, the higher the requirement for brightness uniformity, and the larger the influence coefficient value corresponding to brightness distribution uniformity. A method for determining the brightness distribution uniformity is provided, along with a value of 0.4 for the influence coefficient corresponding to brightness distribution uniformity. Similarly, the higher the user's requirement for sharpness in the preferred image, the larger the influence coefficient value corresponding to the sharpness reference value. A value of 0.6 for the influence coefficient corresponding to the sharpness reference value is provided.
[0063] Specifically, the character recognition process performed by the character processing module includes:
[0064] Characters are extracted from the selected certificate images, and the corresponding character regions for each character are divided.
[0065] For unrecognized character regions, loss region detection is performed, and the character processing method is determined based on the proportion of loss region within the character region in order to identify unrecognized characters.
[0066] The character region is a rectangular area with the maximum width of each character as the short side length and the maximum height of each character as the long side length. The loss region is the area within the character region where the edges of characters cannot be identified. The unidentified characters are characters whose character information could not be obtained during the character extraction process due to the existence of loss regions within the character region.
[0067] Specifically, for a single character, if the proportion of the lost region in the corresponding character area is greater than the preset proportion of the lost region, the character recognition method includes:
[0068] If the character region is within the preset region, the character processing module determines the character information of the character region based on the character information of the same preset region in the associated certificate image;
[0069] If the character area is not within the preset area, the character processing module sends an image quality warning to the user who uploaded the corresponding character.
[0070] Wherein, the loss region ratio is the ratio of the area of the loss region within the corresponding character region to the area of the corresponding character region. The value of the preset loss region ratio can be set by the user according to actual needs and historical records. The higher the user's requirement for the accuracy of the character recognition result, the smaller the value of the preset loss region ratio. A method for determining the value of the preset loss region ratio is provided, which records the historical records that meet the user's accuracy requirements for the character recognition result as reference records, and records the average value of the loss region ratio of each character region when performing character recognition in the reference records as the preset loss region ratio. A value of the preset loss region ratio is provided, which is 0.3.
[0071] Preferred certificate images within the same preset certificate catalog are divided into several sub-image regions of equal area using the same division method. The preset region is determined based on the similarity of reference information within the sub-image regions at the same position of the preferred certificate images within the same preset certificate catalog. Sub-image regions with a reference information similarity greater than a preset reference information similarity are designated as preset regions. The reference information similarity is the ratio of the number of identical characters within a sub-image region to the maximum number of characters in the corresponding sub-image regions of each preferred certificate image at the same position. The user can set the preset reference information similarity value according to actual needs and historical records. The higher the user's requirement for the accuracy of character recognition results, the larger the preset reference information similarity value. One preset reference information similarity value is provided: 50%.
[0072] Specifically, for a preferred certificate image to be stored, the association analysis module determines the associated certificate image based on the association coefficient between each stored preferred certificate image and the preferred certificate image.
[0073] The correlation coefficient is determined based on the similarity between the certificate information of each stored preferred certificate image and the certificate information of the identified preferred certificate image, as well as the certificate interval time.
[0074] The associated certificate image is a stored preferred certificate image with an association coefficient greater than a preset association coefficient. The user can set the value of the preset association coefficient according to actual needs and historical records. The higher the user's requirement for the accuracy of character recognition results, the larger the preset association coefficient. A method for determining the value of the preset association coefficient is provided, in which the historical records of character information determined based on the associated certificate image are recorded as association reference records, and the average value of the association coefficients of the associated certificate images in each association reference record that meets the user's requirement for the accuracy of character recognition results is recorded as the preset association coefficient.
[0075] The correlation coefficient is the natural logarithm of the product of the similarity between the certificate information of each stored preferred certificate image and the recognized certificate information of that preferred certificate image, and the certificate interval duration. The certificate information similarity is determined based on the information overlap of overlapping information in the certificate information corresponding to the two certificate images and the weighting coefficient of overlapping information of corresponding categories. Si is the information overlap degree of the i-th type of overlapping information, and θi is the weight coefficient corresponding to the i-th type of overlapping information. The overlapping information categories include, but are not limited to, certificate inspection location, inspected goods, and production unit. In this invention, the weight coefficients corresponding to various types of overlapping information are not specifically set. Users can set the weight coefficients corresponding to various types of overlapping information according to actual needs. The certificate interval duration is the interval duration between the visa dates of the certificates corresponding to the two certificate images.
[0076] Specifically, for a single character, if the proportion of the lost region of the corresponding character area is less than or equal to the preset proportion of the lost region, the character processing module determines the character recognition method based on the reference interval distance of the lost region within the character area and the difference value of the interval distance.
[0077] The difference between the reference interval distance and the interval distance is determined based on the interval distance between adjacent loss regions within the character region.
[0078] The reference interval distance is the average of the interval distances between adjacent loss regions within the character region. The interval distance difference is the ratio of the sum of the absolute values of the differences between the interval distances of adjacent loss regions and the reference interval distance to the product of the number of loss regions and the preset number of adjacent regions. For any loss region, the adjacent loss regions are determined based on the interval distance between the loss region and other loss regions. The number of loss regions selected from the interval distances in ascending order is recorded as the adjacent loss regions of the loss region. The user can set the preset number of adjacent regions according to actual needs. The higher the user's requirements for the accuracy of the character recognition results, the more preset adjacent regions there are. One possible value for the preset number of adjacent regions is 4.
[0079] Specifically, if the reference interval distance of the lost area within the corresponding character area is less than or equal to the preset reference distance and the interval distance difference value is less than or equal to the preset distance difference value, the area analysis module determines whether to fill the lost area based on whether the character shape in the character area other than the lost area is symmetrical about the vertical or horizontal central axis of the corresponding character area.
[0080] The vertical central axis is the line connecting the center points of the two short sides of the character area, and the horizontal central axis is the line connecting the center points of the two long sides of the character area. If the character shape in the character area other than the lost area is symmetrical about the vertical or horizontal central axis of the corresponding character area, the lost area is filled according to the character shape of the symmetrical area to each lost area, and secondary character recognition is performed on the character area after the lost area is filled. If the character information in the character area is still not recognized, the character information of the character area is determined according to the character information of the same preset area of the associated certificate image.
[0081] Specifically, if the reference interval distance of the corresponding character region is greater than the preset reference distance or the interval distance difference value is greater than the preset distance difference value, the region analysis module determines whether to increase and adjust the short side length and long side length of the corresponding character region based on the number of edge loss regions.
[0082] The increase in the length of the short side and the length of the long side is positively correlated with the number of edge loss regions.
[0083] The edge loss region is a loss region whose distance from the center point of the character region is greater than a preset edge distance. The center point is the intersection of the vertical center axis and the horizontal center axis. A preset edge distance value is provided, which is 20% of the corresponding character region. When the proportion of edge loss regions is large, the character region division has a significant impact on character recognition. The length of the short side and the length of the long side of the character region are increased to avoid incomplete character information in the character region, which would lead to recognition failure. The proportion of edge loss regions is the ratio of the number of edge loss regions to the total number of loss regions in the character region.
[0084] The preset reference distance and preset distance difference value can be set by the user based on historical records. The historical records that determine whether to adjust the short side length and long side length of the corresponding character area based on the number of edge loss areas are recorded as distance reference records. The minimum value of the reference interval distance in the distance reference records is recorded as the preset reference distance, and the minimum value of the interval distance difference value is recorded as the preset distance difference value.
[0085] Please see Figure 4 As shown, this is a schematic diagram of the blockchain-based electronic certificate management method of the present invention. The present invention provides a blockchain-based electronic certificate management method, comprising:
[0086] Image quality category is determined based on brightness distribution uniformity and sharpness reference values;
[0087] The storage method for the certificates and licenses is determined based on the image quality category of each image to be processed.
[0088] The certificate storage method is to determine the preferred certificate image based on the quality coefficient of each type of quality image, or to determine the preferred certificate image based on the quality coefficient of each certificate image to be processed and perform character recognition on the preferred certificate image.
[0089] The character processing method is determined based on the proportion of the lost region within the character area and the distribution of the lost region.
[0090] The character processing method is to determine the character recognition method based on whether the corresponding character region is within a preset region or the reference interval distance of the lost region within the character region and the difference value of the interval distance;
[0091] The preferred image of the certificate to be uploaded is stored in the preset certificate directory. If it contains character information, the preferred image and its character information are stored together in the same preset certificate directory.
[0092] The user can divide the preset certificate catalog according to the visa date and application region of each certificate. It is worth noting that the user can choose the setting method of the preset certificate catalog according to the actual work situation. This is easy for those skilled in the art to understand and will not be elaborated here.
[0093] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.
[0094] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.
Claims
1. A blockchain-based electronic certificate management system, characterized in that, include: The image analysis module is used to detect the brightness distribution uniformity and sharpness reference value of each certificate image to be processed, and to determine the image quality category based on the brightness distribution uniformity and sharpness reference value. The storage analysis module, connected to the image analysis module, is used to determine the certificate storage method based on the image quality category of each certificate image to be processed. If there is a Class I quality image among the certificate images to be uploaded, the certificate storage method is that the storage analysis module determines the preferred certificate image based on the quality coefficient of each Class I quality image; if all the certificate images to be uploaded are Class II quality images, the certificate storage method is that the storage analysis module determines the preferred certificate image based on the quality coefficient of each certificate image to be processed, and the character processing module performs character recognition on the preferred certificate image. The character processing module, which is connected to the storage and analysis module, is used to perform character recognition. The character processing method is determined based on the proportion of the lost region within the character area and the distribution status of the lost region. The character processing method is determined based on whether the corresponding character area is in a preset area or the reference interval distance of the lost region within the character area and the difference value of the interval distance. The association analysis module, which is connected to the character processing module, is used to determine the association coefficient between each stored preferred certificate image and the preferred certificate image, so as to determine the associated certificate image; The region analysis module, which is connected to the character processing module, is used to fill the lost region or adjust the length of the short side and the length of the long side of the character region. The certificate storage module is connected to the image analysis module, the storage analysis module, and the character processing module, respectively, and is used to store preferred certificate images of first-class quality images and preferred certificate images of second-class quality images and their character information.
2. The blockchain-based electronic certificate management system according to claim 1, characterized in that, The image quality categories include: A class of quality images whose brightness distribution uniformity is greater than the preset brightness distribution uniformity and whose sharpness reference value is greater than the preset sharpness reference value; A Class II quality image whose brightness distribution uniformity is less than or equal to a preset brightness distribution uniformity value or whose sharpness reference value is less than or equal to a preset sharpness reference value.
3. The blockchain-based electronic certificate management system according to claim 2, characterized in that, The character recognition process performed by the character processing module includes: Characters are extracted from the selected certificate images, and the corresponding character regions for each character are divided. For unrecognized character regions, loss region detection is performed, and the character processing method is determined based on the proportion of loss region within the character region in order to identify unrecognized characters.
4. The blockchain-based electronic certificate management system according to claim 3, characterized in that, For a single character, if the proportion of the lost region in the corresponding character area is greater than the preset proportion of the lost region, the character recognition method includes: If the character region is within the preset region, the character processing module determines the character information of the character region based on the character information of the same preset region in the associated certificate image; If the character area is not within the preset area, the character processing module sends an image quality warning to the user who uploaded the corresponding character.
5. The blockchain-based electronic certificate management system according to claim 4, characterized in that, For a preferred certificate image to be stored, the association analysis module determines the associated certificate image based on the association coefficient between each stored preferred certificate image and the preferred certificate image. The correlation coefficient is determined based on the similarity between the certificate information of each stored preferred certificate image and the certificate information of the identified preferred certificate image, as well as the certificate interval time.
6. The blockchain-based electronic certificate management system according to claim 5, characterized in that, For a single character, if the proportion of the lost region in the corresponding character area is less than or equal to the preset proportion of the lost region, the character processing module determines the character recognition method based on the reference interval distance and the difference value of the interval distance in the lost region within the character area. The difference between the reference interval distance and the interval distance is determined based on the interval distance between adjacent loss regions within the character region.
7. The blockchain-based electronic certificate management system according to claim 6, characterized in that, If the reference interval distance of the lost area within the corresponding character area is less than or equal to the preset reference distance and the interval distance difference value is less than or equal to the preset distance difference value, the area analysis module determines whether to fill the lost area based on whether the character shape in the character area other than the lost area is symmetrical about the vertical or horizontal central axis of the corresponding character area.
8. The blockchain-based electronic certificate management system according to claim 7, characterized in that, If the reference interval distance of the corresponding character region is greater than the preset reference distance or the interval distance difference value is greater than the preset distance difference value, the region analysis module determines whether to increase or adjust the short side length and long side length of the corresponding character region based on the number of edge loss regions. The increase in the length of the short side and the length of the long side is positively correlated with the number of edge loss regions.
9. A blockchain-based electronic certificate management method according to any one of claims 1 to 8, characterized in that, include: Image quality category is determined based on brightness distribution uniformity and sharpness reference values; The storage method for the certificates and licenses is determined based on the image quality category of each image to be processed. If there is a quality class among the images of certificates to be uploaded, the certificate storage method is that the storage analysis module determines the preferred certificate image based on the quality coefficient of each quality class image. If all the certificate images to be uploaded are of Class II quality, the certificate storage method is that the storage analysis module determines the preferred certificate image based on the quality coefficient of each certificate image to be processed, and the character processing module performs character recognition on the preferred certificate image. The character processing method is determined based on the proportion of the lost region within the character area and the distribution of the lost region. The character processing method is to determine the character recognition method based on whether the corresponding character region is within a preset region or the reference interval distance of the lost region within the character region and the difference value of the interval distance; The preferred image of the certificate to be uploaded is stored in a preset certificate directory. If the preferred image is a preferred image corresponding to a second-class quality image, the preferred image and its character information are stored together in the same preset certificate directory.