A method, device, equipment and medium for identifying corporate logo

Abstract

The present application provides a method, device, equipment and medium for identifying a corporate logo, the method comprising: obtaining a target image of a target enterprise; determining first coordinate information of a graphic and second coordinate information of text in the target image; determining a logo format of the target image based on the first coordinate information and the second coordinate information; determining a corporate logo whose similarity meets preset requirements among candidate corporate logos of the logo format based on the first coordinate information and the second coordinate information of the target image; and sending the corporate logo whose similarity meets preset requirements to a client terminal. The present application determines a corporate logo whose similarity meets preset requirements based on the first position information of a graphic in a target image and the second coordinate information of text in a target image, so that a user obtains a more accurate corporate logo that meets preset requirements, thereby improving the accuracy of corporate logo recognition.

Description

Technical Field

[0001] The present application relates to the field of image recognition, and more specifically, to a method, device, equipment and medium for identifying a corporate logo. Background Art

[0002] In the increasingly competitive global market, strict management and correct use of company logos with unified standards will provide a more effective, clearer and more friendly market image. Logos are a visual way of expressing information formed by people in long-term life and practice. They are visual graphics with certain meanings and can be understood by people. They have a concise, clear and clear visual transmission effect. It is a highly practical specialized subject involving fields such as psychology, aesthetics, and color science. After being refined, abstracted and processed in life practice, they are concentrated in the form of graphics, and express certain spiritual connotations, convey specific information, and form a visual language for people to communicate with each other. As a visual graphic that identifies and conveys information, logos, with their simple and beautiful modeling language, reflect the characteristics of the brand and the image of the enterprise.

[0003] In an enterprise, logos may need to be used in many occasions. The layouts corresponding to pictures in different occasions may be different. It is impossible to completely distinguish multiple logos through manual recognition alone. Summary of the invention

[0004] In view of this, the purpose of the present application is to provide a corporate logo recognition method, recognition device, equipment and medium, which are used to solve the problem of inaccurate corporate logo recognition in the prior art.

[0005] In a first aspect, an embodiment of the present application provides a method for identifying a corporate logo, the method comprising:

[0006] Get a target picture of the target enterprise;

[0007] Determine first coordinate information of the graphic and second coordinate information of the text in the target image;

[0008] Determining a logo format of the target image according to the first coordinate information and the second coordinate information;

[0009] Based on the first coordinate information and the second coordinate information of the target image, determining a corporate logo whose similarity meets a preset requirement from candidate corporate logos of the logo format;

[0010] The enterprise logos whose similarity meets the preset requirements are sent to the client terminal.

[0011] Optionally, determining the logo format of the target image according to the first coordinate information and the second coordinate information includes:

[0012] Determine the relative position, relative distance and relative size of the graphic and the text according to the first coordinate information and the second coordinate information;

[0013] Determining the logo format of the target image according to the relative orientation, relative distance and relative size of the graphic and the text;

[0014] Optionally, the first coordinate information includes coordinate information of a first vertex of a circumscribed rectangle of the graphic, and the second coordinate information includes coordinate information of a second vertex of a circumscribed rectangle of the text; determining the relative orientation and relative distance between the graphic and the text according to the first coordinate information and the second coordinate information includes:

[0015] Determine the first center point of the circumscribed rectangle of the graphic according to the first vertex coordinate information of the circumscribed rectangle of the graphic;

[0016] Determine the position of the second center point of the circumscribed rectangle of the character according to the coordinate information of the second vertex of the circumscribed rectangle of the character;

[0017] Determining the relative orientation and relative distance between the graphic and the text according to the first center point position and the second center point position;

[0018] The first coordinate information includes coordinate information of a first vertex of a circumscribed rectangle of the graphic, and the second coordinate information includes coordinate information of a second vertex of a circumscribed rectangle of the text; determining the relative size of the graphic and the text according to the first coordinate information and the second coordinate information includes:

[0019] Determine the length and width of the graphic and the text respectively according to the first vertex coordinate information of the circumscribed rectangle of the graphic and the second vertex coordinate information of the circumscribed rectangle of the text;

[0020] Determine the relative sizes of the graphic and the text according to the lengths and widths corresponding to the graphic and the text respectively;

[0021] Optionally, the identification method further includes:

[0022] Determine shape information of graphics and content information of text in the target image;

[0023] The enterprise logos whose similarity meets the preset requirements are sent to the client terminal, including:

[0024] Determine, among the corporate logos whose similarities meet the preset requirements, a target corporate logo having the same shape information and text content information as those in the target image;

[0025] Sending the target enterprise identification to the client terminal;

[0026] Optionally, the determining the first coordinate information of the graphic and the second coordinate information of the text in the target image includes:

[0027] Using a graphic recognition model to identify first coordinate information of the graphic in the target image;

[0028] The second coordinate information of the graphic is recognized in the target image using a text recognition model.

[0029] In a second aspect, the present application provides an identification device for enterprise identification, comprising:

[0030] An acquisition module is used to acquire target images of target enterprises;

[0031] A position determination module, used to determine first coordinate information of a graphic and second coordinate information of a text in the target image;

[0032] A layout determination module, used to determine a logo layout of the target image according to the first coordinate information and the second coordinate information;

[0033] A comparison module, configured to determine, based on the first coordinate information and the second coordinate information of the target image, a corporate logo whose similarity meets a preset requirement among candidate corporate logos of the logo format;

[0034] The sending module is used to send the enterprise logos whose similarity meets the preset requirements to the client terminal.

[0035] Optionally, the layout determination module includes:

[0036] A first determining unit, configured to determine the relative position, relative distance and relative size of the graphic and the text according to the first coordinate information and the second coordinate information;

[0037] A second determining unit, configured to determine a logo format of the target image according to a relative position, relative distance and relative size of the graphic and the text;

[0038] In a third aspect, the present application provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0039] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, and the computer program executes the steps of the above method when executed by a processor.

[0040] The present application provides a method for identifying a corporate logo. First, a target image of a target enterprise is obtained; then, the first coordinate information of the graphic and the second coordinate information of the text in the target image are respectively determined, and the target image representation logo format is determined based on the first coordinate information and the second coordinate information; based on the first coordinate information and the second coordinate information of the target image, a corporate logo whose similarity meets the preset requirements is determined among candidate corporate logos in the logo format, and finally the corporate logo whose similarity meets the preset requirements is sent to a client terminal. The present application determines a corporate logo whose similarity meets the preset requirements based on the first position information of the graphic in the target image and the second coordinate information of the text in the target image, so that the user obtains a more accurate corporate logo that meets the preset requirements, thereby improving the accuracy of corporate logo recognition.

[0041] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 A flowchart of a method for identifying a corporate logo provided in an embodiment of the present application;

[0044] Figure 2 A schematic diagram of the position of the first center point provided in an embodiment of the present application;

[0045] Figure 3 A schematic diagram of the position of the second center point provided in an embodiment of the present application;

[0046] Figure 4 A schematic diagram of the structure of a corporate logo recognition device provided in an embodiment of the present application;

[0047] Figure 5 A schematic diagram of the structure of a computer device provided in an embodiment of the present application;

[0048] Figure 6 A schematic diagram of a corporate logo provided in an embodiment of the present application. DETAILED DESCRIPTION

[0049] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0050] Many domestic Internet companies have formed logo recognition business solutions to a certain extent. The current logo recognition can mainly identify the name, location and other information of the logo in the picture. For example, it can identify that the logo in the picture is the logo of a commercial aircraft, as well as basic and simple information such as the shooting location of the picture. However, a corporate headquarters contains many secondary units, and each company has a corresponding logo, but the differences between the logos are small and the changes are subtle. The above recognition business solution cannot meet the requirements of icon logo recognition of some companies. When the layouts are very similar, these logos with different layouts cannot be accurately distinguished, and thus cannot provide users with accurate information, which reduces the user experience.

[0051] The present application embodiment provides a method for identifying a corporate logo, such as Figure 1 As shown, the following steps are included:

[0052] S101, obtaining a target image of a target enterprise;

[0053] S102, determining first coordinate information of a graphic and second coordinate information of a text in the target image;

[0054] S103, determining a logo format of the target image according to the first coordinate information and the second coordinate information;

[0055] S104, based on the first coordinate information and the second coordinate information of the target image, determining a corporate logo whose similarity meets a preset requirement among candidate corporate logos of the logo format;

[0056] S105, sending the enterprise logos whose similarity meets the preset requirements to the client terminal.

[0057] In the above step S101, the target image is a picture taken by a user with a corporate logo, the target enterprise is an enterprise whose corporate logo needs to be identified, and the corporate logo of the target enterprise includes graphics and text.

[0058] Specifically, the server obtains the target image of the target enterprise from the acquisition device, wherein the server can obtain the target image of the target enterprise through the enterprise identification request sent by the image acquisition device, and the image acquisition device may include a smart phone, a camera, etc., which is not limited by this application. The target image in the image acquisition device is obtained by any of the following methods:

[0059] The target image is directly acquired through the camera of the image acquisition device; after acquiring the image through the camera of the image acquisition device, the target image is obtained by cropping the image; or the target image is acquired through the corporate logo recognition program running in the image acquisition device.

[0060] After the user obtains the target image through the image acquisition device, the target image will be uploaded to the server through the network. Before being uploaded to the server, the target image will be compressed to a preset size, such as 200k, and the image will be converted using a binary image converter so that the image is uploaded to the server in the form of a binary stream, which can improve the transmission speed. After the server receives the compressed target image, subsequent steps S102-S105 are executed based on the compressed target image, thereby improving the parsing speed of the target image during the image recognition process.

[0061] In the above step S102, the first coordinate information is the first coordinate information of the graphic identified in the target image by the graphic recognition model, and the first coordinate information includes the first vertex coordinate information of the circumscribed rectangle of the graphic. The second coordinate information is the second coordinate information of the text identified in the target image by the text recognition model, and the second coordinate information includes the second vertex coordinate information of the circumscribed rectangle of the text.

[0062] Specifically, the target image is input into the graphic recognition model and the text recognition model respectively to obtain first coordinate information corresponding to the graphic in the target image and second coordinate information corresponding to the text in the target image.

[0063] Among them, the graphic recognition model is trained through the following steps:

[0064] Step 1021, obtaining a picture training sample set; the target picture training sample set includes at least one training sample, the training sample set includes a training picture and first coordinate information of a graphic in the training picture, and each training sample in the target picture training sample set is a target picture corresponding to the same corporate logo;

[0065] Step 1022: For each training sample, the training image in the training sample is input as a positive sample to the graphic recognition model to be trained, and the first coordinate information of the graphic in the training image is input as a negative sample to the graphic recognition model to be trained, so as to train the graphic recognition model to be trained.

[0066] In the above steps 1021 to 1022, the present application also provides a database, which stores training samples for training the graphic recognition model. Multiple training samples together constitute a graphic training sample set. When the graphic recognition model to be trained is trained, the training picture is input into the graphic recognition model to be trained. The graphic recognition model to be trained will output a recognition result of the first coordinate information, and the recognition result is compared with the first coordinate information of the graphic in the training picture of the training sample. If the comparison result is significantly different, the graphic recognition model to be trained needs to be adjusted. If the comparison result is slightly different, it means that the training accuracy of the graphic recognition model to be trained is getting higher and higher. When the comparison result meets the preset requirements, that is, when the difference is less than a certain threshold, the training of the graphic recognition model to be trained is completed.

[0067] The text recognition model is trained through the following steps:

[0068] Step 1023, obtaining a text training sample set; the text training sample set includes at least one training sample, the training sample set includes training text and second coordinate information of the training text, and each training sample in the target image training sample set is a target image corresponding to the same corporate logo;

[0069] Step 1024, for each training sample, input the training text in the training sample as a positive sample into the text recognition model to be trained, and input the second coordinate information of the text in the training text as a negative sample into the text recognition model to be trained, so as to train the text recognition model to be trained.

[0070] In the above steps 1023 to 1024, the database of the present application also stores training samples for training the text recognition model. Multiple training samples together constitute a text training sample set. When the text recognition model to be trained is trained, the training text is input into the text recognition model to be trained. The text recognition model to be trained will output a recognition result of the second coordinate information, and the recognition result is compared with the second coordinate information of the text in the training text of the training sample. If the comparison result has a large difference, the text recognition model to be trained needs to be adjusted. If the comparison result has a small difference, it means that the training accuracy of the text recognition model to be trained is getting higher and higher. When the comparison result meets the preset requirements, that is, when the difference is less than a certain threshold, the training of the text recognition model to be trained is completed.

[0071] In the above step S103, the logo format is the layout format of graphics and text in the corporate logo, such as left-right layout, top-bottom layout, etc. An enterprise may be composed of multiple branches. In order to distinguish multiple branches, the corporate logos corresponding to the multiple branches are different. The difference can be the difference in logo format, or the difference in the first coordinate information of the graphics or the second coordinate information of the text under the same logo format.

[0072] Specifically, based on the first coordinate information of the graphic and the second coordinate information of the text in the target image, the position of the graphic and the text in the target image can be determined, and then the identification version of the target image can be determined based on the position of the graphic and the position of the text.

[0073] In the above step S104, the candidate corporate logo is a pre-set standard corporate logo.

[0074] Specifically, the server stores corporate logos corresponding to multiple branches of the same company. A candidate corporate logo corresponding to the logo layout is selected from all candidate corporate logos, and based on the first coordinate information and the second coordinate information of the target image, a similarity between the corporate logo in the target image and the candidate corporate logo corresponding to the logo layout is calculated, and based on the calculated similarity, a corporate logo whose similarity meets a preset requirement is determined from among the candidate corporate logos corresponding to the logo layout.

[0075] For example, when the target enterprise is enterprise C, enterprise C includes multiple versions of corporate logos: version 1, version 2, version 3..., all of the above versions of corporate logos are used as candidate corporate logos to compare with the logo layout of the target image to calculate the similarity, and the logo versions of the target image are compared one by one with version 1, version 2, version 3... in the candidate corporate logos, and the corresponding similarity values ​​q1, q2, q3... are obtained, and then the similarity values ​​q1, q2, q3... are compared with the preset results respectively. If the similarity values ​​meet the preset requirements, namely q2 and q5, then version 2 and version 5 in the candidate corporate logos are used as corporate logos whose similarities meet the preset requirements.

[0076] The first coordinate information of the graphic determined by the graphic recognition model and the second coordinate information of the text determined by the text recognition model may be different from the real coordinate information. That is, the similarity between the corporate logo in the target image and the candidate corporate logo corresponding to the logo format may not reach 100%. Therefore, a certain error tolerance is required to determine the corporate logo. At this time, the corporate logo that is closer to the version logo of the target image is determined from version 2 and version 5 of the candidate corporate logo according to the preset error tolerance. The above error tolerance is the range of errors allowed when calculating the similarity value. Specifically, for example, when the similarity value q2 is 85%, the error tolerance is 15%; when the similarity value q5 is 90%, the error tolerance is 10%, and the corporate logo that is closer to the version logo of the target image is the corporate logo of version 5 corresponding to the similarity value q5.

[0077] In the above step 105, the client terminal is used to receive and display the corporate logos whose similarity meets the preset requirements. The client terminal may include a smart phone, a tablet, etc., and this application does not limit this.

[0078] Specifically, the server sends the corporate logo whose similarity meets the preset requirements to the client terminal. When the server sends the corporate logo whose similarity meets the preset requirements to the client terminal, it will carry the information of the corresponding company: such as the company name, company location and other information. After receiving the corporate logo whose similarity meets the preset requirements, the client terminal can help the customer quickly obtain the information of the company corresponding to the brand information, promote the customer's conversion into an investor, and realize the cooperation between the customer and the company. Or when the customer is a consumer and when the customer has a poor experience, the customer can file a complaint against the company based on the company information carried in the corporate logo sent by the server, thereby solving the problem the customer wants to solve, or providing the customer with more professional services.

[0079] The corporate logo recognition method provided in the embodiment of the present application, through the above five steps, the server obtains the first coordinate information about the graphic and the second coordinate information about the text by processing the target image, and determines the version identification of the target image based on the first coordinate information and the second coordinate information, and then screens the candidate corporate logos corresponding to the version identification for the user to obtain a corporate logo with a similarity that meets the requirements, so that the user receives a more accurate version of the corporate logo, which improves the accuracy of the user in obtaining the corporate logo of the identification version corresponding to the target image.

[0080] However, when the candidate corporate logo corresponding to the logo format is compared with the corporate logo of the target image, there may be multiple corporate logos whose similarities meet the preset requirements, and at least two similarity values ​​are the same. Based on the above situation, the present application provides a more detailed recognition method, which includes:

[0081] Step 106, determining the shape information of the graphics and the content information of the text in the target image;

[0082] Step S105 includes:

[0083] Step 1051, determining a target enterprise logo having the same shape information and text content information as the graphic in the target image among the enterprise logos whose similarity meets the preset requirement;

[0084] Step 1052: Send the target enterprise identifier to the client terminal.

[0085] In the above step 106, while the first coordinate information of the graphic in the target image is determined by the graphic recognition model, the graphic recognition model also recognizes the shape information of the graphic in the target image. While the second coordinate information of the text in the target image is determined by the text recognition model, the text recognition model also recognizes the content information of the text in the target image. The shape information of the graphic is the specific shape of the graphic, which may be a triangle, rectangle, square, etc., and the content information of the text is all the text contained in the text part, which may be English, Chinese, etc.

[0086] In the above step 1051, the shapes of the graphics and all the characters contained in the text part of the two corporate logos with the same similarity value are respectively identified, and the shape of the graphics and all the characters contained in the text part of each corporate logo are compared with the shape of the graphics and all the characters in the text part of the target image, and the corporate logo with the same shape information of the graphics and content information of the text in the target image is selected as the target corporate table logo.

[0087] In the above step 1052, the target corporate logo is a corporate logo selected from the corporate logos whose similarities meet the preset requirements and having the same shape information and text content information as the graphics in the target image.

[0088] Specifically, the corporate logo having the same shape information and text content information as those of the graphic in the target image is sent to the client terminal as the target corporate logo.

[0089] In order to understand in more detail the process of determining the version identifier of the target image from the first coordinate information and the second coordinate information, step S103 includes:

[0090] Step 1031, determining the relative position, relative distance and relative size of the graphic and the text according to the first coordinate information and the second coordinate information;

[0091] Step 1032, determining the logo format of the target image according to the relative orientation, relative distance and relative size of the graphic and the text.

[0092] In the above step 1031, the relative orientation can be the position of the text relative to the graphic, or the position of the graphic relative to the text; the relative distance is the straight-line distance between the graphic and the text; the relative size is the ratio of the size of the graphic to the size of the text, or the ratio of the size of the text to the size of the graphic.

[0093] In a feasible implementation manner, the first coordinate information includes coordinate information of a first vertex of a circumscribed rectangle of the graphic, and the second coordinate information includes coordinate information of a second vertex of a circumscribed rectangle of the text;

[0094] When executing step 1031 to determine the relative position and relative distance between the graphic and the text according to the first coordinate information and the second coordinate information, the following steps may be specifically performed:

[0095] Step 10311, determining the first center point position of the circumscribed rectangle of the graphic according to the first vertex coordinate information of the circumscribed rectangle of the graphic;

[0096] Step 10312, determining the second center point position of the circumscribed rectangle of the character according to the second vertex coordinate information of the circumscribed rectangle of the character;

[0097] Step 10313, determining the relative orientation and relative distance between the graphic and the text according to the first center point position and the second center point position.

[0098] In the above step 10311, the first vertex coordinate information includes the coordinate information of the four vertices of the circumscribed rectangle of the graphic, and the first center point position is the position where the center point of the circumscribed rectangle of the graphic is located.

[0099] Specifically, the circumscribed rectangle of the figure is first determined, and then the four coordinate vertices of the circumscribed rectangle of the figure are determined. The corresponding center point is calculated according to the four coordinate vertices, and the center point is used as the first center point position of the circumscribed rectangle of the figure.

[0100] For example, Figure 2 As shown, the four vertices of the circumscribed rectangle of the figure are a, b, c, and d respectively. The coordinates of the center point of the circumscribed rectangle of the figure are calculated to be e based on the coordinates of the four vertices. The center point e is the first center point position of the circumscribed rectangle of the figure.

[0101] In the above step 10312, the second vertex coordinate information includes the coordinate information of the four vertices of the circumscribed rectangle of the text, and the second center point position is the position of the center point of the circumscribed rectangle of the text.

[0102] Specifically, the circumscribed rectangle of the text is first determined, and then the four coordinate vertices of the circumscribed rectangle of the text are determined. The corresponding center point is calculated according to the four coordinate vertices, and the center point is used as the second center point position of the circumscribed rectangle of the text.

[0103] For example, Figure 3 As shown, the four vertices of the text circumscribed rectangle are a1, b1, c1, and d1 respectively. The coordinates of the center point of the text circumscribed rectangle are calculated based on the coordinates of the four vertices to be e1, and the center point e1 is the second center position of the text circumscribed rectangle.

[0104] In the above step 10313, the relative orientation and relative distance of the image and text are determined based on the position of the first center point and the position of the second center point.

[0105] Specifically, the distance between the first center point and the second center point is used as the relative distance between the image and the text, and the relative orientation of the image and the text is determined based on the positions of the two center points in the target image.

[0106] For example, when the first center point is e and the second center point is e1, the distance between the two points e and e1 is used as the relative distance between the picture and the text. At the same time, the orientation of the picture and the text is determined according to the coordinates of the two center points e and e1. For example, when the horizontal coordinate of the first center point e is the same as the horizontal coordinate of the second center point e1, the explanatory text is located on the right or left side of the picture; when the vertical coordinate of the first center point e is the same as the vertical coordinate of the second center point e1, the explanatory text is located below or above the picture.

[0107] In another feasible implementation manner, the first coordinate information includes coordinate information of a first vertex of a circumscribed rectangle of the graphic, and the second coordinate information includes coordinate information of a second vertex of a circumscribed rectangle of the text;

[0108] When executing the above step 1031 to determine the relative sizes of the graphic and the text according to the first coordinate information and the second coordinate information, the following steps may be specifically performed:

[0109] Step 10314, determining the length and width of the graphic and the text respectively according to the first vertex coordinate information of the circumscribed rectangle of the graphic and the second vertex coordinate information of the circumscribed rectangle of the text;

[0110] Step 10315, determining the relative sizes of the graphic and the text according to the lengths and widths corresponding to the graphic and the text respectively.

[0111] In the above step 10314, the length and width of the graphic are respectively the length and width of the circumscribed rectangle of the graphic; the length and width of the graphic are calculated based on the four vertices of the circumscribed rectangle of the graphic. The length and width of the text are respectively the length and width of the circumscribed rectangle of the text; the length and width of the text are calculated based on the four vertices of the circumscribed rectangle of the text.

[0112] Specifically, first determine the circumscribed rectangle of the figure, then determine that the four vertices of the circumscribed rectangle of the figure are a, b, c, and d, the absolute value of the difference in the horizontal coordinates calculated from the vertices a and b or c and d of the circumscribed rectangle of the figure is the length of the circumscribed rectangle of the figure, and the absolute value of the difference in the vertical coordinates calculated from the vertices a and c or b and d is the width of the circumscribed rectangle of the figure; similarly, first determine the circumscribed rectangle of the text, then determine that the four vertices of the circumscribed rectangle of the text are a1, b1, c1, and d1, the absolute value of the difference in the vertical coordinates calculated from the vertices a1 and b1 or c1 and d1 of the circumscribed rectangle of the text is the length of the circumscribed rectangle of the text, and the absolute value of the difference in the vertical coordinates calculated from the vertices a1 and c1 or b1 and d1 is the width of the circumscribed rectangle of the text.

[0113] Taking vertices a and b among the four vertices of the circumscribed rectangle of a figure as examples, the horizontal coordinate of vertex a is x1, the horizontal coordinate of vertex b is x2, and the absolute value of the difference between x1 and x2 is the length of the figure. Taking vertices a and c among the four vertices of the circumscribed rectangle of a figure as examples, the vertical coordinate of vertex a is y1, and the vertical coordinate of vertex c is y3, then the absolute value of the difference between y1 and y3 is the width of the figure; similarly, taking vertices a1 and b1 among the four vertices of the circumscribed rectangle of a text as examples, the horizontal coordinate of vertex a1 is xa, the horizontal coordinate of vertex b1 is xb, and the absolute value of the difference between xa and xb is the length of the text. Taking vertices a1 and c1 among the four vertices of the circumscribed rectangle of the text as examples, the vertical coordinate of vertex a1 is ya, and the vertical coordinate of vertex c1 is yc, then the absolute value of the difference between ya and yc is the width of the text.

[0114] In the above step 10315, the relative size of the graphic and the text refers to the ratio of the size of the graphic to the size of the text, or it can be the ratio of the size of the text to the size of the graphic.

[0115] Specifically, with the width of the image as a reference, the relative size of the graphic and the text can be the ratio of the width of the graphic to the length of the text. A ratio is calculated based on the width of the image and the length of the text, and the ratio is the relative size of the graphic and the text.

[0116] For example, Figure 6 As shown in the figure, when the width of the image is A and the length of the text is 7A, the ratio of the width of the image to the length of the text is , then the length of the text is 7 times the width of the graphic.

[0117] In the above step 1032, the logo format of the target image is determined according to the relative position, relative distance and relative size of the image and the text.

[0118] Specifically, the logo format of the target image is determined according to the position of the image relative to the text, the distance between the center of the image and the center of the text as the relative distance, and the ratio of the size of the image to the size of the text.

[0119] For example, when the distance between the center position of the graphic and the center position of the text is a, the length of the text is 7 times the width of the graphic, and the graphic is located above the text, the logo format corresponding to the target image is determined.

[0120] The embodiment of the present application provides a method for identifying a corporate logo, including: obtaining a target image of a target enterprise; determining the first coordinate information of a graphic and the second coordinate information of a text in the target image, determining the logo format of the target image based on the first coordinate information and the second coordinate information of the target image, and when selecting a candidate corporate logo, performing a similarity comparison with the candidate corporate logo based on the first coordinate information and the second coordinate information, and sending the corporate logo that meets the preset requirements to the user. This method can achieve the distinction and identification of corporate logos with similar formats, and recommend more accurate corporate logos to users.

[0121] See also Figure 4 As shown, it is a structural schematic diagram of a corporate logo recognition device 400 provided in an embodiment of the present application, and the device includes: an acquisition module 401, a position determination module 402, a layout determination module 403, a comparison module 404, and a sending module 405. Specifically:

[0122] An acquisition module 401 is used to acquire a target image of a target enterprise;

[0123] A position determination module 402 is used to determine first coordinate information of a graphic and second coordinate information of a text in the target image;

[0124] A layout determination module 403, configured to determine a logo layout of the target image according to the first coordinate information and the second coordinate information;

[0125] A comparison module 404 is used to determine, based on the first coordinate information and the second coordinate information of the target image, a corporate logo whose similarity meets a preset requirement among candidate corporate logos of the logo format;

[0126] The sending module 405 is used to send the enterprise logos whose similarity meets the preset requirements to the client terminal.

[0127] Optionally, the layout determination module includes:

[0128] A first determining unit, configured to determine the relative position, relative distance and relative size of the graphic and the text according to the first coordinate information and the second coordinate information;

[0129] The second determining unit is used to determine the logo format of the target image according to the relative orientation, relative distance and relative size of the graphic and the text.

[0130] Optionally, the first determining unit includes:

[0131] A third determining unit, configured to determine a first center point position of a circumscribed rectangle of the graphic according to first vertex coordinate information of the circumscribed rectangle of the graphic;

[0132] A fourth determining unit, configured to determine a second center point position of a circumscribed rectangle of the character according to the coordinate information of a second vertex of the circumscribed rectangle of the character;

[0133] A fifth determining unit is used to determine the relative orientation and relative distance between the graphic and the text according to the first center point position and the second center point position.

[0134] Optionally, the first determining unit includes:

[0135] A sixth determining unit, configured to determine the length and width of the graphic and the text respectively according to the first vertex coordinate information of the circumscribed rectangle of the graphic and the second vertex coordinate information of the circumscribed rectangle of the text;

[0136] The seventh determining unit is used to determine the relative sizes of the graphic and the text according to the lengths and widths corresponding to the graphic and the text respectively.

[0137] Optionally, the device further includes:

[0138] An information determination module, used to determine the shape information of the graphics and the content information of the text in the target image;

[0139] The sending module comprises:

[0140] An eighth determination unit is used to determine, among the corporate logos whose similarities meet preset requirements, a target corporate logo that has the same shape information and text content information as the graphic in the target image;

[0141] A sending unit is used to send the target enterprise identifier to the client terminal.

[0142] Optionally, a location determination module includes:

[0143] A first recognition unit, configured to recognize first coordinate information of the graphic in the target image using a graphic recognition model;

[0144] The second recognition unit is used to recognize the second coordinate information of the graphic in the target image by using a text recognition model.

[0145] Corresponds to Figure 1 The method for identifying a corporate identity in the embodiment of the present application further provides a computer device 500, such as Figure 5 As shown, the device includes a memory 501, a processor 502, and a computer program stored in the memory 501 and executable on the processor 502, wherein the processor 502 implements the steps of the method for feeding back the corporate identity when executing the computer program.

[0146] Specifically, the above-mentioned memory 501 and processor 502 can be general-purpose memory and processor, which are not specifically limited here. When the processor 502 runs the computer program stored in the memory 501, it can execute the above-mentioned method for identifying the corporate logo, which solves the problem of how to provide users with more accurate corporate logos in the prior art. First, a target picture of the target enterprise is obtained; then, the first coordinate information of the graphics and the second coordinate information of the text in the target picture are determined using the image recognition model and the text recognition model respectively, and then the layout of the target picture is determined according to the first coordinate information and the second coordinate information, and then the corporate logo that meets the similarity requirements is screened out from the candidate corporate logos according to the first coordinate information and the second coordinate information of the target picture. Finally, the corporate logo whose similarity meets the preset requirements is sent to the user, so that the user can receive a more accurate corporate logo and provide the user with more accurate corporate-related information.

[0147] Corresponds to Figure 1 In the method for identifying a corporate logo, an embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method for identifying a corporate logo are executed.

[0148] Specifically, the storage medium can be a general storage medium, such as a mobile disk, a hard disk, etc. When the computer program on the storage medium is run, the above-mentioned method for identifying corporate logos can be executed, which solves the problem of how to provide users with more accurate corporate logos in the prior art. First, a target picture of the target enterprise is obtained; then, the first coordinate information of the graphics and the second coordinate information of the text in the target picture are determined using the picture recognition model and the text recognition model respectively, and then the layout of the target picture is determined according to the first coordinate information and the second coordinate information, and then the corporate logo that meets the similarity requirements is screened out from the candidate corporate logos according to the first coordinate information and the second coordinate information of the target picture. Finally, the corporate logo whose similarity meets the preset requirements is sent to the user, so that the user can receive a more accurate corporate logo and provide the user with more accurate corporate related information.

[0149] In the embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0150] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0151] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0152] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0153] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and are not to be understood as indicating or implying relative importance.

[0154] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application. They should all be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for identifying a corporate logo, characterized in that: include: Get a target picture of the target enterprise; Determine first coordinate information of the graphic and second coordinate information of the text in the target image; Determining a logo format of the target image according to the first coordinate information and the second coordinate information; The step of determining the logo format of the target image according to the first coordinate information and the second coordinate information includes: Determine the relative position, relative distance and relative size of the graphic and the text according to the first coordinate information and the second coordinate information; the first coordinate information includes the coordinate information of the first vertex of the circumscribed rectangle of the graphic, and the second coordinate information includes the coordinate information of the second vertex of the circumscribed rectangle of the text; The determining the relative position and relative distance between the graphic and the text according to the first coordinate information and the second coordinate information includes: Determine the first center point of the circumscribed rectangle of the graphic according to the first vertex coordinate information of the circumscribed rectangle of the graphic; Determine the position of the second center point of the circumscribed rectangle of the character according to the coordinate information of the second vertex of the circumscribed rectangle of the character; Determining the relative orientation and relative distance between the graphic and the text according to the first center point position and the second center point position; Determining the relative sizes of the graphic and the text according to the first coordinate information and the second coordinate information includes: Determine the length and width of the graphic and the text respectively according to the first vertex coordinate information of the circumscribed rectangle of the graphic and the second vertex coordinate information of the circumscribed rectangle of the text; Determine the relative sizes of the graphic and the text according to the lengths and widths corresponding to the graphic and the text respectively; Determining the logo format of the target image according to the relative orientation, relative distance and relative size of the graphic and the text; Based on the first coordinate information and the second coordinate information of the target image, determining a corporate logo whose similarity meets a preset requirement among candidate corporate logos of the logo format; The enterprise logos whose similarity meets the preset requirements are sent to the client terminal.

2. The identification method according to claim 1, characterized in that: The identification method further comprises: Determine shape information of graphics and content information of text in the target image; The enterprise logos whose similarity meets the preset requirements are sent to the client terminal, including: Determine, among the corporate logos whose similarities meet the preset requirements, a target corporate logo having the same shape information and text content information as those in the target image; The target enterprise identification is sent to the client terminal.

3. The identification method according to claim 1, characterized in that: The determining of the first coordinate information of the graphic and the second coordinate information of the text in the target image includes: Using a graphic recognition model to identify first coordinate information of the graphic in the target image; The second coordinate information of the graphic is recognized in the target image using a text recognition model.

4. A device for identifying a corporate logo, characterized in that: include: An acquisition module is used to acquire target images of target enterprises; A position determination module, used to determine first coordinate information of a graphic and second coordinate information of a text in the target image; A layout determination module, used to determine a logo layout of the target image according to the first coordinate information and the second coordinate information; A comparison module, configured to determine, based on the first coordinate information and the second coordinate information of the target image, a corporate logo whose similarity meets a preset requirement among candidate corporate logos of the logo format; A sending module, used for sending the enterprise logos whose similarity meets the preset requirements to the client terminal; Wherein, the layout determination module includes: A first determining unit is used to determine the relative position, relative distance and relative size of the graphic and the text according to the first coordinate information and the second coordinate information; the first coordinate information includes the coordinate information of the first vertex of the circumscribed rectangle of the graphic, and the second coordinate information includes the coordinate information of the second vertex of the circumscribed rectangle of the text; A second determining unit, configured to determine a logo format of the target image according to a relative position, relative distance and relative size of the graphic and the text; Wherein, when the first determining unit is used to determine the relative orientation and relative distance between the graphic and the text according to the first coordinate information and the second coordinate information, the first determining unit is used to: Determine the first center point of the circumscribed rectangle of the graphic according to the first vertex coordinate information of the circumscribed rectangle of the graphic; Determine the position of the second center point of the circumscribed rectangle of the character according to the coordinate information of the second vertex of the circumscribed rectangle of the character; Determining the relative orientation and relative distance between the graphic and the text according to the first center point position and the second center point position; Wherein, when the first determining unit is used to determine the relative size of the graphic and the text according to the first coordinate information and the second coordinate information, the first determining unit is used to: Determine the length and width of the graphic and the text respectively according to the first vertex coordinate information of the circumscribed rectangle of the graphic and the second vertex coordinate information of the circumscribed rectangle of the text; The relative sizes of the graphic and the text are determined according to the lengths and widths corresponding to the graphic and the text respectively.

5. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 3 are implemented.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 3 are performed.

Images