Terminal 3D ring character recognition method, device and equipment based on OCR technology and medium

Abstract

The application discloses a terminal 3D ring character recognition method, device and equipment based on an OCR technology and a medium, and belongs to the technical field of image recognition. The method comprises the following steps: collecting a terminal image in a ring manner, and storing pictures according to a string order to establish a string candidate set document; cutting a terminal region in the image to obtain a corresponding terminal image set; enhancing the contrast of the pictures, and recognizing the pictures arranged in the order one by one; storing a plurality of recognition results in a plurality of lists respectively, splicing the head and tail of a string in each list to remove the duplicate strings, and obtaining one or more complete strings; and matching the splicing result with a string format in the candidate set document, and selecting a string with a matching degree reaching a set threshold value as a final recognition result. The application improves the existing OCR recognition method, overcomes the difficulty in recognizing terminal ring characters and multi-line characters, improves the recognition rate, solves the problems of high work intensity, time consumption and labor intensity, and improves the work efficiency.

Description

Technical Field

[0001] This invention relates to the field of image recognition technology, and more specifically to a method, apparatus, device, and medium for recognizing 3D circular characters on terminals based on OCR technology. Background Technology

[0002] In recent years, OCR technology has seen a wide range of applications. It can extract printed or handwritten text from images or scanned documents and convert it into an editable text format. Applications include medicine, education, business card scanning, and historical document research. For example, in the medical field, OCR can be used to convert doctors' handwritten prescriptions and medical records into electronic text for easier management and retrieval. In short, OCR technology has wide applications in various fields, improving the efficiency, accuracy, and accessibility of document processing.

[0003] However, existing OCR technology cannot recognize 3D circular text on circular objects, such as circular strings on terminals. The main difficulties in recognizing these characters lie in the fact that the string wraps around the circular terminal, and a single camera cannot capture all the text information; after multiple cameras have captured all the text information, it is necessary to sequentially deduplicate and reassemble the text; and the text information at the edges of the circular object is blurred and distorted, making recognition even more difficult. Therefore, in the development of existing terminal products, the circular characters on their surfaces have long relied on manual recognition and input, resulting in low work efficiency, unstable work quality, and a large consumption of human resources.

[0004] In the prior art, patent CN116030470A discloses a method, device, system, and readable storage medium for recognizing curved text in a circular seal. The method includes: acquiring a curved text image of a circular seal; detecting the curved text image of the circular seal using a text detection model to obtain the coordinates of the text character boxes and the coordinates of the string region; processing each single character in the curved text image of the circular seal based on the coordinates of the text character boxes and the coordinates of the string region to obtain a single character forward-order spliced ​​sub-image and a single character reverse-order spliced ​​sub-image; and recognizing the text content in the curved text image of the circular seal based on the single character forward-order spliced ​​sub-image and the single character reverse-order spliced ​​sub-image.

[0005] The aforementioned patent applies to concatenating circular strings that can be covered by a single image, which can be understood as 2D circular strings. However, for text wrapped around a circular object, it is a 3D circular string, and a single image cannot cover the entire circular string, so multiple images are required. Furthermore, the method in the aforementioned patent that sorts each character frame based on the center coordinates cannot be applied to multiple images because, for 3D circular strings, their representation in a single image is not a standard circle or sector, making it impossible to determine the center position of the string frame, and thus the sorting method in the aforementioned patent cannot be used. Summary of the Invention

[0006] This invention aims to solve the problem that existing technologies cannot recognize 3D ring characters on ring-shaped objects. It proposes a method, device, equipment, and medium for recognizing 3D ring characters on terminals based on OCR technology, which can effectively improve the accuracy and efficiency of 3D ring character recognition in terminals.

[0007] To achieve the above-mentioned objectives, the technical solution of the present invention is as follows: A terminal 3D ring character recognition method based on OCR technology, characterized by comprising the following steps: Step S1: Collect terminal images in a 360° surround view and store the images in string order to create a string candidate set document; Step S2: Crop the terminal area in the image to obtain the corresponding terminal image set; Step S3: Enhance image contrast and perform OCR recognition on each of the sequentially arranged terminal images; Step S4: Store multiple recognition results in multiple lists, concatenate the beginning and end of the strings in each list to remove duplicates, and finally obtain one or more complete strings; Step S5: Match the concatenated result with the preset string format in the candidate set document, select the string with a matching degree that reaches the set threshold as the final recognition result, otherwise use the concatenated result as the final result.

[0008] Furthermore, the multiple recognition results are stored in multiple lists, and the strings in each list are concatenated from beginning to end to remove duplicates, ultimately resulting in one or more complete strings, including: Step S401: Obtain the y-coordinates of multiple string positions identified from multiple images; Step S402: Compare the y-coordinates of multiple strings in multiple images, add strings that are greater than a set threshold to the same list, and store the others in another list; Step S403: For multiple strings in the same list, determine the left and right x coordinates of each string text box, and determine whether to delete the first and last characters based on the left and right x coordinate values. Step S404: Update the list according to the result of step S403, and concatenate the strings in the same list after removing duplicates from the beginning and end to obtain the concatenated result.

[0009] Furthermore, when performing OCR recognition on images arranged in sequence, the images are divided into two categories: one is images that have been cropped and then contrast-enhanced, and the other is images that have not been cropped and have their contrast directly enhanced. OCR recognition is performed on the two categories of images separately, and the result with the higher recognition rate between the two categories is returned as the recognition result.

[0010] Furthermore, the method for concatenating strings in the same list after removing duplicates from the beginning and end is as follows: calculate the similarity between two strings using edit distance, and then design a function to use a for loop to iterate and compare the local similarity of the two strings from the beginning and end respectively. If the local similarity is greater than a set threshold, then concatenate the first string with the second string after removing the local part.

[0011] Furthermore, in step S404, the starting position for concatenation is the string following the last empty character in the same list that is not empty at either end.

[0012] Furthermore, in step S403, strings in the same list are represented as multiple segments of the same complete string. It is determined whether the left x coordinate of each string in the list is 0. If it is 0, it is considered that the first character in the string is not accurately identified and is deleted. It is also determined whether the right x coordinate of each string in the list is equal to the width of the image in which the string is located. If it is equal, it is considered that the last character in the string is not accurately identified and is deleted.

[0013] This invention also proposes a terminal 3D ring character recognition device based on OCR technology, comprising: Image acquisition module for 360° surround acquisition of terminal images; The image storage module is used to store the acquired terminal images in string order and create a string candidate set document; The image cropping module crops the terminal area in the image to obtain the corresponding terminal image set; The image processing module is used to enhance image contrast and perform OCR recognition on each of the sequentially arranged terminal images. The concatenation and deduplication module is used to store multiple recognition results in multiple lists, concatenate the beginning and end of the strings in each list to remove duplicates, and finally obtain one or more complete strings; The results output module is used to match the concatenated result with the string format in the candidate set document, select the string with a matching degree that reaches a set threshold as the final recognition result, otherwise use the concatenated result as the final result.

[0014] Furthermore, the splicing and deduplication module includes: The first recognition unit is used to obtain the y-coordinates of multiple string positions in multiple images for recognition; The first data processing unit is used to compare the y-coordinates of multiple strings in multiple images, add strings that are greater than a set threshold to the same list, and store the others in another list. The second data processing unit is used to determine the left and right x coordinates of each string text box for multiple strings in the same list, and to determine whether to delete the first and last characters based on the left and right x coordinate values. The first concatenation unit is used to update the list according to the processing result of the second data processing unit, and to concatenate the strings in the same list after removing duplicates from the beginning and end to obtain the concatenated result.

[0015] The present invention further proposes a terminal 3D ring character recognition device based on OCR technology, comprising: Memory, used to store computer programs; A processor is used to execute the computer program to implement the steps in the terminal 3D ring character recognition method based on OCR technology as described above.

[0016] The present invention further proposes a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of a terminal 3D ring character recognition method based on OCR technology as described above.

[0017] In summary, the present invention has the following advantages: (1) This invention improves the recognition rate and work efficiency of current terminal surrounding characters and multi-line characters by improving the existing OCR recognition method. It can save time and manpower costs in the process of terminal information input, and can greatly improve its efficiency and accuracy. It has good promotion and application value. (2) This invention uses multiple cameras to capture multiple terminal images in a 360° surround view. Through multi-view image stitching and string matching algorithms, it ensures the correct identification and merging of the same string under multiple views, and realizes accurate string reconstruction and recognition. (3) In order to optimize the string splicing process, the present invention classifies the identified strings in a reasonable way, thereby simplifying the string splicing process from different perspectives and improving the overall processing efficiency; (4) When identifying different strings, the present invention selects the first non-empty string identified as the benchmark for subsequent comparison, and performs string classification and aggregation based on the comparison results, which simplifies the subsequent multi-view splicing operation and improves the overall processing efficiency. (5) In the process of deduplication by splicing the beginning and end of the string, the present invention regards the empty string as a delimiter between complete strings and uses it to identify the start and end positions of the string. The use of the empty string as a delimiter can help the system accurately identify and extract each substring, thereby achieving effective splicing and recombination of the complete string. (6) The present invention presets specific formats and specifications based on the rules of strings to optimize the string recognition process and improve the recognition accuracy. These custom formats and specifications help the system to more accurately identify and classify target strings and reduce the possibility of misidentification or incorrect splicing. (7) The present invention still outputs splicing results that do not meet the set threshold. This processing method ensures the flexibility of the system, which can adapt to diverse input data and provide complete recognition results. Attached Figure Description

[0018] Figure 1 This is a schematic diagram of the overall process of the present invention; Figure 2 This is a schematic diagram of the image acquisition device of the present invention; Figure 3 This is a simplified schematic diagram of the overall process of the present invention; Figure 4 These are terminal images from different perspectives in Embodiment 1 of the present invention. Figure 4 (a) is an image taken by camera a from a first-person perspective. Figure 4 (b) is an image taken by camera b from a second-person perspective. Detailed Implementation

[0019] To more clearly illustrate the present invention, the following description, in conjunction with preferred embodiments and accompanying drawings, further clarifies the invention. Those skilled in the art should understand that the specific description below is illustrative rather than restrictive and should not be construed as limiting the scope of protection of the present invention.

[0020] Example 1 This invention provides a terminal 3D ring character recognition method based on OCR technology, such as... Figures 1 to 3 As shown, it includes the following steps: Step S1: Place the terminal into the... Figure 2 The image acquisition device shown uses four cameras to capture images in a 360° surround; then the images are stored in string order to create a string candidate set document, and the terminal string format and specifications are pre-entered into the document for subsequent string matching.

[0021] Preferably, in this step, when the terminal is placed into the image acquisition device, the front end displays the terminal image. To reduce the error rate, the orientation classifier in OCR technology is not used. Instead, the inverted character terminal image is rotated 180° and the image is stored in string order.

[0022] In this step, the terminal string format specification is a custom rule and standard set by this solution based on specific application scenarios. For example, some strings may begin with a specific character sequence (such as "aBC"). The strings recognized by this solution have certain regularities, so specific formats and specifications can be preset based on these regularities to optimize the string recognition process and improve recognition accuracy. These custom formats and specifications help the system more accurately identify and classify target strings, reducing the possibility of misidentification or incorrect splicing.

[0023] Step S2: Preprocess the image.

[0024] Specifically, it includes: Step S201: Crop the terminal area in the image to obtain the corresponding terminal image set; Step S202: Enhance image contrast.

[0025] Step S3: Perform OCR recognition on each of the sequentially arranged images.

[0026] Specifically, it includes: Images are divided into two categories: those cropped and enhanced for contrast, and those uncropped but directly enhanced for contrast. OCR recognition is performed on both categories, and the result with the higher recognition rate is returned. It should be noted that OCR recognition can automatically obtain the coordinates of text boxes within a string.

[0027] Step S4: Store the multiple recognition results in multiple lists, and concatenate the first and last strings in each list to remove duplicates, finally obtaining one or more complete strings.

[0028] The splicing technology used in this solution can identify two different strings on a single terminal. Because the terminal has a ring-shaped structure, a single camera cannot capture all the strings on the entire terminal at once; therefore, multiple cameras are needed to capture images from different perspectives. Assuming... Figure 4 (a) shows an image taken by camera a from a first-person perspective. Figure 4 (b) shows an image taken by camera b from a second-person perspective. By combining image data from these two different perspectives, the system can completely identify all the string information on the terminal, thereby achieving accurate identification and splicing of the entire terminal string.

[0029] Furthermore, two strings were present on the terminal, one of which was captured from two different perspectives. Despite the string appearing separately in the two perspectives, the system was able to accurately align and regularize the identical strings from both perspectives using a stitching technique. Therefore, the system correctly identified the two strings: “aBC123 dEF456 gHI789” and “ABC123 DEF456 GHI789”, instead of incorrectly stitching them together as “aBC123 dEF456 gHI789 ABC123DEF456” or “GHI789”. Through multi-view image stitching and string matching algorithms, the system ensured that the same string from multiple perspectives was correctly identified and merged, thus achieving accurate string reconstruction and recognition.

[0030] Specifically, step S4 includes the following steps: Step S401: Obtain the y-coordinates of multiple string positions identified from multiple images; Step S402: Compare the y-coordinates of multiple strings in multiple images. Specifically, compare the y-coordinate of each string with the y-coordinate of the first non-empty string. Add strings that are greater than a set threshold to the same list, and store the others in another list. Strings in the same list represent multiple segments of the same complete string. Step S403: For multiple strings in the same list, determine the left and right x coordinates of each string text box; Step S404: Update the list according to the result of step S403, and concatenate the strings in the same list after removing duplicates from the beginning and end to obtain the concatenated result.

[0031] In step S402 above, considering that the PaddleOCR technology used will recognize empty strings and defaults to setting the y-coordinate of empty strings to 0, in order to optimize the subsequent string concatenation processing steps, step S402 can reasonably classify the recognized strings, thereby simplifying the string concatenation process from different perspectives. For example, from the same perspective, OCR may recognize multiple strings, such as "aBC123", "dEF456", "gHI789" and "ABC123", "DEF456". If all strings are compared with the y-coordinate (i.e., 0) of the empty string, the system needs to process a large amount of redundant data, increasing the complexity of subsequent concatenation work. To improve efficiency, the system chooses the first non-empty string (let's say "aBC123") as the benchmark for subsequent comparisons. Figure 4As shown in (a), the y-coordinates of two complete strings differ significantly, while the y-coordinates of substrings within the same complete string are usually relatively close (generally less than 250 pixels). Therefore, the system sets a threshold (250 pixels) to determine whether strings belong to different parts of the same complete string. When the y-coordinate distance between strings "aBC123" and "dEF456" is less than this threshold, the system assumes they belong to the same complete string and categorizes them into the same list. For strings with a y-coordinate difference greater than the threshold, such as "ABC123", the system determines that they are part of another complete string and categorizes them into different lists. In this way, the system can effectively classify and aggregate strings, simplifying subsequent multi-view concatenation operations and improving overall processing efficiency.

[0032] Further, step S403 specifically includes: determining whether the left x-coordinate of each string in the list is 0; if it is 0, the first character in the string is considered inaccurately identified and deleted; determining whether the right x-coordinate of each string in the list is equal to the width of the image containing the string; if it is equal, the last character in the string is considered inaccurately identified and deleted; thus, the list is updated to the string field with improved accuracy for each image. The aforementioned coordinate processing method can distinguish whether each string field comes from the same complete string and improve the accuracy of string concatenation.

[0033] Furthermore, in step S404, the method for deduplicating and concatenating strings in the same list is as follows: The similarity between two strings is calculated using edit distance. Then, a function is designed to iterate through the two strings from the beginning and end using a for loop, comparing their local similarity. If the local similarity is greater than a set threshold, the first string is concatenated with the second string (with its local portion removed) to achieve deduplication. In this embodiment, the similarity threshold is set to 0.7; and the starting position for concatenation is the string after the last empty character in the same list that is not empty at either end. This scheme treats empty strings as separators between complete strings, used to identify the start and end positions of strings. For example, in the list ["dEF456", "gHI789", " ", "aBC123"], the presence of the empty string " " indicates that "aBC123" is the beginning of a complete string. Therefore, the system uses the empty string as a marker and takes "aBC123" as the starting position in the concatenation process. Using an empty string as a delimiter helps the system accurately identify and extract each substring, thereby enabling effective concatenation and recombination of the complete string.

[0034] Step S5: Match the concatenated result with the string format in the candidate set, select the string with a matching degree that reaches the set threshold as the final recognition result, otherwise use the concatenated result as the final result.

[0035] It should be noted that failing to meet the threshold does not necessarily mean the recognition result is unacceptable. It could simply mean the string's format is not present in the preset formats and specifications of this solution, belonging to a new or undefined string type. Therefore, even if the string does not meet the set threshold, the system will still consider it a valid recognition result and display it as the final output on the user interface. This approach ensures the system's flexibility, allowing it to adapt to diverse input data and provide complete recognition results.

[0036] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Any simple modifications or equivalent changes made to the above embodiments based on the technical essence of the present invention shall fall within the protection scope of the present invention.

[0037] Example 2 Based on the same inventive concept, this invention provides a terminal 3D ring character recognition device based on OCR technology, including: an image acquisition module, an image storage module, an image cropping module, an image processing module, a splicing and deduplication module, and a result output module.

[0038] The image acquisition module is used to acquire images from the terminal in a 360° surround view.

[0039] The image storage module is used to store the acquired terminal images in string order and create a string candidate set document.

[0040] The image cropping module is used to crop the terminal area in the image to obtain the corresponding terminal image set.

[0041] The image processing module is used to enhance image contrast and perform OCR recognition on each of the sequentially arranged terminal images.

[0042] The concatenation and deduplication module is used to store multiple recognition results in multiple lists, concatenate the beginning and end of the strings in each list to remove duplicates, and finally obtain one or more complete strings.

[0043] Specifically, the splicing and deduplication module includes a first identification unit, a first data processing unit, a second data processing unit, and a first splicing unit.

[0044] The first recognition unit is used to obtain the y-coordinates of multiple string positions in multiple images.

[0045] The first data processing unit is used to compare the y-coordinates of multiple strings in multiple images. Specifically, it compares the y-coordinate of each string with the y-coordinate of the first non-empty string. Strings that are greater than a set threshold are added to the same list, while others are stored in another list. Strings in the same list represent multiple segments of the same complete string.

[0046] The second data processing unit is used to determine the left and right x-coordinates of each string text box for multiple strings in the same list, and to determine whether to delete the first and last characters based on the x-coordinate values. Specifically, the second data processing unit performs the following checks: it checks whether the left x-coordinate of each string in the same list is 0. If it is 0, it considers the first character in the string to be inaccurately recognized and deletes it; it checks whether the right x-coordinate of each string in the same list is equal to the width of the image containing the string. If it is, it considers the last character in the string to be inaccurately recognized and deletes it. At this point, the list is updated to the string field with improved accuracy for each image.

[0047] The first concatenation unit is used to concatenate strings in the updated list after removing duplicates from the beginning and end, resulting in a concatenated result. The first concatenation unit performs this deduplication as follows: it calculates the similarity between two strings using edit distance, then designs a function that uses a for loop to iteratively compare the local similarity of the two strings from the beginning and end. If the local similarity is greater than a set threshold, the first string is concatenated with the second string (after removing its local similarity component), achieving deduplication. In this embodiment, the similarity threshold is set to 0.7; and the starting position for concatenation is the string after the last empty character in the same list that is not empty at either end.

[0048] The results output module is used to match the concatenated result with the string format in the candidate set document, select the string with a matching degree that reaches the set threshold as the final recognition result, otherwise use the concatenated result as the final result.

[0049] The functions of the above modules correspond one-to-one with the steps in the terminal 3D ring character recognition method in Embodiment 1. Any parts not described in detail will not be repeated.

[0050] Example 3 Based on the same inventive concept, embodiments of the present invention also provide a terminal identification device based on OCR technology, comprising: Memory, used to store computer programs; A processor is used to execute the computer program to implement the steps of a terminal 3D ring character recognition method based on OCR technology as described in Embodiment 1 above.

[0051] Preferably, the computer program can be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the device.

[0052] The processor can be a central processing unit, or other general-purpose processors, digital signal processors, application-specific integrated circuits, off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor, or the processor can be any conventional processor. The processor is the control center of the device and connects the various parts of the device using various interfaces and lines.

[0053] The memory mainly includes a program storage area and a data storage area. The program storage area can store the operating system, applications required for at least one function, etc., while the data storage area can store related data, etc. In addition, the memory can be a high-speed random access memory, or a non-volatile memory, such as a plug-in hard disk, a smart memory card, a secure digital card, and a flash memory card, or the memory can be other volatile solid-state storage devices.

[0054] Example 4 Based on the same inventive concept, this embodiment of the invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the terminal 3D ring character recognition method based on OCR technology as described in Embodiment 1 above.

[0055] Computer storage media can be tangible media that may contain or store programs for use by or in conjunction with an instruction execution system, apparatus or device.

Claims

1. A terminal 3D ring character recognition method based on OCR technology, characterized in that, Includes the following steps: Step S1: Collect terminal images in a 360° surround view and store the images in string order to create a string candidate set document; Step S2: Crop the terminal area in the image to obtain the corresponding terminal image set; Step S3: Enhance image contrast and perform OCR recognition on each of the sequentially arranged terminal images; Step S4: Store the multiple recognition results in multiple lists, and concatenate the first and last strings in each list to remove duplicates, ultimately obtaining one or more complete strings; including: Step S401: Obtain the y-coordinates of multiple string positions identified from multiple images; Step S402: Compare the y-coordinates of multiple strings in multiple images, add strings that are greater than a set threshold to the same list, and store the others in another list; Step S403: For multiple strings in the same list, determine the left and right x coordinates of each string text box, and determine whether to delete the first and last characters based on the left and right x coordinate values. Step S404: Update the list according to the result of step S403, and concatenate the strings in the same list after removing duplicates from the beginning and end to obtain the concatenated result; Step S5: Match the concatenated result with the preset string format in the candidate set document, select the string with a matching degree that reaches the set threshold as the final recognition result, otherwise use the concatenated result as the final result.

2. The terminal 3D ring character recognition method based on OCR technology as described in claim 1, characterized in that, When performing OCR recognition on sequentially arranged images, the images are divided into two categories: one is images that have been cropped and then contrast-enhanced, and the other is images that have been directly enhanced without cropping. OCR recognition is performed on the two categories of images separately, and the result with the higher recognition rate between the two categories is returned as the recognition result.

3. The terminal 3D ring character recognition method based on OCR technology as described in claim 1, characterized in that, The method for concatenating strings from the same list after removing duplicates is as follows: calculate the similarity between two strings using edit distance, and then design a function to use a for loop to iterate and compare the local similarity of the two strings from the beginning and end respectively. If the local similarity is greater than a set threshold, then concatenate the first string with the second string after removing the local part.

4. A terminal 3D ring character recognition method based on OCR technology as described in claim 1 or 3, characterized in that, In step S404, the starting position for concatenation is the string following the last empty character in the same list that is not empty at either end.

5. The terminal 3D ring character recognition method based on OCR technology as described in claim 1, characterized in that, In step S403, strings in the same list are represented as multiple segments of the same complete string. It is determined whether the left x coordinate of each string in the list is 0. If it is 0, it is considered that the first character in the string is not accurately identified and is deleted. It is also determined whether the right x coordinate of each string in the list is equal to the width of the image in which the string is located. If it is equal, it is considered that the last character in the string is not accurately identified and is deleted.

6. A terminal 3D circular character recognition device based on OCR technology, characterized in that, include: Image acquisition module for 360° surround acquisition of terminal images; The image storage module is used to store the acquired terminal images in string order and create a string candidate set document; The image cropping module crops the terminal area in the image to obtain the corresponding terminal image set; The image processing module is used to enhance image contrast and perform OCR recognition on each of the sequentially arranged terminal images. The concatenation and deduplication module is used to store multiple recognition results in multiple lists, concatenate the beginning and end of the strings in each list to remove duplicates, and finally obtain one or more complete strings; The results output module is used to match the concatenated result with the string format in the candidate set document, select the string with a matching degree that reaches a set threshold as the final recognition result, otherwise use the concatenated result as the final result; The splicing and deduplication module includes: The first recognition unit is used to obtain the y-coordinates of multiple string positions in multiple images for recognition; The first data processing unit is used to compare the y-coordinates of multiple strings in multiple images, add strings that are greater than a set threshold to the same list, and store the others in another list. The second data processing unit is used to determine the left and right x coordinates of each string text box for multiple strings in the same list, and to determine whether to delete the first and last characters based on the left and right x coordinate values. The first concatenation unit is used to update the list according to the processing result of the second data processing unit, and to concatenate the strings in the same list after removing duplicates from the beginning and end to obtain the concatenated result.

7. A terminal 3D circular character recognition device based on OCR technology, characterized in that, include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the steps of the terminal 3D ring character recognition method based on OCR technology as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the terminal 3D ring character recognition method based on OCR technology as described in any one of claims 1 to 5.

Images