A method and system for determining character recognition related parameters

Abstract

An embodiment of the present specification provides a method for determining parameters related to character recognition, the method comprising obtaining preset information of the three-dimensional character, wherein the preset information of the three-dimensional character includes at least one of the line width of the three-dimensional character, the character spacing between two adjacent characters, and the line spacing between two adjacent rows of characters; and determining the resolution of a character information acquisition device used to obtain point cloud data of the three-dimensional character based on the preset information of the three-dimensional character.

Description

Technical Field

[0001] The present application relates to the field of character recognition, and in particular to a method and system for determining parameters related to character recognition. Background Art

[0002] In the industrial field, many workpieces have three-dimensional characters processed on their surfaces to represent the information of the workpieces. In modern industry, the automated operation of workpieces can be supported by identifying the three-dimensional characters on the workpieces. The recognition of three-dimensional characters on the workpieces depends on the scanning of the workpiece nameplate by the character information acquisition device. In the actual recognition process, what kind of character information acquisition device to adopt and what parameters to use during recognition often need to be set based on experience, which leads to instability in the recognition process and increased labor costs. How to automatically determine the relevant parameters for character recognition is a technical problem that needs to be solved urgently in this field. Summary of the Invention

[0003] One embodiment of this specification provides a method for determining parameters related to character recognition. The method includes: obtaining preset information for a three-dimensional character, the preset information including at least one of the following: line width, character spacing between two adjacent characters, and line spacing between two adjacent lines of characters; and, based on the preset information, determining a resolution of a character information acquisition device used to acquire point cloud data of the three-dimensional character; the resolution being used to reflect the distance between two adjacent points in the point cloud data acquired by the character information acquisition device.

[0004] In some embodiments, the method further comprises: determining a resolution of the character information acquisition device based on the line width and a smaller value of the character spacing and the line spacing.

[0005] In some embodiments, the ratio of the line width, the character spacing, or the line spacing to the resolution of the character information acquisition device ranges from 5 to 10.

[0006] In some embodiments, obtaining the preset information of the three-dimensional character includes: obtaining the preset information of the three-dimensional character through input information of a terminal device.

[0007] In some embodiments, the input information of the terminal device includes specific numerical information of preset information of the three-dimensional character or two-dimensional code information corresponding to the specific numerical information.

[0008] In some embodiments, the method further includes: determining a search radius of associated point cloud data in the point cloud data of the three-dimensional character based on the resolution of the character information acquisition device; the associated point cloud data in the point cloud data of the three-dimensional character is used to reflect the point cloud data of a single character.

[0009] In some embodiments, the method further includes: obtaining a resolution of a character information acquisition device used to obtain point cloud data of the three-dimensional character; determining a search radius for associated point cloud data in the point cloud data of the three-dimensional character based on the resolution; the associated point cloud data in the point cloud data of the three-dimensional character is used to reflect the point cloud data of a single character.

[0010] In some embodiments, the method of acquiring the resolution of a character information acquisition device for acquiring point cloud data of the three-dimensional character includes: acquiring the resolution of the character information acquisition device through input information of a terminal device.

[0011] One embodiment of this specification provides a system for determining parameters related to character recognition, the system comprising: an acquisition module for acquiring preset information for a three-dimensional character, the preset information comprising at least one of line width, character spacing between two adjacent characters, and line spacing between two adjacent lines of characters; and a resolution determination module for determining, based on the preset information, the resolution of a character information acquisition device used to acquire point cloud data of the three-dimensional character.

[0012] One of the embodiments of this specification provides a device for determining character recognition related parameters, the device including a processor and a memory; the memory is used to store instructions, and when the instructions are executed by the processor, the device implements the operations corresponding to the method for determining character recognition related parameters provided in one of the embodiments.

[0013] One embodiment of this specification provides a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the method for determining character recognition related parameters provided in one embodiment. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] This specification will be further described in the form of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, like numbers represent like structures, wherein:

[0015] Figure 1 is a schematic diagram of an application scenario of a system for determining character recognition related parameters according to some embodiments of the present application;

[0016] Figure 2 is a module diagram of a system for determining character recognition related parameters according to some embodiments of this specification;

[0017] Figure 3 is an exemplary flow chart of a method for determining character recognition related parameters according to some embodiments of the present application;

[0018] Figure 4 is an exemplary flow chart of determining a search radius based on the resolution of an information collection device according to some embodiments of the present application;

[0019] Figure 5 This is an exemplary flowchart of a method for determining preset information of a three-dimensional character according to some embodiments of the present application. DETAILED DESCRIPTION

[0020] To more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly describes the drawings required for describing the embodiments. Obviously, the drawings described below are merely examples or embodiments of this specification. Those skilled in the art can apply this specification to other similar scenarios based on these drawings without inventive effort. Unless otherwise apparent from the context or otherwise noted, the same reference numerals in the figures represent the same structure or operation.

[0021] It should be understood that the terms "system," "device," "unit," and / or "module" used herein are a method for distinguishing different components, elements, parts, portions, or assemblies at different levels. However, if other terms can achieve the same purpose, the terms may be replaced by other expressions.

[0022] As used in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not refer to the singular but also include the plural. Generally speaking, the terms "comprises" and "include" only indicate the inclusion of the steps and elements specifically identified, and these steps and elements do not constitute an exclusive list. A method or apparatus may also include other steps or elements.

[0023] Flowcharts are used throughout this specification to illustrate the operations performed by systems according to embodiments of this specification. It should be understood that preceding or following operations do not necessarily need to be performed in exact order. Instead, the steps may be processed in reverse order or simultaneously. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0024] In the field of three-dimensional character recognition, the recognition effect of characters is closely related to relevant parameters. For example, when an image acquisition device with a suitable resolution is not selected, the point cloud data of the three-dimensional characters may not be clear, which may lead to character recognition errors. In this field, the relevant parameters for three-dimensional character recognition are often set by experienced operators, which not only increases the labor cost of the recognition process, but also brings unstable factors to the recognition process. Based on this, one or more embodiments of this specification provide a method and system for determining relevant parameters for character recognition, which are used to determine the relevant parameters in the character recognition process. In some embodiments, the relevant parameters in the character recognition process may include algorithm parameters related to the character recognition process and device parameters related to character acquisition. Among them, the algorithm parameters may include relevant parameters such as the search radius for segmenting characters and the number of characters. The device parameters may include relevant parameters such as the resolution of the camera device when acquiring characters. Based on the method and system for determining character recognition related parameters provided in this application, by processing the preset information of three-dimensional characters (for example, the line width of three-dimensional characters, the character spacing between two adjacent characters, the line spacing between two adjacent rows of characters, etc.), the character recognition related parameters can be automatically determined, thereby automatically adjusting the corresponding device parameters and / or algorithm parameters, realizing the reasonable allocation of equipment and / or automatic adaptation of the algorithm, so as to improve the accuracy of the character recognition process and reduce the technical cost and labor cost of the character recognition process.

[0025] Figure 1 This is a schematic diagram of an application scenario of a system for determining character recognition related parameters according to some embodiments of the present application.

[0026] like Figure 1 The system 100 for determining character recognition related parameters may include a processing device 110 , a network 120 , a character information collection device 130 , a terminal device 140 , and a storage device 150 .

[0027] In some embodiments, the character recognition parameter determination system 100 can be combined with a 3D character recognition system to provide the 3D character recognition system with device parameters and algorithm parameters, thereby making the 3D character recognition process more accurate and reducing technical costs. In some embodiments, the 3D character recognition system used in conjunction with the character recognition parameter determination system 100 can recognize the 3D characters by capturing a 3D image of the 3D characters and then processing the image using a character recognition algorithm.

[0028] In some embodiments, the three-dimensional characters can be embossed and / or recessed characters on the surface of a workpiece. The workpiece surface can be flat or curved. The characters can be at least one of text, numbers, patterns, character strings, QR codes, barcodes, and the like, or a combination thereof. Examples include identification codes embossed on liquefied gas cylinders, inkjet codes on beverage bottles, and character strings punched or laser-machined on machined workpieces. Other examples include bank card numbers and the stamped steel on the nameplate of a motor housing. Other examples include embossed and recessed characters on metal parts, for example, embossed and recessed characters on key components of aircraft engines or automobile engines.

[0029] In some embodiments, the system 100 for determining character recognition-related parameters may involve the process of recognizing characters on a workpiece, so that production management equipment (e.g., workpiece transportation management equipment, warehouse management equipment, etc.) can manage the workpiece production. For example, the system 100 for determining character recognition-related parameters may involve recognizing three-dimensional characters imprinted on a workpiece, where the three-dimensional characters correspond to workpiece qualification information. By recognizing the workpiece qualification information corresponding to the three-dimensional characters, the system determines whether the workpiece is qualified. The warehouse management equipment can then determine whether to store the workpiece based on the determination result.

[0030] In some embodiments, the processing device 110 can be used to process information and / or data related to three-dimensional character recognition. For example, the processing device 110 can obtain preset information of a three-dimensional character from a user, wherein the preset information of the three-dimensional character can be information such as the line width or character spacing of the character. For another example, the processing device 110 can be used based on the point cloud data of the three-dimensional character obtained by the character information acquisition device 130, wherein the point cloud data is used to represent the spatial information of the three-dimensional character. In other embodiments, the processing device 110 can also be based on relevant parameters for determining character recognition, for example, the processing device 110 can determine device parameters (such as resolution) based on the point cloud data of the three-dimensional character. For another example, the processing device 110 can determine the search radius of the three-dimensional character based on the preset information of the three-dimensional character. In some embodiments, the processing device 110 can also execute a character recognition algorithm based on the determined relevant parameters for character recognition, for example, the processing device 110 can determine the corresponding two-dimensional image based on the point cloud data of the three-dimensional character, and recognize the character meaning of the three-dimensional character based on the two-dimensional image and relevant parameters.

[0031] In some embodiments, the processing device 110 may be regional or remote. For example, the processing device 110 may access information and / or data stored in the character information collection device 130 or the terminal device 140 via the network 120. In some embodiments, the processing device 110 may be directly connected to the character information collection device 130 or the terminal device 140 to access the information and / or data stored therein. For example, the processing device 110 may be located in the character information collection device 130 or directly connected to the character information collection device 130.

[0032] In some embodiments, the processing device 110 may include a processor. The processor may process data and / or information related to 3D character recognition. For example, the processor may receive a 3D character recognition request signal sent by the character information acquisition device 130 or the terminal device 140 and send a control instruction to the character information acquisition device 130. For another example, the processor may obtain an image of a 3D character captured by the character information acquisition device 130, recognize the 3D character based on its depth information, and then send the 3D character recognition result to the terminal device 140.

[0033] The network 120 can facilitate the exchange of data and / or information within the system 100 for determining parameters related to character recognition. In some embodiments, one or more components within the system 100 for determining parameters related to character recognition (e.g., the processing device 110, the character information acquisition device 130, and the terminal device 140) can transmit data and / or information to other components within the system 100 for determining parameters related to character recognition via the network 120. For example, point cloud data of a three-dimensional character acquired by the character information acquisition device 130 can be transmitted to the processing device 110 via the network 120. For another example, the recognition results of the three-dimensional character generated by the processing device 110 can be transmitted to the terminal device 140 via the network 120.

[0034] The character information acquisition device 130 is used to collect relevant information about three-dimensional characters. In some embodiments, the character information acquisition device 130 can obtain point cloud data and / or two-dimensional image depth information of the three-dimensional characters. In some embodiments, the character information acquisition device may include a camera and a light source. The light source can be used to irradiate light information onto the concave and convex characters on the workpiece, and the camera can be used to collect the light signal irradiated onto the three-dimensional characters. In some embodiments, the character information acquisition device 130 may include multiple sets of devices with different resolutions, and the processing device 110 can select the corresponding device from the character information acquisition device 130 based on the determined relevant parameters.

[0035] In some embodiments, terminal device 140 can input and / or output relevant information or data. In some embodiments, a user can obtain the results of 3D character recognition by processing device 110 through terminal device 140. For example, a user can view a 2D image corresponding to the 3D character recognized by processing device 110 through terminal device 140. In some embodiments, terminal device 140 can be a portable device with data acquisition, storage, and / or transmission functions, such as a smartphone 140-1, a tablet computer 140-2, a laptop computer 140-3, a smart camera, or any combination thereof.

[0036] In some embodiments, the terminal device 140 can be connected to the processing device 110 via the network 120 (e.g., a wired connection or a wireless connection). The user can obtain the result of the three-dimensional character recognition performed by the processing device 110 through the terminal device 140, and the result of the three-dimensional character recognition can be transmitted to the terminal device 140 via the processing device 110. In some embodiments, the user can set preset parameters for the three-dimensional character through the terminal device 140 so that the processing device 110 can determine the image acquisition parameters of the character information acquisition device 130. The image acquisition parameters of the character information acquisition device 130 may include light source color parameters, camera position parameters, camera shooting angle parameters, etc.

[0037] The storage device 150 can store data (for example, point cloud data of three-dimensional characters, character meanings corresponding to three-dimensional characters, etc.) and / or instructions (for example, instructions for identifying three-dimensional characters based on the depth information of three-dimensional characters, instructions for reconstructing the depth information of three-dimensional characters based on multiple two-dimensional images of three-dimensional characters at different angles, etc.). In some embodiments, the storage device 150 can store data obtained from the character information acquisition device 130 and / or the terminal device 140 (for example, push information about the character information acquisition device 130, image acquisition parameters, etc.). In some embodiments, the storage device 150 can store information and / or instructions for execution or use by the processing device 110 to perform the exemplary method described in this application. For example, the processing device 110 can determine the relevant parameters for recognizing characters based on the three-dimensional point cloud data of the three-dimensional characters according to the instructions stored in the storage device 150, such as the optimal resolution and the search radius, and determine the content of the three-dimensional point cloud data based on the relevant parameters.

[0038] In some embodiments, the storage device 150 can be connected to the network 120 to communicate with one or more components of the system 100 for determining parameters related to character recognition (e.g., the processing device 110, the character information acquisition device 130, the terminal device 140, etc.). One or more components of the system 100 for determining parameters related to character recognition can access data or instructions stored in the storage device 150 through the network 120. In some embodiments, the storage device 150 can be directly connected to or communicate with one or more components of the system 100 for determining parameters related to character recognition (e.g., the processing device 110, the character information acquisition device 130, the terminal device 140). In some embodiments, the storage device 150 can be part of the processing device 110. In some embodiments, the processing device 110 can be provided independently of the character information acquisition device 130. In some embodiments, the processing device 110 can also be located in the character information acquisition device 130 or the terminal device 140.

[0039] It should be noted that the above description is provided for illustrative purposes only and is not intended to limit the scope of this application. For those of ordinary skill in the art, various changes and modifications can be made under the guidance of the content of this application. The features, structures, methods and other features of the exemplary embodiments described in this application can be combined in various ways to obtain additional and / or alternative exemplary embodiments.

[0040] Figure 2 It is a module diagram of a method for determining character recognition related parameters according to some embodiments of this specification.

[0041] like Figure 2 As shown, in some embodiments, a system 200 for determining character recognition related parameters may include an acquisition module 210 and a resolution determination module 220. The system 200 for determining character recognition related parameters may implement a method for determining character recognition related parameters by executing the acquisition module 210 and the resolution determination module 220.

[0042] The acquisition module 210 can be configured to acquire preset information for a 3D character, including at least one of the following: line width, character spacing between two adjacent characters, and line spacing between two adjacent rows of characters. In some embodiments, the preset information for the 3D character can be stored in the storage device 150, and the acquisition module 210 can be implemented by reading corresponding data from the storage device 150.

[0043] In some embodiments, an operator may input preset information of a three-dimensional character through the terminal device 140. That is, the acquisition module 210 may obtain the preset information of the three-dimensional character through the input information of the terminal device. In some embodiments, the input information of the terminal device includes specific numerical information of the preset information of the three-dimensional character or QR code information corresponding to the specific numerical information.

[0044] The resolution determination module 220 can be configured to determine the resolution of a character information acquisition device used to acquire point cloud data of a three-dimensional character based on preset information about the three-dimensional character. In some embodiments, the resolution determination module 220 can determine the resolution of the character information acquisition device based on the smaller of the line width, the character spacing, and the line spacing; the resolution reflects the distance between two adjacent points in the point cloud data collected by the character information acquisition device. In some embodiments, the ratio of the line width, the character spacing, or the line spacing to the resolution of the character information acquisition device is in a range of 5 to 10.

[0045] In some embodiments, the character recognition related parameters also include a search radius in the character segmentation process. In some embodiments, the character recognition related parameter determination system 200 may further include a search radius determination module 230 .

[0046] The search radius determination module 230 can be used to determine the search radius of associated point cloud data in the point cloud data of the three-dimensional character based on the preset information of the three-dimensional character; the associated point cloud data in the point cloud data of the three-dimensional character is used to reflect the point cloud data of a single character.

[0047] In some embodiments, the search radius determination module 230 may determine a search radius for associated point cloud data in the three-dimensional character point cloud data based on the resolution of the character information acquisition device. In some embodiments, the search radius determination module 230 may obtain the resolution of the character information acquisition device used to acquire the three-dimensional character point cloud data, and then determine a search radius for associated point cloud data in the three-dimensional character point cloud data based on the resolution; the associated point cloud data in the three-dimensional character point cloud data is used to reflect the point cloud data of a single character.

[0048] It should be noted that the above description of the character segmentation system and its modules for point cloud data is for convenience only and does not limit this specification to the scope of the embodiments. It is understandable that those skilled in the art, after understanding the principles of the system, may arbitrarily combine the modules or form a subsystem connected with other modules without deviating from the principles. In some embodiments, Figure 2The modules disclosed herein may be different modules within a system, or a single module may implement the functions of two or more of the aforementioned modules. For example, the modules may share a storage module, or each module may have its own storage module. Such variations are within the scope of protection of this specification.

[0049] Figure 3 This is an exemplary flowchart of a method for determining character recognition related parameters according to some embodiments of the present application.

[0050] In some embodiments, the method 300 for determining character recognition related parameters can be executed by the system 100 for determining character recognition related parameters (such as the processing device 110) or the system 200 for determining character recognition related parameters. For example, the method 300 for determining character recognition related parameters can be stored in a storage device (such as the storage device 150) in the form of a program or instruction. When the system 100 for determining character recognition related parameters (such as the processing device 110) executes the program or instruction, the method 300 for determining character recognition related parameters can be implemented. The operational diagram of the method 300 for determining character recognition related parameters presented below is illustrative. In some embodiments, the process can be completed using one or more additional operations not described and / or one or more operations not discussed. In addition, Figure 3 The order in which the operations of flow 300 are illustrated and described below is not intended to be limiting.

[0051] Step 310 , obtaining preset information of the three-dimensional character. In some embodiments, step 310 may be implemented by the obtaining module 210 .

[0052] In some embodiments, the preset information may be information related to the representation of the three-dimensional character. In some embodiments, the preset information may include at least one of the line width of the three-dimensional character, the character spacing between two adjacent characters, and the line spacing between two adjacent lines of characters.

[0053] In some embodiments, the processing device 110 can obtain the preset information of the three-dimensional character from the input information of the terminal device. In some embodiments, the input information of the terminal device 140 includes specific numerical information of the preset information of the three-dimensional character. For example, the line width of the three-dimensional character is 3 mm. For another example, the character spacing between two adjacent characters is 5 mm. In some embodiments, the input information of the terminal device 140 can also include QR code information corresponding to the specific numerical information. For example, the terminal device 140 can determine the preset information of the three-dimensional character by identifying the QR code information of the workpiece corresponding to the three-dimensional character.

[0054] In some embodiments, an operator can measure the three-dimensional character to determine preset information of the three-dimensional character and input the information into the terminal device 140, which then sends the preset information to the processing device 110. In some embodiments, exemplary measuring devices may include a micrometer, a vernier caliper, an image measuring instrument, and the like.

[0055] In some embodiments, the data measurement device may automatically measure preset information of the three-dimensional character and automatically send the preset information to the terminal device 140 and / or the processing device 110 .

[0056] In some embodiments, considering that the relevant parameters of the three-dimensional characters on different workpieces may be different, when performing large-scale recognition, in order to improve the degree of automation and reduce manual operations, the workpiece types of different workpieces can be identified first, and then the workpiece types can determine the preset information of the three-dimensional characters to be recognized thereon, wherein the correspondence between the preset information of the three-dimensional characters and the workpiece types can be pre-stored in the storage device 150.

[0057] In some embodiments, the preset information of the three-dimensional character can be automatically determined by the high-precision character information acquisition device 130. The specific content of the preset information of the three-dimensional character can be referred to in this application. Figure 5 and its related descriptions.

[0058] Step 320 , based on the preset information of the three-dimensional character, determines the resolution of the character information acquisition device for acquiring point cloud data of the three-dimensional character. In some embodiments, step 320 may be performed by the resolution determination module 220 .

[0059] Resolution can refer to the accuracy of the three-dimensional character point cloud data acquired by the character information acquisition device and can be used to reflect the distance between two adjacent points in the point cloud data acquired by the character information acquisition device. That is, resolution can reflect the actual physical distance between the two closest point cloud data (pixels) in the three-dimensional character point cloud data acquired by the character information acquisition device and mapped to the physical object. In some embodiments, resolution can also be a parameter related to pixels, resolution rate, etc.

[0060] In some embodiments, the resolution of a character information acquisition device used to acquire point cloud data for a three-dimensional character can be determined based on preset information about the three-dimensional character. Furthermore, the resolution of the character information acquisition device used to acquire point cloud data for the three-dimensional character can be determined based on at least one of the line width of the three-dimensional character, the character spacing between two adjacent characters, or the line spacing between two adjacent lines of characters. In some embodiments, the resolution of the character information acquisition device can be determined based on the minimum of the line width, the character spacing, and the line spacing.

[0061] In some embodiments, the ratio of the line width, character spacing, or line spacing to the resolution of the character information collection device 130 may be in the range of 5 to 10. In some embodiments, the ratio of the minimum of the line width, character spacing, and line spacing to the resolution of the character information collection device 130 may be in the range of 5 to 10.

[0062] In some embodiments, the morphological information of three-dimensional characters on different types of workpieces may differ. Using the same character information acquisition device to recognize three-dimensional characters on different workpieces may affect recognition results or waste resources. For example, when using a low-resolution character information acquisition device, the point cloud data acquired by the character information acquisition device may not clearly represent the strokes and spacing of the three-dimensional characters, leading to problems such as character and stroke adhesion, which in turn affects recognition results. Assigning a high-resolution character information acquisition device to workpieces with lower requirements will result in a waste of resources and may also result in workpieces with higher requirements not having a suitable character information acquisition device, leading to recognition errors. The resolution determined in step 320 is the lowest theoretical resolution that can correspond to the three-dimensional characters of that type of workpiece. The lowest theoretical resolution may refer to the lowest resolution of the character information acquisition device 130 that can clearly represent information such as the lines and spacing of the three-dimensional characters. Therefore, character information acquisition devices can be reasonably allocated based on the lowest theoretical resolution of the three-dimensional characters to avoid the aforementioned problems.

[0063] In some embodiments, in order to improve the accuracy of character recognition, the point cloud data of the three-dimensional character can be split into point cloud data corresponding to each character, so as to perform corresponding character recognition. Splitting the point cloud data of the three-dimensional character into point cloud data corresponding to a single character can be achieved by a clustering algorithm. Specifically, one or more point cloud data can be selected from the point cloud data of the three-dimensional character as one or more initial point cloud data, and then based on the initial point cloud data and a preset search radius (i.e., a distance threshold), the associated point cloud data is determined to determine the point cloud data of a single character. For example, if the distance from the initial point cloud data is greater than the search radius, the point is not the associated point cloud data of the initial point cloud data. If the distance from the initial point cloud data is less than the search radius, the point is the associated point cloud data of the initial point cloud data. Among them, the distance between adjacent point cloud data in the associated point cloud data is less than the search radius. Finally, one or more initial point cloud data and multiple associated point cloud data are used as the point cloud data of a single character, so that the single character can be separated from the three-dimensional character.

[0064] In some embodiments, the search radius for associated point cloud data can be a distance threshold used to determine whether point cloud data is associated point cloud data. For example, if the search radius is 1 mm and the distance between initial point cloud data A and point cloud data B is 1.5 mm, that is, the distance between initial point cloud data A and point cloud data B is greater than the search radius, then point cloud data B is not associated point cloud data with initial point cloud data A. For another example, if the search radius is 1 mm and the distance between initial point cloud data A and point cloud data B is 0.5 mm, that is, the distance between initial point cloud data A and point cloud data B is less than the search radius, then point cloud data B is associated point cloud data with initial point cloud data A.

[0065] In some embodiments, in order to improve the accuracy of the search radius and thereby improve the accuracy of the character recognition process, the three-dimensional character recognition method provided in this application can also determine the search radius method based on the resolution of the character information acquisition device.

[0066] In step 330 , based on the resolution of the character information acquisition device, a search radius for associated point cloud data in the point cloud data of the three-dimensional character is determined. In some embodiments, step 330 may be performed by the search radius determination module 230 .

[0067] In some embodiments, a search radius (i.e., a distance threshold) for associated point cloud data in the point cloud data of a three-dimensional character can be determined based on the resolution of the character information acquisition device. In some embodiments, the search radius is greater than the resolution. In some embodiments, the ratio of the search radius to the resolution is in a range of 5 to 10.

[0068] In some embodiments, the search radius for the associated point cloud data can also be directly determined based on preset information about the 3D character. In some embodiments, the ratio of any one of the line width, character spacing, or line spacing of the 3D character to the search radius is in a range of 5 to 20. In some embodiments, the ratio of the minimum of the line width, character spacing, or line spacing of the 3D character to the search radius is in a range of 5 to 20.

[0069] In some embodiments, the appearance of three-dimensional characters processed on different workpieces may differ, that is, the preset information of the three-dimensional characters processed on different workpieces may be different. The determination system 100 can automatically obtain the preset information of the three-dimensional character to be recognized (for example, the line width or character spacing of the character), and automatically adjust the resolution of the character information acquisition device 130 that obtains the point cloud data of the three-dimensional character based on the obtained preset information, so that the resolution of the character information acquisition device can match the preset information of the three-dimensional character to be recognized, thereby improving the recognition accuracy of the character information acquisition device. In some embodiments, the determination system 100 can also determine the search radius of associated point cloud data in the point cloud data of the three-dimensional character based on the adjusted resolution, thereby achieving more accurate clustering of the point cloud data of a single character and improving the accuracy of character segmentation or character recognition.

[0070] In some other embodiments, the determination system 100 can also automatically adjust the search radius of the associated point cloud data in the program algorithm based on the preset information obtained, so that the search radius of the associated point cloud data can match the preset information of the three-dimensional character, thereby improving the accuracy of finding the associated point cloud data, and further improving the accuracy of character segmentation or character recognition.

[0071] In some other embodiments, the determination system 100 may also adjust the search radius of the associated point cloud data directly according to the resolution of the character information collection device 130. The resolution of the character information collection device 130 may be a default setting or determined according to preset information of the three-dimensional character.

[0072] Figure 4 This is an exemplary flow chart of determining a search radius based on the resolution of an information collection device according to some embodiments of the present application. For details of process 400, please refer to steps 410-420.

[0073] Step 410: Obtain the resolution of a character information acquisition device used to obtain point cloud data of the three-dimensional character.

[0074] In some embodiments, the processing device 110 can obtain the resolution of the character information acquisition device based on the preset information of the three-dimensional character. The resolution is used to reflect the distance between two adjacent points in the point cloud data collected by the character information acquisition device. Furthermore, the processing device 110 can obtain the resolution of the character information acquisition device 130 based on the line width or character spacing. For example, if the ratio of the character spacing to the resolution of the character information acquisition device 130 is set to 10 and the character spacing is 1 mm, the resolution of the character information acquisition device 130 can be set to 100 microns. For more description on obtaining the resolution of the character information acquisition device based on the preset information of the three-dimensional character, please refer to Figure 3 and its related descriptions.

[0075] In other embodiments, the processing device 110 may also directly obtain the resolution of the character information collection device 130 from other devices. For example, the processing device 110 may obtain the resolution of the character information collection device 130 through input information from the terminal device 140. For another example, the processing device 110 may pre-store the resolution of the character information collection device 130 in the storage device 150 of the processing device 110, and the resolution of the character information collection device 130 may be obtained through the storage device 150. For another example, the processing device 110 may directly obtain the resolution of the character information collection device 130 from the storage device 150.

[0076] Step 420 : determining a search radius for associated point cloud data in the point cloud data of the three-dimensional character based on the resolution.

[0077] In some embodiments, the processing device 110 determines a search radius for associated point cloud data in the point cloud data of the three-dimensional character based on the resolution of the character information acquisition device 130. In some embodiments, the search radius is greater than the resolution. In some embodiments, the ratio of the search radius to the resolution is in a range of 5 to 10.

[0078] Through process 400 of the present application, a search radius for associated point cloud data in the point cloud data of a three-dimensional character can be determined based on the resolution. In this case, the search radius can accurately reflect the stroke information and spacing information of the three-dimensional character, thereby making the three-dimensional character segmentation more accurate, avoiding three-dimensional character segmentation errors caused by an unreasonable search radius setting, and thus improving the accuracy of the three-dimensional character recognition process. For example, a segmentation error may include multiple three-dimensional characters being combined into a single word due to the search radius not being able to reflect the spacing information.

[0079] The present application provides a method for automatically determining preset information of a three-dimensional character. Figure 5 This is an exemplary flow chart of a method for determining preset information of a three-dimensional character according to some embodiments of the present application. For details of process 500, please refer to steps 510-540.

[0080] Step 510: Obtain point cloud data of the three-dimensional character.

[0081] In some embodiments, to rationally allocate character information acquisition devices, in step 510, a high-resolution character information acquisition device may be used to acquire point cloud data of three-dimensional characters to avoid clarity issues with the point cloud data of three-dimensional characters. The high-resolution character information acquisition device may be a character information acquisition device with a resolution higher than or much higher than that required for three-dimensional character point cloud data recognition.

[0082] In some embodiments, when executing step 510, the overall point cloud data of the workpiece surface and the three-dimensional characters located on the workpiece surface can be obtained first, and then the point cloud data of the three-dimensional characters can be extracted from the overall point cloud data. In some embodiments, after obtaining the overall point cloud data of the workpiece surface, the point cloud data of the three-dimensional characters can be determined based on the target detection algorithm. In some embodiments, the base surface point cloud data of the workpiece surface can be determined based on the overall point cloud data of the workpiece surface, and then the point cloud data outside the base surface point cloud data can be extracted from the overall point cloud data as the point cloud data of the three-dimensional characters. In some embodiments, the position of the three-dimensional character on the workpiece surface can be determined based on the relationship between the point cloud data of the three-dimensional character and the point cloud data of the workpiece surface, and the preset information of the three-dimensional character can include the position of the three-dimensional character on the workpiece surface. In some embodiments, the method for determining the character recognition related parameters provided in the present application can determine the placement position, placement angle and other information of the character information acquisition device 130 in the subsequent recognition task based on the position of the three-dimensional character on the workpiece surface.

[0083] Step 520: Determine row and column information for the 3D character based on the point cloud data of the 3D character. The row and column information may be used to represent the arrangement of characters in the 3D character. In some embodiments, the row and column information may include one or more of row arrangement direction, column arrangement direction, the number of individual characters per row, the number of individual characters per column, and the like.

[0084] In some embodiments, the method for automatically obtaining row and column information can be implemented by the following method.

[0085] First, the cluster projection of the point cloud data of the 3D character in all directions is established.

[0086] In some embodiments, before projection, a 2D image of the 3D character can be determined based on the point cloud data of the 3D character. For example, the 2D image of the 3D character can be the point cloud data of the 3D character with depth information removed. For another example, a horizontal base plane can be determined based on the curvature of the workpiece surface, and the point cloud data of the 3D character can be projected onto the horizontal base plane to obtain a 2D image of the 3D character.

[0087] In some embodiments, the cluster projection of the three-dimensional character can be performed in any direction on the two-dimensional image, using the center point of the two-dimensional image as the origin. For example, the projection direction can be set at 1°, that is, 360 projection directions are set, and the difference between adjacent projection directions is 1°. Cluster projection can be understood as translating the point cloud data along a direction perpendicular to the projection direction to form a straight line. Among them, the point cloud data of the projected three-dimensional character forms multiple clusters in the projection direction, and the point cloud data in each cluster is continuously distributed, and there are cluster gaps between clusters.

[0088] Next, a first projection direction is selected from each projection.

[0089] In some embodiments, a first projection direction can be selected based on the distribution of settlements within each settlement projection. For example, a settlement projection with a uniform distribution of settlements and equal or similar spacing between settlements can be selected as the first projection direction. Finally, the 3D point cloud data is segmented based on the first projection direction, and the segmented point cloud data is projected along a second projection direction perpendicular to the first projection direction to determine the row and column data of the 3D character.

[0090] In some embodiments, the settlement interval in the first projection direction can be used as a segmentation boundary, and the point cloud data of the three-dimensional character can be segmented along the first projection direction. In order to determine the number of rows of the three-dimensional character, the segmented three-dimensional point cloud data may contain point cloud data of multiple three-dimensional characters. At this time, the segmented point cloud data can be projected based on a second projection direction perpendicular to the first projection direction. If there is no settlement interval in the projection of the second projection direction, there is only one row or column of three-dimensional characters; if there is a uniform interval in the projection of the second projection direction, the number of characters in each row or column can be determined based on the projection interval of the second projection direction. In some embodiments, considering that three-dimensional characters are generally multi-line character strings, the first projection direction can be the row direction. In some embodiments, character recognition can be performed on the point cloud data of the three-dimensional character to determine the orientation of the character, and the first projection direction can be determined as the row direction or the column direction based on the orientation of the character.

[0091] Step 530: Segment the 3D character based on its row and column information, and determine point cloud data for each character and format information for the 3D character. The format information for the 3D character may include information related to the distribution of each character within the 3D character, such as the character width (character size), the spacing between adjacent characters, and the spacing between adjacent rows of characters. The preset information may include the format information for the 3D character.

[0092] In some embodiments, the format information of the three-dimensional characters can be determined based on the point cloud data of each character. For example, the character width of the three-dimensional characters can be determined based on the width of the point cloud data of each character; for example, the line spacing of the three-dimensional characters can be determined based on the spacing between each row of three-dimensional characters; for example, the character spacing of the three-dimensional characters can be determined based on the spacing of the point cloud data of each character.

[0093] In some embodiments, the 3D character can be projected based on row and column information, and point cloud data for each character can be determined based on the projection. During projection, the row direction can be used as the first projection direction. For specific projection methods, see the relevant content of step 520. During segmentation, the 3D character can be segmented into rows of 3D characters based on the projection interval, and the point cloud data for each row of 3D characters can then be segmented into point cloud data for each individual character.

[0094] In some embodiments, the three-dimensional characters can be segmented first and then the point cloud data of each character can be determined based on the row and column information. For example, the three-dimensional characters can be segmented into point cloud data of individual characters based on a clustering algorithm, and then the row and column positions of each character can be determined based on the row and column information and the point cloud data of the individual characters to determine the point cloud data of each character.

[0095] Step 540, determining the content information of the three-dimensional character based on the point cloud data of each character, wherein the content information of the three-dimensional character can be the internal information of each character, and the content information includes the character type of the current character, the line width of the three-dimensional character and other information, and the preset information can include the content information of the three-dimensional character.

[0096] In some embodiments, step 540 can be implemented by a recognition algorithm. In some implementations, step 540 can determine the text content of the three-dimensional character through a text recognition algorithm to determine the character type of the three-dimensional character; for example, when the text recognition result of the three-dimensional character is "A7833", the character type of the three-dimensional character can be letters and numbers. In some embodiments, step 540 can be implemented by a contour recognition algorithm. The outer contour and inner contour of the three-dimensional character can be determined by the contour recognition algorithm first, and the contour thickness can be determined based on the outer contour and / or inner contour of the three-dimensional character, and then the average contour thickness is used as the stroke width of the three-dimensional character, wherein the outer contour refers to the outer contour line of the three-dimensional character, the inner contour refers to the inner contour line of the three-dimensional character, and the contour thickness refers to the width of the line in the closed figure formed by the outer contour and / or inner contour.

[0097] In some embodiments, the preset information determined based on process 500 can be used in the recognition process of similar three-dimensional characters. For example, process 300 can be executed based on the preset information determined by process 500 to determine the resolution of the three-dimensional characters of this type, and the character information collection device 130 can be reasonably allocated based on the resolution of each three-dimensional character. In some embodiments, the preset information can be set according to actual needs, and process 500 can omit some steps based on the actual needs of the preset information. For example, when the three-dimensional characters to be recognized are all single-line character strings, the preset information may not include information such as line spacing, and process 500 does not need to perform the relevant steps of line segmentation. In some embodiments, process 500 can replace some steps manually based on actual needs. For example, the operator can manually enter the row and column data of the three-dimensional characters, and correspondingly, process 500 can omit step 520.

[0098] The beneficial effects that may be brought about by one or more embodiments disclosed in this specification include but are not limited to: (1) This application realizes the automatic configuration of parameters related to character recognition, reduces labor costs, and improves the stability of the recognition process; (2) The determination method provided by this application can determine the resolution suitable for three-dimensional characters, thereby realizing the reasonable configuration of the character information acquisition device and reducing technical costs; (3) This application also provides a method for automatically determining the preset information of three-dimensional characters, further improving the degree of automation in the three-dimensional character recognition process. It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced may be any one or a combination of the above, or any other possible beneficial effects.

[0099] While the basic concepts have been described above, it will be apparent to those skilled in the art that the detailed disclosure is merely illustrative and does not limit this specification. Although not explicitly stated herein, various modifications, improvements, and revisions to this specification may be made by those skilled in the art. Such modifications, improvements, and revisions are suggested in this specification and remain within the spirit and scope of the exemplary embodiments of this specification.

[0100] This specification also uses specific terms to describe the embodiments of this specification. For example, "one embodiment," "an embodiment," and / or "some embodiments" refer to a feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "one embodiment," "an embodiment," or "an alternative embodiment" two or more times in different locations in this specification do not necessarily refer to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of this specification may be appropriately combined.

[0101] In addition, unless expressly stated in the claims, the order of the processing elements and sequences, the use of alphanumeric characters, or the use of other names described in this specification are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some of the invention embodiments currently considered useful through various examples, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the spirit and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0102] Similarly, it should be noted that, in order to simplify the presentation of this specification and thus facilitate understanding of one or more embodiments of the invention, the foregoing descriptions of the embodiments of this specification sometimes combine multiple features into a single embodiment, figure, or description thereof. However, this disclosure method does not imply that the subject matter of this specification requires more features than those recited in the claims. In fact, an embodiment may have fewer features than all of the features of a single disclosed embodiment.

[0103] In some embodiments, numbers are used to describe the quantity of components and attributes. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise stated, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the description and claims are approximate values, which may change according to the required characteristics of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the settings of such numerical values ​​are as accurate as possible within the feasible range.

[0104] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, and documents, cited in this specification is hereby incorporated by reference in its entirety. This includes application history documents that are inconsistent with or conflict with the content of this specification, as well as documents (currently or subsequently attached to this specification) that limit the broadest scope of the claims of this specification. It should be noted that if the descriptions, definitions, and / or terminology used in the accompanying materials are inconsistent or conflicting with the content of this specification, the descriptions, definitions, and / or terminology used in this specification will control.

[0105] Finally, it should be understood that the embodiments described in this specification are intended only to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly described and illustrated in this specification.

Claims

1. A method for determining parameters related to character recognition, characterized in that: The method comprises: Obtain point cloud data of three-dimensional characters; Establishing a settlement projection of the point cloud data of the three-dimensional character in all directions; Selecting a first projection direction from the settlement projections; Segmenting the point cloud data of the three-dimensional character based on the first projection direction, and projecting the segmented point cloud data based on a second projection direction to determine row and column information of the three-dimensional character, wherein the first projection direction is perpendicular to the second projection direction, and the row and column information refers to information used to represent the arrangement of characters in the three-dimensional character; Segmenting the three-dimensional characters based on row and column information of the three-dimensional characters to determine point cloud data of each character and format information of the three-dimensional characters, wherein the format information of the three-dimensional characters includes character spacing between two adjacent characters and line spacing between two adjacent lines of characters; determining content information of the three-dimensional characters based on the point cloud data of the respective characters, wherein the content information of the three-dimensional characters includes line width of the three-dimensional characters; Determining the character spacing, the line spacing, and the line width as preset information of the three-dimensional character; and Based on the preset information of the three-dimensional character, the resolution of the character information acquisition device used to obtain the point cloud data of the three-dimensional character is determined; the resolution is used to reflect the distance between two adjacent points in the point cloud data collected by the character information acquisition device.

2. The determination method according to claim 1, characterized in that The resolution of the character information acquisition device is determined based on the smaller value of the line width, the character spacing, and the line spacing.

3. The determination method according to claim 1, characterized in that The numerical range of the ratio of the line width, the character spacing, or the line spacing to the resolution of the character information acquisition device is 5-10.

4. The determination method according to claim 1, characterized in that The method further comprises: Based on the resolution of the character information acquisition device, a search radius of associated point cloud data in the point cloud data of the three-dimensional character is determined; the associated point cloud data in the point cloud data of the three-dimensional character is used to reflect the point cloud data of a single character.

5. The determination method according to claim 4, characterized in that: The numerical range of the ratio of the search radius to the resolution is 5-10.

6. The determination method according to claim 1, characterized in that: The method further comprises: Obtaining a resolution of a character information acquisition device for acquiring point cloud data of the three-dimensional character; The search radius of associated point cloud data in the point cloud data of the three-dimensional character is determined based on the resolution; the associated point cloud data in the point cloud data of the three-dimensional character is used to reflect the point cloud data of a single character.

7. The determination method according to claim 6, characterized in that: The obtaining of the resolution of the character information acquisition device for obtaining the point cloud data of the three-dimensional character comprises: The resolution of the character information acquisition device is obtained through input information of the terminal device.

8. A system for determining parameters related to character recognition, characterized in that: The system comprises: An acquisition module is configured to acquire point cloud data of a three-dimensional character; establish cluster projections of the point cloud data of the three-dimensional character in various directions; select a first projection direction from the cluster projections; segment the point cloud data of the three-dimensional character based on the first projection direction, and project the segmented point cloud data based on a second projection direction to determine row and column information of the three-dimensional character, wherein the first projection direction is perpendicular to the second projection direction, and the row and column information refers to information used to characterize the arrangement of characters in the three-dimensional character; segment the three-dimensional character based on the row and column information of the three-dimensional character, determine the point cloud data of each character and the format information of the three-dimensional character, wherein the format information of the three-dimensional character includes the character spacing between two adjacent characters and the line spacing between two adjacent lines of characters; determine the content information of the three-dimensional character based on the point cloud data of each character, wherein the content information of the three-dimensional character includes the line width of the three-dimensional character; determine the character spacing, the line spacing, and the line width as preset information of the three-dimensional character; The resolution determination module is used to determine the resolution of a character information acquisition device used to obtain point cloud data of the three-dimensional character based on preset information of the three-dimensional character.

9. A device for determining parameters related to character recognition, the device comprising a processor and a memory; the memory is used to store instructions, characterized in that: When the instruction is executed by the processor, the device implements operations corresponding to the method for determining character recognition related parameters as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The storage medium stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer runs the method for determining character recognition related parameters as described in any one of claims 1 to 7.

Images