CN113792735A - Enterprise identifier identification method, enterprise identifier identification device, enterprise identifier identification equipment and enterprise identifier identification medium - Google Patents
Enterprise identifier identification method, enterprise identifier identification device, enterprise identifier identification equipment and enterprise identifier identification medium Download PDFInfo
- Publication number
- CN113792735A CN113792735A CN202111129020.5A CN202111129020A CN113792735A CN 113792735 A CN113792735 A CN 113792735A CN 202111129020 A CN202111129020 A CN 202111129020A CN 113792735 A CN113792735 A CN 113792735A
- Authority
- CN
- China
- Prior art keywords
- coordinate information
- enterprise
- determining
- graph
- target picture
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000004590 computer program Methods 0.000 claims description 12
- 230000015654 memory Effects 0.000 claims description 10
- 238000012549 training Methods 0.000 description 46
- 238000003909 pattern recognition Methods 0.000 description 11
- 230000000007 visual effect Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000012216 screening Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Character Discrimination (AREA)
Abstract
The application provides an enterprise identifier identification method, an enterprise identifier identification device, equipment and a medium, wherein the method comprises the following steps: acquiring a target picture about a target enterprise; determining first coordinate information of a graph and second coordinate information of characters in the target picture; determining an identification format of the target picture according to the first coordinate information and the second coordinate information; determining enterprise identifications with similarity meeting preset requirements in the candidate enterprise identifications of the identification format based on the first coordinate information and the second coordinate information of the target picture; and sending the enterprise identification with the similarity meeting the preset requirement to a client terminal. According to the enterprise identification recognition method and device, the enterprise identification with the similarity meeting the preset requirement is determined based on the first position information of the graph in the target picture and the second coordinate information of the characters in the target picture, so that the user can obtain the enterprise identification which is more accurate and meets the preset requirement, and the accuracy of enterprise identification recognition is improved.
Description
Technical Field
The present application relates to the field of image recognition, and in particular, to a method, an apparatus, a device, and a medium for recognizing an enterprise identifier.
Background
In a global market where competition is intense, the identification of companies that strictly manage and correctly use unified standards will provide a more effective, clearer and more intimate market image. The mark is a visual information expression mode formed by people in long-term life and practice, and has a certain meaning and a visual pattern which can be understood by people. It has the visual transmission effect of being simple, clear and clear at a glance. It is a special subject with strong practicability, and relates to the fields of psychology, aesthetics, colorism and the like. The visual language is characterized in that the visual language is presented in a graphic mode in a centralized way through extraction, abstraction and processing in life practice, a certain mental meaning is expressed, specific information is transmitted, and the visual language for people to communicate with each other is formed. The mark is used as a visual pattern for identifying and transmitting information, and embodies the characteristics of a brand and the image of an enterprise by virtue of a simple and beautiful modeling language.
In an enterprise, the identifiers are required to be used in various occasions, the corresponding formats of the pictures in different occasions may be different, and the various identifiers cannot be completely distinguished only through manual identification.
Disclosure of Invention
In view of the above, an object of the present application is to provide an enterprise identifier identification method, an enterprise identifier identification device, and an enterprise identifier identification medium, which are used to solve the problem in the prior art that the identification of an enterprise identifier is inaccurate.
In a first aspect, an embodiment of the present application provides a method for identifying an enterprise identifier, where the method includes:
acquiring a target picture about a target enterprise;
determining first coordinate information of a graph and second coordinate information of characters in the target picture;
determining an identification format of the target picture according to the first coordinate information and the second coordinate information;
determining enterprise identifications with similarity meeting preset requirements in the candidate enterprise identifications of the identification format based on the first coordinate information and the second coordinate information of the target picture;
and sending the enterprise identification with the similarity meeting the preset requirement to a client terminal.
Optionally, the determining the identifier format of the target picture according to the first coordinate information and the second coordinate information includes:
determining the relative position, relative distance and relative size of the graph and the character according to the first coordinate information and the second coordinate information;
determining the identification format of the target picture according to the relative position, relative distance and relative size of the graph and the characters;
optionally, the first coordinate information includes first vertex coordinate information of a circumscribed rectangle of the graph, and the second coordinate information includes second vertex coordinate information of a circumscribed rectangle of the text; determining the relative position and the relative distance between the graph and the character according to the first coordinate information and the second coordinate information, wherein the determining comprises the following steps:
determining a first central point position of the circumscribed rectangle of the graph according to the first vertex coordinate information of the circumscribed rectangle of the graph;
determining a second central point position of the circumscribed rectangle of the character according to the second vertex coordinate information of the circumscribed rectangle of the character;
determining the relative position and relative distance between the graph and the character according to the position of the first central point and the position of the second central point;
the first coordinate information comprises first vertex coordinate information of a circumscribed rectangle of the graph, and the second coordinate information comprises second vertex coordinate information of a circumscribed rectangle of the character; determining the relative sizes of the graph and the characters according to the first coordinate information and the second coordinate information, wherein the relative sizes comprise:
determining the length and the width corresponding to the graph and the characters respectively according to the first vertex coordinate information of the circumscribed rectangle of the graph and the second vertex coordinate information of the circumscribed rectangle of the characters;
determining the relative sizes of the graph and the characters according to the length and the width respectively corresponding to the graph and the characters;
optionally, the identification method further includes:
determining shape information of the graph and content information of the characters in the target picture;
and sending the enterprise identification with the similarity meeting the preset requirement to a client terminal, wherein the method comprises the following steps:
determining a target enterprise identifier which is the same as the shape information of the graph and the content information of the characters in the target picture in the enterprise identifiers with the similarity meeting the preset requirement;
sending the target enterprise identification to the client terminal;
optionally, the determining the first coordinate information of the graph and the second coordinate information of the text in the target picture includes:
identifying first coordinate information of the graph in the target picture by utilizing a graph identification model;
and recognizing second coordinate information of the graph in the target picture by using a character recognition model.
In a second aspect, the present application provides an apparatus for identifying an enterprise, comprising:
the acquisition module is used for acquiring a target picture about a target enterprise;
the position determining module is used for determining first coordinate information of a graph and second coordinate information of characters in the target picture;
the format determining module is used for determining the identification format of the target picture according to the first coordinate information and the second coordinate information;
the comparison module is used for determining enterprise identifications with similarity meeting preset requirements in the candidate enterprise identifications of the identification format based on the first coordinate information and the second coordinate information of the target picture;
and the sending module is used for sending the enterprise identification with the similarity meeting the preset requirement to the client terminal.
Optionally, the layout determining module includes:
the first determining unit is used for determining the relative position, the relative distance and the relative size of the graph and the character according to the first coordinate information and the second coordinate information;
the second determining unit is used for determining the identification format of the target picture according to the relative position, the relative distance and the relative size of the graph and the character;
in a third aspect, the present application provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the above method when executing the computer program.
In a fourth aspect, the present application provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the above method.
The application provides a method for identifying enterprise identifications, which comprises the steps of firstly, obtaining a target picture of a target enterprise; then, respectively determining first coordinate information of a graph and second coordinate information of characters in the target picture, and determining a representation identification format of the target picture according to the first coordinate information and the second coordinate information; and determining enterprise identifications with similarity meeting preset requirements in the candidate enterprise identifications of the identification format according to the first coordinate information and the second coordinate information of the target picture, and finally sending the enterprise identifications with the similarity meeting the preset requirements to a client terminal. According to the enterprise identification recognition method and device, the enterprise identification with the similarity meeting the preset requirement is determined based on the first position information of the graph in the target picture and the second coordinate information of the characters in the target picture, so that the user can obtain the enterprise identification which is more accurate and meets the preset requirement, and the accuracy of enterprise identification recognition is improved.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a schematic flowchart of an enterprise identifier recognition method according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of a first center point location provided by an embodiment of the present application;
FIG. 3 is a schematic diagram of a second center point location provided by an embodiment of the present application;
fig. 4 is a schematic structural diagram of an apparatus for identifying an enterprise identifier according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of a computer device according to an embodiment of the present application;
fig. 6 is a schematic diagram of an enterprise identifier according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.
Many internet companies in China all form a Logo recognition service scheme to a certain extent, the name of the Logo in a picture can be mainly recognized by current Logo recognition, and information such as positions can be recognized, for example, the Logo in the picture can be recognized as the Logo of a commercial airplane, and the shooting position of the picture and other simple basic information can be recognized.
The embodiment of the application provides an enterprise identifier identification method, as shown in fig. 1, including the following steps:
s101, acquiring a target picture of a target enterprise;
s102, determining first coordinate information of a graph and second coordinate information of characters in the target picture;
s103, determining an identification format of the target picture according to the first coordinate information and the second coordinate information;
s104, determining enterprise identifications with similarity meeting preset requirements in the candidate enterprise identifications of the identification format based on the first coordinate information and the second coordinate information of the target picture;
and S105, sending the enterprise identification with the similarity meeting the preset requirement to the client terminal.
In step S101, the target picture is a picture taken by the user and includes an enterprise identifier, the target enterprise is an enterprise that needs to identify the enterprise identifier, and the enterprise identifier of the target enterprise includes a graphic and a text.
Specifically, the server obtains a target picture of the target enterprise from the sending and obtaining device, where the server may obtain the target picture of the target enterprise from the enterprise identification request sent by the picture obtaining device, and the picture obtaining device may include a smart phone, a camera, and the like, which is not limited in this application. The target picture in the picture acquisition device is obtained by any one of the following methods:
directly acquiring a target picture through a camera of picture acquisition equipment; after a picture is acquired through a camera of the picture acquisition equipment, a target picture is obtained by cutting the picture; or the target picture is acquired through an enterprise identification recognition program operated in the picture acquisition equipment.
After a user acquires a target picture through picture acquisition equipment, the target picture is uploaded to a server through a network, the target picture is compressed to a preset size, such as 200k, before the target picture is uploaded to the server, the picture is converted through a binary picture converter, the picture is uploaded to the server in a binary stream mode, transmission speed can be improved, after the server receives the compressed target picture, subsequent steps S102-S105 are executed based on the compressed target picture, and analysis speed of the target picture is improved in an image identification process.
In step S102, the first coordinate information is first coordinate information for identifying the graph in the target picture through the graph identification model, and the first coordinate information includes first vertex coordinate information of a circumscribed rectangle of the graph. The second coordinate information is the second coordinate information of the characters identified in the target picture through a character identification model, and the second coordinate information comprises the second vertex coordinate information of the circumscribed rectangle of the characters.
Specifically, a target picture is respectively input into a graph recognition model and a character recognition model, and first coordinate information corresponding to a graph in the target picture and second coordinate information corresponding to characters in the target picture are obtained.
The pattern recognition model is obtained by training through the following steps:
step 1021, acquiring a picture training sample set; the target picture training sample set comprises at least one training sample, the training sample set comprises training pictures and first coordinate information of graphs in the training pictures, and each training sample in the target picture training sample set is a target picture corresponding to the same enterprise identifier;
and 1022, for each training sample, inputting the training picture in the training sample to the pattern recognition model to be trained as a positive sample, inputting the first coordinate information of the pattern in the training picture to the pattern recognition model to be trained as a negative sample, and training the pattern recognition model to be trained.
In the above steps 1021 to 1022, the present application is further provided with a database, the database stores training samples for training the pattern recognition model, a plurality of training samples jointly form a pattern training sample set, when the pattern recognition model to be trained is trained, the training picture is input into the pattern recognition model to be trained, the pattern recognition model to be trained outputs a recognition result of the first coordinate information, the recognition result is compared with the first coordinate information of the pattern in the training picture of the training sample, if the difference of the comparison results is large, the pattern recognition model to be trained needs to be adjusted, if the difference of the comparison results is small, the training precision of the pattern recognition model to be trained is higher and higher, and when the comparison result meets the preset requirement, namely the difference is smaller than a certain threshold value, the training of the pattern recognition model to be trained is finished.
The character recognition model is obtained by training through the following steps:
step 1023, a text training sample set is obtained; the character training sample set comprises at least one training sample, the training sample set comprises training characters and second coordinate information of the training characters, and each training sample in the target picture training sample set is a target picture corresponding to the same enterprise identifier;
and 1024, aiming at each training sample, inputting the training characters in the training samples into the character recognition model to be trained as positive samples, inputting the second coordinate information of the characters in the training characters into the character recognition model to be trained as negative samples, and training the character recognition model to be trained.
In the above steps 1023 to 1024, the database of the present application further stores training samples for training the character recognition model, a plurality of training samples jointly form a character training sample set, when the character recognition model to be trained is trained, the training characters are input into the character recognition model to be trained, the character recognition model to be trained outputs a recognition result of the second coordinate information, the recognition result is compared with the second coordinate information of the characters in the training characters of the training sample, if the difference of the comparison results is large, the character recognition model to be trained needs to be adjusted, if the difference of the comparison results is small, the training precision of the character recognition model to be trained is higher and higher, and when the comparison result meets the preset requirement, namely the difference is smaller than a certain threshold value, the training of the character recognition model to be trained is finished.
In step S103, the mark format is an arrangement format of the graphics and the text in the enterprise mark, such as left-right arrangement, up-down arrangement, and the like. In order to distinguish the branch companies, enterprise identifications corresponding to the branch companies have certain differences, wherein the differences can be different in identification formats, or different in first coordinate information of a figure or second coordinate information of a character under the same identification format.
Specifically, the position of the graphic in the target picture and the position of the character in the target picture can be determined according to the first coordinate information of the graphic and the second coordinate information of the character in the target picture, and then the identification version of the target picture is determined according to the position of the graphic and the position of the character.
In step S104, the candidate enterprise id is a preset standard enterprise id.
Specifically, the server stores enterprise identifiers corresponding to a plurality of branch companies of the same enterprise. And screening candidate enterprise identifications corresponding to the identification formats from all the candidate enterprise identifications, calculating the similarity between the enterprise identifications in the target picture and the candidate enterprise identifications corresponding to the identification formats based on the first coordinate information and the second coordinate information of the target picture, and determining the enterprise identifications with the similarity meeting the preset requirements from the candidate enterprise identifications corresponding to the identification formats according to the calculated similarity.
For example, when the target enterprise is enterprise C, enterprise C includes multiple versions of enterprise identities: the enterprise identifications of all the versions are used as candidate enterprise identifications to be compared with the identification format of the target picture to calculate similarity, the identification versions of the target picture are respectively compared with the versions 1, 2 and 3 … … in the candidate enterprise identifications one by one to obtain corresponding similarity numerical values q1, q2 and q3 … …, then the similarity numerical values q1, q2 and q3 … … are respectively compared with preset results, if the numerical values of which the similarity numerical values meet preset requirements are q2 and q5, the versions 2 and 5 in the candidate enterprise identifications serve as enterprise identifications of which the similarity meets the preset requirements.
The first coordinate information of the graph determined by the graph recognition model and the second coordinate information of the character determined by the character recognition model may be different from the real coordinate information to some extent, that is, the similarity between the enterprise identifier in the target picture and the candidate enterprise identifier corresponding to the identifier format may not reach 100%, and therefore, a certain fault tolerance rate is required to determine the enterprise identifier. Determining an enterprise identifier which is more similar to the version identifier of the target picture from the version 2 and the version 5 of the candidate enterprise identifiers according to a preset fault tolerance rate, wherein the fault tolerance rate is a range in which errors are allowed to occur when calculating a similarity value, and specifically, when the similarity value q2 is 85%, the fault tolerance rate is 15%; when the value q5 of the similarity is 90%, the fault tolerance is 10%, and the enterprise id closer to the version id of the target picture is the enterprise id of version 5 corresponding to the value q5 of the similarity.
In the step 105, the client terminal is configured to receive and display an enterprise identifier whose similarity meets a preset requirement, where the client terminal may include a smart phone, a tablet, and the like, and the application is not limited thereto.
Specifically, the server sends the enterprise identifier with the similarity meeting the preset requirement to the client terminal, and when the server sends the enterprise identifier with the similarity meeting the preset requirement to the client terminal, the server can carry the information of the corresponding company: for example, the company name, the company location, and other information, after receiving the enterprise identifier whose similarity meets the preset requirement, the client terminal can help the client to quickly obtain the company information corresponding to the brand information, promote the conversion of the client to the investor, and realize the cooperation between the client and the company, or when the client is a consumer and the experience of the client is poor, the client can complain about the company according to the company information carried in the enterprise identifier sent by the server, thereby solving the problem that the client wants to solve, or providing more professional services for the client, and the like.
According to the method for identifying the enterprise logo, provided by the embodiment of the application, through the five steps, the server processes the target picture to obtain the first coordinate information about the graph and the second coordinate information about the character, the version logo of the target picture is determined based on the first coordinate information and the second coordinate information, and then the enterprise logo with the similarity meeting the requirement is obtained by screening the candidate enterprise logo corresponding to the version logo for the user, so that the enterprise logo of the more accurate version is received by the user, and the accuracy rate of the enterprise logo of the target picture corresponding to the logo version is improved.
However, when the candidate enterprise id corresponding to the id format is compared with the enterprise id of the target picture, there may be a plurality of enterprise ids whose similarities meet the preset requirement, and at least two similarity values are the same, based on the above situation, the present application provides a more detailed identification method, where the identification method includes:
step 106, determining shape information of the graph and content information of the characters in the target picture;
step S105, including:
step 1051, determining a target enterprise identifier which is the same as the shape information of the graph and the content information of the characters in the target picture in the enterprise identifiers with the similarity meeting the preset requirement;
step 1052, sending the target enterprise identity to the client terminal.
In step 106, the first coordinate information of the graph in the target picture is determined by using the graph recognition model, and the graph recognition model also recognizes the shape information of the graph in the target picture. And determining second coordinate information of the characters in the target picture by using the character recognition model, and recognizing content information of the characters in the target picture by using the character recognition model. The shape information of the graph is the specific shape of the graph, and may be a triangle, a rectangle, a square, etc., and the content information of the characters is all characters contained in the character part, and may be english, chinese, etc.
In the step 1051, the shapes of the graphics and all the characters included in the character part are recognized by the two enterprise logos with the same similarity value, the shapes of the graphics and all the characters included in the character part of each enterprise logo are compared with the shapes of the graphics and all the characters of the character part of the target picture, and the enterprise logo with the same shape information of the graphics and the same content information of the characters in the target picture is selected as the target enterprise list logo.
In the above step 1052, the target enterprise id is an enterprise id that is the same as the shape information of the graph and the content information of the text in the target picture, which are screened out from the enterprise ids whose similarity meets the preset requirement.
Specifically, the enterprise identifier which is the same as the shape information of the graph and the content information of the characters in the target picture is used as the target enterprise identifier and sent to the client terminal.
In order to understand the process of determining the version identifier of the target picture from the first coordinate information and the second coordinate information in more detail, step S103 includes:
step 1031, determining the relative orientation, relative distance and relative size of the graph and the characters according to the first coordinate information and the second coordinate information;
and 1032, determining the identification format of the target picture according to the relative position, relative distance and relative size of the graph and the characters.
In the above step 1031, the relative orientation may be the position of the character corresponding to the graphic, or the position of the graphic with respect to the character; the relative distance is a straight line distance between the graph and the character; the relative size is a ratio of the size of the figure to the size of the text, and may also be a ratio of the size of the text to the size of the figure.
In a possible embodiment, the first coordinate information includes first vertex coordinate information of a circumscribed rectangle of the figure, and the second coordinate information includes second vertex coordinate information of a circumscribed rectangle of the text;
when the step 1031 is executed to determine the relative orientations and relative distances between the graphics and the characters according to the first coordinate information and the second coordinate information, the steps may be specifically executed according to the following steps:
step 10311, determining a first central point position of the circumscribed rectangle of the graph according to the first vertex coordinate information of the circumscribed rectangle of the graph;
step 10312, determining a second central point position of the circumscribed rectangle of the characters according to the second vertex coordinate information of the circumscribed rectangle of the characters;
and 10313, determining the relative position and the relative distance between the graph and the character according to the first central point position and the second central point position.
In step 10311, the first vertex coordinate information includes coordinate information of four vertices of the circumscribed rectangle of the graph, and the first central point is a position where a central point of the circumscribed rectangle of the graph is located.
Specifically, the external rectangle where the graph is located is determined, then four coordinate vertexes of the external rectangle are determined, corresponding central points are calculated according to the four coordinate vertexes, and the central points are used as first central point positions of the external rectangle.
For example, as shown in fig. 2, four vertices of the circumscribed rectangle of the graph are a, b, c, and d, respectively, and the coordinate of the center point of the circumscribed rectangle of the graph is calculated as e based on the coordinates of the four vertices, where the center point e is the first center point position of the circumscribed rectangle of the graph.
In step 10312, the second vertex coordinate information includes coordinate information of four vertices of the circumscribed rectangle of the character, and the second central point is a position where a central point of the circumscribed rectangle of the character is located.
Specifically, the external rectangle where the character is located is determined, then four coordinate vertexes of the external rectangle are determined, corresponding central points are calculated according to the four coordinate vertexes, and the central points are used as second central point positions of the external rectangle.
For example, as shown in fig. 3, four vertices of the circumscribed rectangle of the character are a1, b1, c1, and d1, respectively, the coordinates of the center point of the circumscribed rectangle of the character are calculated as e1 based on the coordinates of the four vertices, and the center point e1 is the second center position of the circumscribed rectangle of the character.
In step 10313, the relative orientations and relative distances of the pictures and the characters are determined according to the positions of the first center point and the second center point.
Specifically, the distance between the two center points of the first center point and the second center point is used as the relative distance between the picture and the text, and the relative orientation between the picture and the text is determined based on the positions of the two center points in the target picture.
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, and 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 abscissa of the first center point e is the same as the abscissa of the second center point e1, the text is located on the right side or the left side of the picture; when the ordinate of the first center point e is the same as the ordinate of the second center point e1, the caption is located below or above the picture.
In another possible embodiment, the first coordinate information includes first vertex coordinate information of a circumscribed rectangle of the figure, and the second coordinate information includes second vertex coordinate information of a circumscribed rectangle of the text;
when the step 1031 is executed to determine the relative sizes of the graphics and the characters according to the first coordinate information and the second coordinate information, the steps may be specifically executed according to the following steps:
step 10314, determining lengths and widths corresponding to the graph and the characters respectively according to first vertex coordinate information of the circumscribed rectangle of the graph and second vertex coordinate information of the circumscribed rectangle of the characters;
and step 10315, determining the relative sizes of the graphics and the characters according to the lengths and the widths respectively corresponding to the graphics and the characters.
In step 10314, the length and width corresponding to the graph are respectively the length and width of the circumscribed rectangle where the graph is located; the length and width of the graph are calculated based on four vertexes of a circumscribed rectangle where the graph is located. The length and the width corresponding to the characters are respectively the length and the width of the circumscribed rectangle where the characters are located, and the length and the width of the characters are obtained by calculation based on four vertexes of the circumscribed rectangle where the characters are located.
Specifically, firstly, determining a circumscribed rectangle of the graph, then determining four vertexes of the circumscribed rectangle of the graph as a, b, c and d respectively, wherein the absolute value of a horizontal coordinate difference value calculated according to the vertexes a and b or two vertexes of c and d of the circumscribed rectangle of the graph is the length of the circumscribed rectangle of the graph, and the absolute value of a vertical coordinate difference value calculated according to the vertexes a and c or two vertexes of b and d is the width of the circumscribed rectangle of the graph; similarly, the circumscribed rectangle of the character is determined, then four vertexes of the circumscribed rectangle of the character are respectively determined to be a1, b1, c1 and d1, the absolute value of the difference value of the vertical coordinates calculated according to the vertexes a1 and b1 or two vertexes c1 and d1 of the circumscribed rectangle of the character is the length of the circumscribed rectangle of the character, and the absolute value of the difference value of the vertical coordinates calculated according to the vertexes a1 and c1 or two vertexes b1 and d1 of the circumscribed rectangle of the character is the width of the circumscribed rectangle of the character.
Taking a vertex a and a vertex b of four vertices of a circumscribed rectangle of the graph as an example, the abscissa of the vertex a is x1, the abscissa of the vertex b is x2, and the absolute value of the difference between x1 and x2 is the length of the graph, taking a vertex a and a vertex c of four vertices of a circumscribed rectangle of the graph as an example, the ordinate of the vertex a is y1, and the ordinate of the vertex c is y3, then the absolute value of the difference between y1 and y3 is the width of the graph; similarly, taking the vertex a1 and the vertex b1 of the four vertices of the circumscribed rectangle of the character as an example, the abscissa of the vertex a1 is xa, the abscissa of the vertex b1 is xb, and the absolute value of the difference between xa and xb is the length of the character, taking the vertex a1 and the vertex c1 of the four vertices of the circumscribed rectangle of the character as an example, the ordinate of the vertex a1 is ya, and the ordinate of the vertex c1 is yc, then the absolute value of the difference between ya and yc is the width of the character.
In step 10315, the relative size of the graphics and the characters refers to the ratio of the size of the graphics to the size of the characters, or may be the ratio of the size of the characters to the size of the graphics.
Specifically, the width of the picture is taken as a reference, the relative size of the graph and the text can be a ratio of the width of the graph to the length of the text, and a ratio is obtained by calculation according to the width of the picture and the length of the text, and the ratio is the relative size of the graph and the text.
For example, as shown in FIG. 6, when the width of the picture is A and the length of the text is 7A, the ratio of the width of the graphic to the length of the text is
Then the length of the text is 7 times the width of the graphic.
In step 1032, the identification format of the target picture is determined according to the relative position, relative distance and relative size of the picture and the text.
Specifically, the identification format of the target picture is determined according to which orientation of the character the graphic is located in, and the distance between the center position of the picture and the center position of the character as relative distances, and according to the ratio of the size of the graphic to the size of the character.
For example, when the distance between the center position of the figure and the center position of the character is a, the length of the character is 7 times the width of the figure, and the figure is positioned above the character, so as to determine the corresponding identification format of the target picture.
The method for identifying the enterprise identifier provided by the embodiment of the application comprises the following steps: acquiring a target picture of a target enterprise; determining first coordinate information of a graph and second coordinate information of characters in a target picture, determining an identification format of the target picture based on the first coordinate information and the second coordinate information of the target picture, comparing the similarity with candidate enterprise identifications according to the first coordinate information and the second coordinate information when selecting the candidate enterprise identifications, and sending the enterprise identifications with the similarity meeting preset requirements to a user. By the method, the enterprise identifications with similar formats can be distinguished and distinguished, and more accurate enterprise identifications are recommended for users.
Referring to fig. 4, a schematic structural diagram of an apparatus 400 for identifying an enterprise identifier according to an embodiment of the present application is shown, where the apparatus includes: the system comprises an acquisition module 401, a position determination module 402, a format determination module 403, a comparison module 404, and a sending module 405, specifically:
an obtaining module 401, configured to obtain a target picture about a target enterprise;
a position determining module 402, configured to determine first coordinate information of a graphic and second coordinate information of a text in the target picture;
a format determining module 403, configured to determine an identifier format of the target picture according to the first coordinate information and the second coordinate information;
a comparing module 404, configured to determine, based on the first coordinate information and the second coordinate information of the target picture, an enterprise identifier whose similarity meets a preset requirement from among candidate enterprise identifiers of the identifier format;
a sending module 405, configured to send the enterprise identifier whose similarity meets a preset requirement to the client terminal.
Optionally, the layout determining module includes:
the first determining unit is used for determining the relative position, the relative distance and the relative size of the graph and the character according to the first coordinate information and the second coordinate information;
and the second determining unit is used for determining the identification format of the target picture according to the relative position, the relative distance and the relative size of the graph and the character.
Optionally, the first determining unit includes:
the third determining unit is used for determining the position of a first central point of the circumscribed rectangle of the graph according to the first vertex coordinate information of the circumscribed rectangle of the graph;
a fourth determining unit, configured to determine a second central point position of the circumscribed rectangle of the text according to second vertex coordinate information of the circumscribed rectangle of the text;
and the fifth determining unit is used for determining the relative position and the relative distance between the graph and the character according to the first central point position and the second central point position.
Optionally, the first determining unit includes:
a sixth determining unit, configured to determine, according to the first vertex coordinate information of the circumscribed rectangle of the graphic and according to the second vertex coordinate information of the circumscribed rectangle of the text, a length and a width corresponding to the graphic and the text, respectively;
and the seventh determining unit is used for determining the relative sizes of the graph and the characters according to the lengths and the widths corresponding to the graph and the characters respectively.
Optionally, the apparatus further includes:
the information determining module is used for determining the shape information of the graph and the content information of the characters in the target picture;
the sending module comprises:
an eighth determining unit, configured to determine, in the enterprise identifiers whose similarity meets a preset requirement, a target enterprise identifier that is the same as shape information of a graph and content information of a character in the target picture;
and the sending unit is used for sending the target enterprise identification to the client terminal.
Optionally, the position determining module includes:
the first identification unit is used for identifying first coordinate information of the graph in the target picture by utilizing a graph identification model;
and the second identification unit is used for identifying second coordinate information of the graph in the target picture by utilizing a character identification model.
Corresponding to the method for identifying an enterprise identifier in fig. 1, an embodiment of the present application further provides a computer device 500, as shown in fig. 5, the device includes a memory 501, a processor 502, and a computer program stored on the memory 501 and executable on the processor 502, where the processor 502 implements the steps of the method for feeding back an enterprise identifier when executing the computer program.
Specifically, the memory 501 and the processor 502 can be general memories and processors, which are not specifically limited herein, and when the processor 502 runs the computer program stored in the memory 501, the method for identifying the enterprise identifier can be executed, which solves the problem in the prior art of how to provide a more accurate enterprise identifier for a user, and first, a target picture about a target enterprise is obtained; then, determining first coordinate information of a graph and second coordinate information of characters in a target picture by using a picture recognition model and a character recognition model respectively, then determining a format of the target picture according to the first coordinate information and the second coordinate information, then screening out enterprise identifications meeting the similarity requirement from candidate enterprise identifications according to the first coordinate information and the second coordinate information of the target picture, and finally sending the enterprise identifications meeting the preset requirement of the similarity to a user, so that the user can receive more accurate enterprise identifications and provide more accurate enterprise related information for the user.
Corresponding to the method for identifying an enterprise identifier in fig. 1, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the steps of the method for identifying an enterprise identifier.
Specifically, the storage medium can be a general storage medium, such as a mobile disk, a hard disk, and the like, and when a computer program on the storage medium is run, the method for identifying the enterprise identifier can be executed, so that the problem of how to provide a more accurate enterprise identifier for a user in the prior art is solved, and first, a target picture about a target enterprise is obtained; then, determining first coordinate information of a graph and second coordinate information of characters in a target picture by using a picture recognition model and a character recognition model respectively, then determining a format of the target picture according to the first coordinate information and the second coordinate information, then screening out enterprise identifications meeting the similarity requirement from candidate enterprise identifications according to the first coordinate information and the second coordinate information of the target picture, and finally sending the enterprise identifications meeting the preset requirement of the similarity to a user, so that the user can receive more accurate enterprise identifications and provide more accurate enterprise related information for the user.
In the embodiments provided in the present application, it should be understood that the disclosed method and apparatus may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus once an item is defined in one figure, it need not be further defined and explained in subsequent figures, and moreover, the terms "first", "second", "third", etc. are used merely to distinguish one description from another and are not to be construed as indicating or implying relative importance.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present application, and are used for illustrating the technical solutions of the present application, but not limiting the same, and the scope of the present application is not limited thereto, and although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope disclosed in the present application; such modifications, changes or substitutions do not depart from the spirit and scope of the present disclosure, which should be construed in light of the above teachings. Are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A method for identifying an enterprise logo is characterized by comprising the following steps:
acquiring a target picture about a target enterprise;
determining first coordinate information of a graph and second coordinate information of characters in the target picture;
determining an identification format of the target picture according to the first coordinate information and the second coordinate information;
determining enterprise identifications with similarity meeting preset requirements in the candidate enterprise identifications of the identification format based on the first coordinate information and the second coordinate information of the target picture;
and sending the enterprise identification with the similarity meeting the preset requirement to a client terminal.
2. The identification method according to claim 1, wherein the determining the identification format of the target picture according to the first coordinate information and the second coordinate information comprises:
determining the relative position, relative distance and relative size of the graph and the character according to the first coordinate information and the second coordinate information;
and determining the identification format of the target picture according to the relative position, relative distance and relative size of the graph and the characters.
3. The recognition method according to claim 2, wherein the first coordinate information includes first vertex coordinate information of a circumscribed rectangle of the figure, and the second coordinate information includes second vertex coordinate information of a circumscribed rectangle of the character; determining the relative position and the relative distance between the graph and the character according to the first coordinate information and the second coordinate information, wherein the determining comprises the following steps:
determining a first central point position of the circumscribed rectangle of the graph according to the first vertex coordinate information of the circumscribed rectangle of the graph;
determining a second central point position of the circumscribed rectangle of the character according to the second vertex coordinate information of the circumscribed rectangle of the character;
and determining the relative position and the relative distance between the graph and the character according to the position of the first central point and the position of the second central point.
4. The recognition method according to claim 2, wherein the first coordinate information includes first vertex coordinate information of a circumscribed rectangle of the figure, and the second coordinate information includes second vertex coordinate information of a circumscribed rectangle of the character; determining the relative sizes of the graph and the characters according to the first coordinate information and the second coordinate information, wherein the relative sizes comprise:
determining the length and the width corresponding to the graph and the characters respectively according to the first vertex coordinate information of the circumscribed rectangle of the graph and the second vertex coordinate information of the circumscribed rectangle of the characters;
and determining the relative sizes of the graph and the characters according to the length and the width respectively corresponding to the graph and the characters.
5. The identification method according to claim 1, characterized in that the identification method further comprises:
determining shape information of the graph and content information of the characters in the target picture;
and sending the enterprise identification with the similarity meeting the preset requirement to a client terminal, wherein the method comprises the following steps:
determining a target enterprise identifier which is the same as the shape information of the graph and the content information of the characters in the target picture in the enterprise identifiers with the similarity meeting the preset requirement;
and sending the target enterprise identification to the client terminal.
6. The identification method according to claim 1, wherein the determining first coordinate information of a graphic and second coordinate information of a text in the target picture comprises:
identifying first coordinate information of the graph in the target picture by utilizing a graph identification model;
and recognizing second coordinate information of the graph in the target picture by using a character recognition model.
7. An apparatus for identifying an enterprise logo, comprising:
the acquisition module is used for acquiring a target picture about a target enterprise;
the position determining module is used for determining first coordinate information of a graph and second coordinate information of characters in the target picture;
the format determining module is used for determining the identification format of the target picture according to the first coordinate information and the second coordinate information;
the comparison module is used for determining enterprise identifications with similarity meeting preset requirements in the candidate enterprise identifications of the identification format based on the first coordinate information and the second coordinate information of the target picture;
and the sending module is used for sending the enterprise identification with the similarity meeting the preset requirement to the client terminal.
8. The recognition apparatus of claim 7, wherein the layout determination module comprises:
the first determining unit is used for determining the relative position, the relative distance and the relative size of the graph and the character according to the first coordinate information and the second coordinate information;
and the second determining unit is used for determining the identification format of the target picture according to the relative position, the relative distance and the relative size of the graph and the character.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of any of the preceding claims 1-6 are implemented by the processor when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, is adapted to carry out the steps of the method of any one of the preceding claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111129020.5A CN113792735A (en) | 2021-09-26 | 2021-09-26 | Enterprise identifier identification method, enterprise identifier identification device, enterprise identifier identification equipment and enterprise identifier identification medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111129020.5A CN113792735A (en) | 2021-09-26 | 2021-09-26 | Enterprise identifier identification method, enterprise identifier identification device, enterprise identifier identification equipment and enterprise identifier identification medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113792735A true CN113792735A (en) | 2021-12-14 |
Family
ID=79184361
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111129020.5A Pending CN113792735A (en) | 2021-09-26 | 2021-09-26 | Enterprise identifier identification method, enterprise identifier identification device, enterprise identifier identification equipment and enterprise identifier identification medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113792735A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080065611A1 (en) * | 1999-07-22 | 2008-03-13 | Markmonitor Inc. | Method and system for searching and monitoring internet trademark usage |
| CN107705347A (en) * | 2017-09-12 | 2018-02-16 | 方家齐 | One Trademark design accessory system |
| CN110196917A (en) * | 2019-05-30 | 2019-09-03 | 厦门一品威客网络科技股份有限公司 | Personalized LOGO format method for customizing, system and storage medium |
| CN112580620A (en) * | 2020-12-25 | 2021-03-30 | 北京百度网讯科技有限公司 | Sign picture processing method, device, equipment and medium |
-
2021
- 2021-09-26 CN CN202111129020.5A patent/CN113792735A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080065611A1 (en) * | 1999-07-22 | 2008-03-13 | Markmonitor Inc. | Method and system for searching and monitoring internet trademark usage |
| CN107705347A (en) * | 2017-09-12 | 2018-02-16 | 方家齐 | One Trademark design accessory system |
| CN110196917A (en) * | 2019-05-30 | 2019-09-03 | 厦门一品威客网络科技股份有限公司 | Personalized LOGO format method for customizing, system and storage medium |
| CN112580620A (en) * | 2020-12-25 | 2021-03-30 | 北京百度网讯科技有限公司 | Sign picture processing method, device, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109670591B (en) | Neural network training method and image matching method and device | |
| CN105338479B (en) | Information processing method and device based on places | |
| CN103377287B (en) | A kind of method and apparatus throwing in Item Information | |
| EP3660703A1 (en) | Method, apparatus, and system for identifying device, storage medium, processor, and terminal | |
| CN106933867B (en) | Image query method and device | |
| JP5983540B2 (en) | Medium or function identification method and program, article including marker, and marker arrangement method | |
| CN105808681B (en) | Published information viewing method and system based on electronic map and mobile positioning | |
| CN112100422A (en) | Engineering drawing processing method, device, equipment and storage medium | |
| CN113223013B (en) | Method, device, equipment and storage medium for pulmonary vessel segmentation positioning | |
| CN103425982A (en) | Information processing apparatus, information processing method, and program | |
| CN104657389A (en) | Positioning method, system and mobile terminal | |
| CN108614895B (en) | Abnormal data access behavior identification method and data processing device | |
| KR20220098315A (en) | Image processing method and apparatus, electronic device and recording medium | |
| CN111652144B (en) | Question segmentation method, device, equipment and medium based on target area fusion | |
| CN112598805A (en) | Prompt message display method, device, equipment and storage medium | |
| CN108664860B (en) | Method and device for identifying room plan | |
| CN113762309A (en) | Object matching method, device and equipment | |
| CN113792735A (en) | Enterprise identifier identification method, enterprise identifier identification device, enterprise identifier identification equipment and enterprise identifier identification medium | |
| CN105787111A (en) | Private map making method based on user interest | |
| CN111598090A (en) | Method for identifying mark on printed circuit board and related equipment | |
| CN106547891A (en) | For the quick visualization method of the pictured text message of palm display device | |
| CN110413819B (en) | Method and device for acquiring picture description information | |
| CN107526489B (en) | Picture adjusting method and device | |
| CN112381162B (en) | Information point identification method and device and electronic equipment | |
| CN115034177A (en) | Presentation file conversion method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |