Handwriting system and handwriting recognition method

Abstract

The embodiment of the invention provides a handwriting system and a handwriting recognition method. The handwriting system comprises a writing surface, a handwriting pen and an electronic device, the writing surface comprises at least one optical identification code, and each optical identification code corresponds to one coordinate; the handwriting pen is used for determining a written target content according to a plurality of target optical identification codes passed by a user when the user uses the handwriting pen to write on the writing surface; the electronic device comprises a display screen, and the display screen is used for displaying the target content. According to the scheme, the writing track when the user writes the characters can be identified through the optical identification code on the writing surface, and the writing track can assist in identifying the written characters, so that the accuracy of handwriting identification is improved.

Description

Technical Field

[0001] The present application relates to the field of image recognition technology, and in particular to a handwriting system and a handwriting recognition method. Background Art

[0002] In electronic handwriting application scenarios, users write text through electronic devices, and the electronic devices can automatically recognize the corresponding content of the text written by the users and store the corresponding content, thereby improving the users' work or life efficiency.

[0003] In the related art, a text recognition module is predetermined, and the text written by the user is used as input to the text recognition module, which then outputs a recognition result.

[0004] However, each user has different writing habits, and different users may write the same character differently, which may lead to inaccurate recognition results of the character recognition module. Summary of the Invention

[0005] The embodiments of the present application provide a handwriting system and a handwriting recognition method to improve the accuracy of text recognition.

[0006] In a first aspect, an embodiment of the present application provides a handwriting system comprising: a writing surface, a stylus, and an electronic device, wherein the writing surface comprises at least one optical identification code, wherein each optical identification code corresponds to a coordinate; the stylus is used to determine the target content of the writing based on multiple target optical identification codes passed by the user when writing on the writing surface using the stylus; the electronic device comprises a display screen, and the display screen is used to display the target content.

[0007] In a possible implementation, the stylus includes a refill and an optical sensor, wherein the refill is used to write the target content on the writing surface; and the optical sensor is used to read the target optical identification code when the user is writing.

[0008] In one possible embodiment, the stylus also includes a first processor, wherein the first processor is used to identify and process the multiple target optical identification codes to obtain the multiple target coordinates corresponding to the multiple target optical identification codes; the first processor is used to determine the target order of the stylus passing through the multiple target optical identification codes; the first processor is used to determine a first trajectory of the target content based on the multiple target coordinates; and the first processor is used to generate the digitized text based on the first trajectory and the target order.

[0009] In a possible implementation, the first processor is configured to determine a plurality of stroke start and end coordinates from the plurality of target coordinates; and the first processor is configured to generate the digitized text according to the first trajectory and the plurality of stroke start and end coordinates.

[0010] In a possible implementation, the stylus further includes a communication module, wherein the communication module is configured to send the target content to the electronic device.

[0011] In a second aspect, an embodiment of the present application provides a handwriting system, comprising: a stylus and an electronic screen, the stylus comprising an optical sensor, wherein the display surface of the electronic screen comprises at least one optical identification code, and the electronic screen is used to display target content written by a user on the display surface, wherein each optical identification code corresponds to a coordinate; the stylus is used to determine the target content of the writing based on multiple target optical identification codes passed by the user when writing on the electronic screen using the stylus; and the optical sensor is used to read the optical identification code when the user is writing.

[0012] In one possible embodiment, the stylus also includes a first processor, wherein the first processor is used to identify and process the multiple target optical identification codes to obtain the multiple target coordinates corresponding to the multiple target optical identification codes; the first processor is used to determine the target order of the stylus passing through the multiple target optical identification codes; the first processor is used to determine a first trajectory of the target content based on the multiple target coordinates; and the first processor is used to generate the digitized text based on the first trajectory and the target order.

[0013] In a possible implementation, the first processor is configured to determine a plurality of stroke start and end coordinates from the plurality of target coordinates; and the first processor is configured to generate the digitized text according to the first trajectory and the plurality of stroke start and end coordinates.

[0014] In a possible implementation, the stylus further includes a communication module, wherein the communication module is used to send the target content to the electronic screen.

[0015] In a third aspect, an embodiment of the present application provides a handwriting recognition method, comprising: when a user writes with a stylus, reading multiple target optical identification codes on the writing surface through the optical sensor of the stylus; converting the multiple target optical identification codes into multiple target coordinates; determining a target order for reading the multiple target optical identification codes; and generating digitized text and target content written by the user based on the multiple target coordinates and the target order.

[0016] In one possible implementation, generating a digitized text written by a user based on the multiple target coordinates and the target order includes: determining a first trajectory of the target content based on the multiple target coordinates; and generating the digitized text based on the first trajectory and the order of the multiple target coordinates.

[0017] In one possible implementation, generating the digitized text according to the first trajectory and the order of the multiple target coordinates includes: extracting multiple stroke start and end coordinates from the multiple target coordinates; and generating the digitized text according to the first trajectory and the multiple stroke start and end coordinates.

[0018] In a possible implementation, the method further includes: performing verification processing on the digitized text to obtain a verification result, wherein the verification result is verification passed or verification failed; if the verification result is verification passed, outputting the digitized text.

[0019] In a possible implementation, the verification process includes: performing verification processing on the digitized text by comparing the target stroke sequence with a standard stroke sequence.

[0020] In a possible implementation, the verification process includes: verifying the digitized text by comparing the start and end coordinates of each stroke of the trajectory with the relative coordinates of the start and end points of the standard strokes.

[0021] In a possible implementation, the verification process includes: verifying the digitized text by comparing the start and end coordinates of strokes of different trajectories with the relative coordinates of the start and end points of standard strokes.

[0022] In a fourth aspect, an embodiment of the present application provides a handwriting recognition device, comprising: a reading module for reading a plurality of target optical recognition codes on a writing surface through an optical sensor of a stylus when a user writes with a stylus; a conversion module for converting the plurality of target optical recognition codes into a plurality of target coordinates; a determination module for determining a target order for reading the plurality of target optical recognition codes; and a generation module for generating digitized text and target content written by the user based on the plurality of target coordinates and the target order.

[0023] In a possible implementation, the generation module is specifically configured to determine a first trajectory of the target content according to the multiple target coordinates; and the generation module is specifically configured to generate the digitized text according to the first trajectory and the order of the multiple target coordinates.

[0024] In a possible implementation, the generation module is specifically used to extract multiple stroke start and end coordinates from the multiple target coordinates; the generation module is also specifically used to generate the digitized text based on the first trajectory and the multiple stroke start and end coordinates.

[0025] In one possible implementation, the device further includes: a verification module for performing verification processing on the digitized text to obtain a verification result, wherein the verification result is verification passed or verification failed; the verification module is further configured to output the digitized text if the verification result is verification passed.

[0026] In a possible implementation, the verification module is specifically configured to verify the digitized text by comparing the target stroke sequence with a standard stroke sequence.

[0027] In a possible implementation, the verification module is specifically configured to verify the digitized text by comparing the start and end coordinates of each stroke trajectory with the relative coordinates of the start and end points of a standard stroke.

[0028] In a possible implementation, the verification module is specifically configured to verify the digitized text by comparing the start and end coordinates of strokes of different trajectories with the relative coordinates of the start and end points of standard strokes.

[0029] In a fifth aspect, an embodiment of the present application provides a handwriting recognition device, comprising: a memory, a processor; the memory executes instructions; the processor executes the calculator execution instructions stored in the memory, so that the processor executes the third aspect above and / or various possible implementations of the third aspect.

[0030] In a sixth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer execution instructions are stored. When the computer execution instructions are executed by a processor, they are used to implement the third aspect above and / or various possible implementation methods of the third aspect.

[0031] In a seventh aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above third aspect and / or various possible implementation methods of the third aspect.

[0032] The handwriting system and handwriting recognition method provided by the embodiments of the present application include: a writing surface, a stylus, and an electronic device. The writing surface includes at least one optical recognition code, each of which corresponds to a coordinate. The stylus is configured to determine the target content of the writing based on multiple target optical recognition codes that the user passes through when writing on the writing surface. The electronic device includes a display screen configured to display the target content. In this solution, the optical recognition codes on the writing surface can be used to identify the user's writing trajectory. The writing trajectory can assist in the recognition of the written text, thereby improving the accuracy of handwriting recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0034] Figure 1 A schematic diagram of an application scenario of a handwriting system provided in an embodiment of the present application;

[0035] Figure 2 A schematic diagram of a handwriting system provided in an embodiment of the present application;

[0036] Figure 3 A schematic diagram of the target sequence provided in the embodiment of the present application;

[0037] Figure 4 A schematic diagram of the target sequence provided in the embodiment of the present application;

[0038] Figure 5 A schematic diagram of the structure of a stylus provided in an embodiment of the present application;

[0039] Figure 6 A schematic diagram of a handwriting system provided in an embodiment of the present application;

[0040] Figure 7 A flowchart of a handwriting recognition method provided in an embodiment of the present application;

[0041] Figure 8 A schematic diagram of the stroke start and end coordinates provided in an embodiment of the present application;

[0042] Figure 9 A schematic diagram of the structure of a handwriting recognition device provided in an embodiment of the present application;

[0043] Figure 10 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0044] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0045] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0046] It should be noted that the handwriting system and handwriting recognition method of the present application can be used in the field of image recognition, and can also be used in any field other than image recognition. The application field of the handwriting system and handwriting recognition method of the present application is not limited.

[0047] Figure 1 This is a schematic diagram of an application scenario for a handwriting system provided in an embodiment of the present application. For example, the illustrated scenario illustrates a user writing handwritten text on an electronic device. The handwritten text appears as an image to the electronic device. When the user needs to enter the handwritten text into the electronic device, the electronic device recognizes the handwritten text, obtains the text content corresponding to the handwritten text, and then enters the text content.

[0048] In conjunction with the scenario example, for an electronic device, the handwritten text written by the user is just an image containing text. To obtain the specific text content corresponding to the handwritten text, the handwritten text needs to be recognized.

[0049] In the related art, a default text recognition module is used to recognize handwritten text to determine the specific text content corresponding to the handwritten text. After the text content is determined, the text content can be entered into the electronic device.

[0050] However, each user has different writing habits, and different users may write the same character differently. While the character recognition module has a certain degree of recognition accuracy, the character recognition module may recognize different text content for the same character written by different users, affecting user experience.

[0051] The handwriting system and handwriting recognition method provided in this application are intended to solve the above technical problems in the prior art.

[0052] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0053] Figure 2 This is a schematic diagram of a handwriting system provided in an embodiment of the present application. The handwriting system includes a writing surface, a stylus, and an electronic device, wherein:

[0054] The writing surface includes at least one optical identification code, wherein each optical identification code corresponds to a coordinate;

[0055] The stylus is used to determine the target content of the writing based on multiple target optical recognition codes that the user passes through when writing on the writing surface with the stylus;

[0056] The electronic device includes a display screen, and the display screen is used to display target content.

[0057] For example, optical identification (OID) technology is a technology that reads and analyzes optical identification codes optically. Optical identification codes exist in the form of specific patterns or dot matrices. Optical identification codes can be captured by optical sensors (such as cameras or scanners) and decoded into digital information. The use process of optical identifiers may include: an encoding stage, encoding digital information into a dot pattern of an optical identification code, and then connecting the optical identification code with specific information such as coordinates, identification information, or audio and video information through software. A printing stage, printing the graphic or dot matrix on paper, card or other surfaces. A decoding stage, using an optical sensor to read the printed graphic or dot matrix and restore it to digital information.

[0058] For example, the digital information may be coordinates, identification information, or text information.

[0059] Optionally, in this application, the coordinates are coordinates relative to the writing surface.

[0060] Specifically, a coordinate system is established on the writing surface, and for multiple positions on the writing surface, the relative coordinates of each position on the writing surface are determined. According to the position corresponding to each optical identification code on the writing surface, the relative coordinates corresponding to each optical identification code are determined. According to the relative coordinates corresponding to each optical identification code, digital information corresponding to each optical identification code is generated.

[0061] Optionally, the type of the writing surface includes but is not limited to at least one of the following: paper, a touchpad, a handwriting tablet, a touch screen, or a plastic surface.

[0062] For example, the stylus includes a recognition function. While the user is writing on the writing surface with the stylus, the target optical recognition code recognizes the optical recognition code that the stylus passes through, obtaining the coordinates corresponding to the passed optical recognition code. By connecting the passed coordinates, the user's writing path can be obtained. This path can assist in recognition, thereby improving the accuracy of the recognized target content.

[0063] Exemplarily, the target content is digital content that can be used for storage or transmission. The stylus pen transmits the target content to the electronic device, and the electronic device converts the target content into an image and displays it on a display screen.

[0064] In a feasible implementation, the stylus includes a pen core and an optical sensor, wherein:

[0065] The pen refill is used to write target content on the writing surface;

[0066] The optical sensor is used to read the target optical identification code when the user writes.

[0067] Optionally, the stylus can be a capacitive stylus or a pen that can actually write on paper. If the stylus is a capacitive stylus, the writing surface can be a touch screen, a touchpad, or a writing tablet. If the stylus is a real pen, the writing surface can be paper or a plastic surface.

[0068] Optionally, the optical sensor captures a small area on the writing surface directly in front of the stylus through a built-in camera. If there is an optical identification code in the small area, the optical identification code can be read.

[0069] Optionally, the optical sensor is equipped with a light source (for example, an infrared light source) to enhance contrast through the light source to reduce interference from ambient light, thereby improving the accuracy of the optical sensor in reading the optical identification code.

[0070] Exemplarily, the optical sensor reads a range area encompassing the location where the pen refill is written on the writing surface, so that the optical sensor reads the location close to the written location, thereby improving the accuracy of reading the target optical identification code. Furthermore, the area of ​​the small range area read by the optical sensor is less than or equal to a default value to avoid the problem of the optical sensor reading multiple optical identification codes, resulting in low recognition accuracy.

[0071] In combination with the scenario example, when the user writes, the optical sensor works simultaneously, and the optical sensor synchronously reads the target optical identification code of the writing position or the target optical identification code close to the writing position, and determines the coordinates of the writing position through the target optical identification code.

[0072] In this feasible implementation, by providing a refill and an optical sensor on the stylus, writing and reading the target optical identification code can be performed simultaneously, thereby reading the written coordinates in real time, and the accuracy of text recognition can be improved based on the real-time read coordinates.

[0073] In a feasible implementation, the stylus further includes a first processor, wherein:

[0074] The first processor is used to identify and process the multiple target optical identification codes to obtain multiple target coordinates corresponding to the multiple target optical identification codes;

[0075] The first processor is used to determine a target order in which the stylus passes through a plurality of target optical identification codes;

[0076] The first processor is used to determine a first trajectory of the target content according to the multiple target coordinates;

[0077] The first processor is used to generate digitized text according to the first trajectory and the target sequence.

[0078] Exemplarily, each optical identification code has encoded coordinates corresponding to the optical identification code, and the first processor obtains the corresponding coordinates from the optical identification code.

[0079] Exemplarily, multiple target coordinates are connected by a line to obtain a first track, and the first track identifies the track written by the user.

[0080] Combined with the scenario example, some characters have similar shapes but different strokes. The target order represents the order of connecting the target optical recognition codes, which can reflect the written strokes, thereby distinguishing similar characters through the target order.

[0081] Next, combine Figure 3 Describe the target sequence.

[0082] Figure 3 This is a schematic diagram of the target sequence provided in the embodiment of the present application. Figure 3 As shown, the shapes of characters A and B are similar. The first trajectories obtained by connecting characters A and B to the target coordinates are similar, and the problem of low accuracy exists in the second trajectory identifier alone. However, when characters A and B are written, the order of the second strokes is different. For example, the trajectories corresponding to the second strokes of characters A and B are both connected to optical recognition code A and optical recognition code B, where the order of the second stroke of character A is optical recognition code A to optical recognition code B, and the order of the second stroke of character B is optical recognition code B to optical recognition code A. There is a clear difference in the order of the strokes, so characters A and B can be accurately distinguished by the target order.

[0083] In this feasible implementation, by combining the first trajectory and the target sequence, the digitized text can be comprehensively recognized in multiple dimensions including the shape and strokes of the target content, thereby improving recognition accuracy.

[0084] In a feasible implementation, the first processor is configured to determine a plurality of stroke start and end coordinates from a plurality of target coordinates;

[0085] The first processor is used to generate digitized text according to the first trajectory and a plurality of stroke start and end coordinates.

[0086] For example, the target content may include multiple strokes. When writing the target content, the user needs to lift the pen and start writing again between different strokes. The coordinates corresponding to the position where the pen is put down are the starting coordinates of the stroke, and the coordinates corresponding to the position where the pen is lifted are the ending coordinates of the stroke.

[0087] Combined with the scene example, refer to Figure 3 Characters 1 and 2 are similar. The starting coordinates of the second stroke of character 1 correspond to the coordinates corresponding to optical recognition code A, and the starting coordinates of the second stroke of character 2 correspond to the coordinates corresponding to optical recognition code B. It can be seen that the starting and ending positions of similar characters are significantly different. Similar characters can be accurately identified by using the starting and ending coordinates.

[0088] Next, combine Figure 4 Describe the target sequence.

[0089] Figure 4 This is a schematic diagram of the target sequence provided in the embodiment of the present application. Figure 4 As shown, for example, character 1 and character 2 have the same number of strokes and a similar stroke order. When character 1 becomes character 3 due to the user's writing habits or problems with the electronic device, confusion is likely to occur, and the handwritten text cannot be correctly identified as character 1 or character 2. Alternatively, when recognizing handwritten text and outputting digitized text and target content, the distance between the coordinates of the starting point and / or end point of the stroke coordinates, as indicated by the arrows, can be used to correctly determine that the handwritten text is character 1.

[0090] In this feasible implementation, by combining the first trajectory and the stroke start and end coordinates, the digitized text can be comprehensively recognized based on the shape of the target content and multiple dimensions of the strokes, thereby improving recognition accuracy.

[0091] In a feasible implementation, the stylus further includes a communication module, wherein:

[0092] The communication module is used to send target content to the electronic device.

[0093] Optionally, the communication module sends the target content to the electronic device via wireless communication. It is understood that wireless communication does not require additional cables or complicated setup procedures compared to wired communication, which can improve the convenience of communication and thus enhance the user experience.

[0094] Optionally, the target content is stored in a local storage of the stylus pen, and when the stylus pen is connected to the electronic device, the target content is sent to the electronic device.

[0095] Exemplarily, the electronic device includes a communication module, and the communication module of the stylus pen establishes a communication connection with the communication module of the electronic device, so that the stylus pen can send target content to the electronic device.

[0096] refer to Figure 5 , Figure 5 This is a schematic diagram of the structure of the stylus provided in this application. Figure 5 As shown, the stylus includes an optical sensor, a refill, a first processor, and a communication module. The refill is used for writing, the optical sensor is used to read an optical identification code, the first processor is used to identify the optical identification code, and the communication module is used for the stylus to communicate with other devices.

[0097] In this feasible implementation, the target content is transmitted through the communication module, and the user does not need to copy the content stored in the stylus pen to the electronic device, which can achieve real-time transmission, thereby improving the transmission efficiency of the target content.

[0098] Figure 6 This is a schematic diagram of a handwriting system provided in an embodiment of the present application. The handwriting system includes a stylus and an electronic screen. The stylus includes an optical sensor, wherein:

[0099] The display surface of the electronic screen includes at least one optical identification code, and the electronic screen is used to display target content written by the user on the display surface, wherein each optical identification code corresponds to a coordinate;

[0100] The stylus is used to determine the target content of the writing based on multiple target optical recognition codes that the user passes through when writing on the electronic screen with the stylus;

[0101] The optical sensor is used to read the optical identification code as the user writes.

[0102] For example, the display surface of the electronic screen not only displays the target content, but also stores the default coordinates through the optical identification code. The target content is the content written by the user.

[0103] For example, an optical recognition code on the display surface is read by an optical sensor, and the stylus is used to identify the read optical recognition code to obtain corresponding coordinates, which are used to assist in identifying the target content.

[0104] Optionally, the electronic screen is a capacitive screen and the stylus is a capacitive pen. The capacitive screen determines the location of the stylus's contact on the screen by detecting tiny changes in current caused by the stylus. When a user writes on the capacitive screen, the capacitive screen senses the location of the stylus tip and renders and displays smooth lines based on the sensed location. The smooth lines represent the target content.

[0105] In a feasible implementation, the stylus further includes a communication module, wherein:

[0106] The communication module is used to send target content to the electronic screen.

[0107] Exemplarily, the stylus recognizes the target content, sends the target content to the electronic screen, and the electronic screen generates a corresponding image according to the target content and displays the corresponding image.

[0108] Combined with the scenario example, the communication module recognizes the target content in real time and sends the target content to the electronic screen in real time, so that the electronic screen displays the target content in real time, thereby achieving timely feedback on the user's writing and improving the user's experience.

[0109] It should be noted that the implementation principle and beneficial effects of the stylus of this embodiment are similar to those of the above embodiment and will not be described in detail here.

[0110] Figure 7 A flow chart of a handwriting recognition method provided in an embodiment of the present application is shown as follows: Figure 7 As shown, the method includes:

[0111] S701: When a user writes with a stylus pen, the optical sensor of the stylus pen reads a plurality of target optical identification codes on the writing surface.

[0112] Exemplarily, the target optical recognition code is the optical recognition code closest to the position where the stylus is written, and the coordinates of the target optical recognition code are close to the position where the stylus is written.

[0113] For example, the optical sensor reads multiple target optical identification codes in a continuous reading manner. As the user writes, the optical sensor continuously captures the real-time writing position, thereby obtaining multiple target optical identification codes.

[0114] Optionally, operating parameters (such as the amount of illumination) are adjusted according to the real-time light conditions of the optical sensor, so that the operating parameters adapt to the real-time light conditions, thereby improving the reading accuracy of the optical sensor.

[0115] S702: Convert multiple target optical identification codes into multiple target coordinates.

[0116] For example, during the encoding phase of the optical identification code, the optical identification code is connected to the coordinates, that is, the target optical identification code and the coordinates are in a one-to-one correspondence. Based on the one-to-one correspondence, the target optical identification code can be accurately converted to the corresponding target coordinates.

[0117] S703: Determine a target order for reading multiple target optical identification codes.

[0118] Exemplarily, the multiple target optical recognition codes are read in real time when the user writes, so the target order of reading the multiple target optical recognition codes is the writing order.

[0119] In combination with a scenario example, for example, when a user writes, he first passes by the target optical recognition code with coordinates (100, 150) and then passes by the target optical recognition code with coordinates (150, 200). In the target sequence, (100, 150) is located before (150, 200).

[0120] S704: Generate the digitized text and target content written by the user according to the multiple target coordinates and target order.

[0121] For example, the recognition accuracy can be improved by combining target coordinates and target order for recognition.

[0122] For example, the digitized text can be used for storage and transmission. The target content is the content written in the handwriting of the user.

[0123] In this scenario example, digitized text can be stored locally for note-taking purposes and retrieved from the local storage when needed. The digitized text can also be sent to other devices via a communication connection, allowing them to use the digitized text. The target content is user-written content, and the target content can reflect the user's handwriting.

[0124] Based on the above implementation manner, the target coordinates of the target content written by the user can be accurately determined through the target optical recognition code, and the target content can be assisted in recognition according to the target coordinates, thereby improving the recognition accuracy.

[0125] A feasible implementation method can generate the digitized text written by the user by the following method: determining a first trajectory of the target content according to multiple target coordinates; and generating the digitized text according to the first trajectory and the order of the multiple target coordinates.

[0126] Optionally, multiple target coordinates are concatenated and smoothed using a Bresenham's line algorithm, a smoothing algorithm (including but not limited to Bezier curves or spline interpolation algorithms), or the like, to obtain a smooth first trajectory. It is understood that smoothing can improve the smoothness of the first trajectory, avoid jagged edges, and thus improve the accuracy of the first trajectory.

[0127] Optionally, the first trajectory is subjected to denoising processing to prevent noise points introduced by factors such as an uneven writing surface or ambient light interference from affecting the accuracy of the first trajectory.

[0128] For example, there are written contents with similar shapes but different writing orders, and the written contents with similar shapes can be further distinguished by the first track.

[0129] In this feasible implementation, by combining the first trajectory and the order of multiple target coordinates, the accuracy of generating digitized text can be improved.

[0130] A feasible implementation method can generate digitized text by the following method, including: extracting multiple stroke start and end coordinates from multiple target coordinates; generating digitized text according to the first trajectory and the multiple stroke start and end coordinates.

[0131] Optionally, the stroke start and end coordinates are determined based on the degree of continuity during writing. For example, when a user finishes writing a stroke, they lift the stylus and start writing the next stroke at a new location. This process involves interruptions in writing, and the stroke start and end coordinates are determined based on the interruptions in writing.

[0132] Next, combine Figure 8 Describe the start and end coordinates of the strokes.

[0133] Figure 8 This is a schematic diagram of the stroke start and end coordinates provided in the embodiment of this application. Figure 8 As shown, the user's written content passes through multiple target optical recognition codes, and the corresponding coordinates are determined based on the multiple target optical recognition codes. The user first writes at coordinate A. When they reach coordinate B, they lift the stylus and start writing again at coordinate C. When they reach coordinate D for the first time, they lift the stylus and start writing again at coordinate E. Therefore, the coordinates of the stroke starting point include coordinates A, C, and E, and the coordinates of the stroke ending point include coordinates B, D, and F.

[0134] Combined with the scenario example, the starting and ending points and relative positions of multiple strokes, as well as the writing order and direction of each stroke can be accurately distinguished to assist in the recognition of digitized text.

[0135] In this feasible implementation, by combining the first trajectory and the stroke start and end coordinates, the digitized text can be comprehensively recognized based on the shape of the target content and multiple dimensions of the strokes, thereby improving recognition accuracy.

[0136] In a feasible implementation, the handwriting recognition method further includes: performing verification processing on the digitized text to obtain a verification result, the verification result being either verification passed or verification failed; if the verification result is verification passed, outputting the digitized text.

[0137] Optionally, the verification process includes but is not limited to at least one of the following: text recognition (such as classifier, neural network, etc.), stroke order check, trajectory check, etc.

[0138] Combined with the scenario example, verification processing is used to evaluate the accuracy of the recognition results. If the verification fails, it means that there is a recognition anomaly or a user writing anomaly, and the recognition result needs to be corrected.

[0139] Optionally, if the verification fails, the digitized text is annotated to remind the user that there may be anomalies in the digitized text, so that the user can discover the anomalies in time and make corrections in time.

[0140] In this feasible implementation, anomalies in the digitized text can be discovered through verification processing so that corrections can be made in a timely manner, thereby improving the accuracy of the digitized text.

[0141] A feasible implementation method may be to perform verification processing by the following method: verifying the digitized text by comparing the target stroke sequence with the standard stroke sequence.

[0142] Illustratively, the standard stroke order is the correct stroke order for writing text, and the standard stroke order may be established by a standard or specification.

[0143] Optionally, the standard stroke sequence is pre-stored in local storage.

[0144] Combined with the scenario example, when performing verification processing, the target sequence is compared with the standard stroke sequence in local storage. If they are consistent, the verification passes; if they are inconsistent, the verification fails.

[0145] In this feasible implementation, by comparing the standard stroke sequence, recognition errors can be reduced, thereby improving the accuracy of digitized text.

[0146] A feasible implementation method may be to perform verification processing by the following method: verifying the digitized text by comparing the starting and ending coordinates of each stroke trajectory with the relative coordinates of the starting and ending points of the standard strokes.

[0147] Exemplarily, the relative coordinates of the standard stroke start and end points are determined based on the relative positions of the correct stroke start and end points of the written text, and the correct stroke start and end points may be established by a standard or specification.

[0148] Optionally, the relative coordinates of the starting and ending points of the standard strokes are pre-stored in local storage.

[0149] Combined with the scenario example, when performing verification processing, the start and end coordinates of each stroke of the trajectory are compared with the relative coordinates of the standard stroke start and end points in the local storage. If they are consistent, the verification is passed; if they are inconsistent, the verification fails.

[0150] In this feasible implementation, by comparing the relative coordinates of the starting and ending points of standard strokes, recognition errors can be reduced, thereby improving the accuracy of digitized text.

[0151] A feasible implementation method may be to perform verification processing by the following method: verifying the digitized text by comparing the starting and ending coordinates of the strokes of different trajectories with the relative coordinates of the starting and ending points of the standard strokes.

[0152] Exemplarily, the start and end coordinates of the strokes of different trajectories are the start and end coordinates of different strokes, which can reflect the positional relationship between the different strokes.

[0153] Combined with the scene example, refer to Figure 8 The target content includes three trajectories, namely, the trajectory from coordinate A to coordinate B, the trajectory from coordinate C to coordinate D, and the trajectory from coordinate E to coordinate F. Comparing the start and end coordinates of the strokes of different trajectories can include comparing whether the relative position between coordinates B and coordinates C is consistent with the relative coordinates of the start and end points of the standard stroke, and comparing whether the relative position between coordinates D and coordinates E is consistent with the relative coordinates of the start and end points of the standard stroke, so as to verify whether the relative positions between different strokes are correct.

[0154] In this feasible implementation, by comparing the relative coordinates of the starting and ending points of standard strokes, recognition errors can be reduced, thereby improving the accuracy of digitized text.

[0155] Figure 9 This is a schematic diagram of the structure of a handwriting recognition device provided in an embodiment of the present application. Figure 9 As shown, the handwriting recognition device 90 may include: a reading module 91, a conversion module 92, a determination module 93, a generation module 94, and a verification module 95, wherein:

[0156] The reading module 91 is used to read multiple target optical identification codes on the writing surface through the optical sensor of the stylus when the user writes with the stylus;

[0157] A conversion module 92, configured to convert a plurality of target optical identification codes into a plurality of target coordinates;

[0158] A determination module 93 is used to determine a target order for reading a plurality of target optical identification codes;

[0159] The generating module 94 is used to generate the digitized text written by the user and the target content according to the multiple target coordinates and target orders.

[0160] Optionally, the reading module 91 may execute Figure 7 S701 in the embodiment.

[0161] Optionally, the conversion module 92 may execute Figure 7 S702 in the embodiment.

[0162] Optionally, the determination module 93 may execute Figure 7 S703 in the embodiment.

[0163] Optionally, the generation module 94 may execute Figure 7 S704 in the embodiment.

[0164] It should be noted that the handwriting recognition device shown in the embodiment of the present application can execute the technical solution shown in the above method embodiment, and its implementation principles and beneficial effects are similar, which will not be repeated here.

[0165] In a possible implementation, the generating module 94 is specifically configured to:

[0166] determining a first trajectory of the target content according to the plurality of target coordinates;

[0167] A digitized text is generated according to the first trajectory and the sequence of the plurality of target coordinates.

[0168] In a possible implementation, the generating module 94 is specifically configured to:

[0169] Extracting multiple stroke start and end coordinates from multiple target coordinates;

[0170] A digitized text is generated according to the first trajectory and the plurality of stroke start and end coordinates.

[0171] The verification module 95 is used to:

[0172] Verify the digitized text to obtain a verification result, which is either a pass or a fail.

[0173] If the verification result is passed, the digitized text is output.

[0174] In a possible implementation, the verification module 95 is specifically configured to:

[0175] The digitized text is verified by comparing the target stroke sequence with the standard stroke sequence.

[0176] In a possible implementation, the verification module 95 is specifically configured to:

[0177] The digitized text is verified by comparing the stroke start and end coordinates of each trajectory with the relative coordinates of the standard stroke start and end points.

[0178] In a possible implementation, the verification module 95 is specifically configured to:

[0179] The digitized text is verified by comparing the starting and ending coordinates of the strokes of different trajectories with the relative coordinates of the starting and ending points of the standard strokes.

[0180] Figure 10 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application, such as Figure 10 As shown, the electronic device includes:

[0181] The electronic device includes a processor 291 and memory 292. It may also include a communication interface 293 and a bus 294. The processor 291, memory 292, and communication interface 293 can communicate with each other via bus 294. Communication interface 293 can be used for information transmission. The processor 291 can invoke logic instructions stored in memory 292 to execute the method of the above embodiment.

[0182] In addition, the logic instructions in the memory 292 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product.

[0183] Memory 292, as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as program instructions / modules corresponding to the methods in the embodiments of the present application. Processor 291 executes the software programs, instructions, and modules stored in memory 292 to execute functional applications and data processing, thereby implementing the methods in the above-mentioned method embodiments.

[0184] Memory 292 may include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function, while the data storage area may store data generated based on the use of the terminal device. Memory 292 may also include high-speed random access memory and non-volatile memory.

[0185] An embodiment of the present application provides a non-transitory computer-readable storage medium, in which computer execution instructions are stored. When the computer execution instructions are executed by a processor, they are used to implement the method of the aforementioned embodiment.

[0186] An embodiment of the present application provides a computer program product, including a computer program, which implements the method of the aforementioned embodiment when executed by a processor.

[0187] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all optional embodiments, and the actions and modules involved are not necessarily required by this application.

[0188] It should be further noted that, although the various steps in the flowchart are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps may be performed in other orders. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily performed at the same time, but may be performed at different times. The execution order of these sub-steps or stages is not necessarily to be performed in sequence, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0189] It should be understood that the above-described device embodiments are merely illustrative, and the device of the present application may also be implemented in other ways. For example, the division of units / modules in the above-described embodiments is merely a logical functional division, and actual implementations may employ other division methods. For example, multiple units, modules, or components may be combined or integrated into another system, or some features may be omitted or not implemented.

[0190] In addition, unless otherwise specified, the functional units / modules in the various embodiments of the present application may be integrated into a single unit / module, each unit / module may exist physically separately, or two or more units / modules may be integrated together. The aforementioned integrated units / modules may be implemented in the form of hardware or software program modules.

[0191] If the integrated units / modules are implemented in hardware, the hardware can be digital circuits, analog circuits, etc. The physical implementation of the hardware structure includes, but is not limited to, transistors and memristors. The processor can be any appropriate hardware processor, such as a CPU, GPU, FPGA, DSP, and ASIC. The storage unit can be any appropriate magnetic storage medium or magneto-optical storage medium, such as resistive random access memory (RRAM), dynamic random access memory (DRAM), static random access memory (SRAM), enhanced dynamic random access memory (EDRAM), high-bandwidth memory (HBM), and hybrid memory cube (HMC).

[0192] If the integrated unit / module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes various media that can store program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), mobile hard drives, magnetic disks, or optical disks.

[0193] In the above embodiments, the description of each embodiment has its own emphasis. For parts not described in detail in a particular embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined in any way. To keep the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0194] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of the present application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0195] It should be understood that the present application is not limited to the exact structure described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A handwriting system, characterized in that: Comprising: a writing surface, a stylus, and an electronic device, wherein: The writing surface includes at least one optical identification code, wherein each optical identification code corresponds to a coordinate; The stylus is used to determine the target content of the writing based on multiple target optical recognition codes that the user passes through when writing on the writing surface with the stylus; The electronic device includes a display screen, and the display screen is used to display the target content.

2. The system according to claim 1, wherein: The stylus includes a pen core and an optical sensor, wherein: The pen core is used to write the target content on the writing surface; The optical sensor is used to read the target optical identification code when the user writes.

3. The system according to claim 1, wherein: The stylus further includes a first processor, wherein: The first processor is configured to perform recognition processing on the multiple target optical identification codes to obtain the multiple target coordinates corresponding to the multiple target optical identification codes; The first processor is configured to determine a target order in which the stylus passes through the plurality of target optical identification codes; The first processor is configured to determine a first trajectory of the target content according to the multiple target coordinates; The first processor is configured to generate digitized text according to the first trajectory and the target sequence.

4. The system according to claim 3, characterized in that The first processor is used to determine a plurality of stroke start and end coordinates from the plurality of target coordinates; The first processor is configured to generate the digitized text according to the first trajectory and the plurality of stroke start and end coordinates.

5. The system according to claim 1, wherein: The stylus also includes a communication module, wherein: The communication module is used to send the target content to the electronic device.

6. A handwriting system, characterized in that: include: A stylus and an electronic screen, wherein the stylus includes an optical sensor, wherein The display surface of the electronic screen includes at least one optical identification code, and the electronic screen is used to display target content written by a user on the display surface, wherein each optical identification code corresponds to a coordinate; The stylus is used to determine the target content of the writing according to a plurality of target optical recognition codes passed by the user when writing on the electronic screen with the stylus; The optical sensor is used to read the optical identification code when the user writes.

7. The system according to claim 6, characterized in that The stylus further includes a first processor, wherein: The first processor is configured to perform recognition processing on the multiple target optical identification codes to obtain the multiple target coordinates corresponding to the multiple target optical identification codes; The first processor is configured to determine a target order in which the stylus passes through the plurality of target optical identification codes; The first processor is configured to determine a first trajectory of the target content according to the multiple target coordinates; The first processor is configured to generate digitized text according to the first trajectory and the target sequence.

8. The system according to claim 7, characterized in that The first processor is used to determine a plurality of stroke start and end coordinates from the plurality of target coordinates; The first processor is configured to generate the digitized text according to the first trajectory and the plurality of stroke start and end coordinates.

9. The system according to claim 6, wherein: The stylus also includes a communication module, wherein: The communication module is used to send the target content to the electronic screen.

10. A handwriting recognition method, characterized in that: include: When the user writes with the stylus, the optical sensor of the stylus reads multiple target optical identification codes on the writing surface; converting the plurality of target optical identification codes into a plurality of target coordinates; determining a target order for reading the plurality of target optical identification codes; According to the multiple target coordinates and the target order, digitized text written by the user and target content are generated.

11. The method according to claim 10, characterized in that Generating a digitized text written by a user according to the plurality of target coordinates and the target order, comprising: determining a first trajectory of the target content according to the multiple target coordinates; The digitized text is generated according to the first trajectory and the order of the plurality of target coordinates.

12. The method according to claim 11, characterized in that Generating the digitized text according to the first trajectory and the order of the plurality of target coordinates includes: Extracting a plurality of stroke start and end coordinates from the plurality of target coordinates; The digitized text is generated according to the first trajectory and the plurality of stroke start and end coordinates.

13. The method according to any one of claims 10 to 12, characterized in that The method further comprises: Performing verification processing on the digitized text to obtain a verification result, wherein the verification result is verification passed or verification failed; If the verification result is that the verification is passed, the digitized text is output.

14. The method according to claim 13, characterized in that The verification process includes: The digitized text is verified by comparing the target stroke sequence with the standard stroke sequence.

15. The method according to claim 14, characterized in that The verification process includes: The digitized text is verified by comparing the stroke start and end coordinates of each trajectory with the relative coordinates of the standard stroke start and end points.

16. The method according to claim 13, characterized in that The verification process includes: The digitized text is verified by comparing the starting and ending coordinates of the strokes of different trajectories with the relative coordinates of the starting and ending points of the standard strokes.

Images