WO2021046801A1

WO2021046801A1 - Image recognition method, apparatus and device, and storage medium

Info

Publication number: WO2021046801A1
Application number: PCT/CN2019/105693
Authority: WO
Inventors: 赵利伟
Original assignee: 鸿合科技股份有限公司
Priority date: 2019-09-12
Filing date: 2019-09-12
Publication date: 2021-03-18

Abstract

An image recognition method, apparatus and device, and a storage medium, belonging to the field of image processing. The method comprises: acquiring the name of an object to be recognized in an image (S1); and on the basis of the name of the object to be recognized, using a preset library to obtain association information of the object to be recognized, wherein the preset library stores the name of the object to be recognized and association information corresponding thereto (S2). A user uploads an image to an electronic device, and the electronic device obtains the name of an object to be recognized in the image, and then obtains association information of the object to be recognized in the preset library according to the name of the object to be recognized, and displays the association information of the object to be recognized to the user; therefore, it is convenient for users to obtain more association information of the object to be recognized.

Description

Image recognition method, device, equipment and storage medium

Technical field

This application relates to the field of image processing technology, in particular to an image recognition method, device, equipment, and storage medium.

Background technique

Image recognition refers to the use of computers to process, analyze, and understand images to identify targets and objects in various patterns. With the continuous advancement of science and technology, image recognition is increasingly used in people’s daily work. For example, in a traffic scene, after a capture machine captures an image of a vehicle, it can recognize the license plate of the image to obtain the license plate number of the vehicle. . However, in the prior art, the information that the user can obtain from the image recognition result is limited, which is not conducive to the user's information acquisition.

Summary of the invention

In view of this, this application proposes an image recognition method, device, equipment, and storage medium, with the purpose of obtaining more information about the object to be recognized.

Based on the foregoing objectives, the first aspect of the present application provides an image recognition method, which includes:

Obtain the name of the object to be identified in the image;

Based on the name of the object to be identified, a preset library is used to obtain the associated information of the object to be identified; the preset library stores the name of the object to be identified and its corresponding associated information.

Optionally, the obtaining the associated information of the object to be identified by using a preset library based on the name of the object to be identified includes: transmitting the name of the object to be identified to a server storing the preset library , So that the server determines the associated information of the object to be identified through the preset library; and receives the associated information of the object to be identified fed back by the server.

Optionally, the obtaining the name of the object to be recognized in the image includes: obtaining the object to be recognized from the image; matching the object to be recognized with a preset object in a database; If the preset object matches the object to be identified, the name of the object to be identified is determined based on the matching result.

Optionally, the method further includes: if there is no preset object matching the object to be recognized in the database, outputting prompt information; and obtaining a new preset object that can be matched with the object to be recognized And its name; storing the new preset object and its name in the database.

Optionally, the method further includes: displaying the image, the name of the object to be identified, and the associated information.

Optionally, the displaying the image, the name of the object to be identified, and the associated information includes: generating a label of the object to be identified, the label including the name of the object to be identified and the associated information Information; display the image, and display the label in a preset area of the image.

Optionally, the displaying the image, the name of the object to be identified, and the associated information before further includes: matching the object to be identified with a pre-obtained sensitive object; if the object to be identified is If the sensitive object is not matched successfully, the display of the image, the name of the object to be identified, and the associated information is executed.

Based on the same inventive concept, the second aspect of the present application provides an image recognition device, which includes:

The name determination module is used to obtain the name of the object to be identified in the image;

The associated information acquisition module is configured to use a preset library to obtain the associated information of the object to be identified based on the name of the object to be identified; the preset library stores the name of the object to be identified and its corresponding associated information .

Based on the same inventive concept, the third aspect of the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and running on the processor. The processor executes the program as follows Any one of the image recognition methods provided in the first aspect of the present application.

Based on the same inventive concept, the fourth aspect of the present application provides a non-transitory computer-readable storage medium, the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to make the computer execute Any one of the image recognition methods provided in the first aspect of the present application.

It can be seen from the above that the image recognition method, device, equipment and storage medium provided by this application first obtain the name of the object to be recognized in the image, and then use the name of the object to be recognized and its corresponding associated information to be stored In this solution, the user uploads the image to the electronic device, and the electronic device obtains the name of the object to be identified in the image, and then obtains the name of the object to be identified in the preset library according to the name of the object to be identified. The associated information of the object, and the associated information of the object to be identified is displayed to the user, so that the user can obtain more associated information of the object to be identified.

Description of the drawings

In order to more clearly describe the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only These are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

FIG. 1 is a schematic flowchart of an image recognition method provided by an embodiment of the application;

Figure 2 is a display effect diagram provided by an embodiment of the application;

Figure 3 is an explanation of step S1 in Figure 1;

FIG. 4 is a hardware architecture diagram shown in an exemplary embodiment of this application;

FIG. 5 is a schematic structural diagram of an image recognition device provided by an embodiment of the application.

detailed description

In order to make the objectives, technical solutions, and advantages of the present application clearer, the following further describes the present application in detail in conjunction with specific embodiments and with reference to the accompanying drawings.

It should be noted that all the expressions "first" and "second" used in the examples of this application are used to distinguish two entities with the same name but not the same or parameters that are not the same, as shown in "first" and "second" Only for the convenience of presentation, it should not be construed as a limitation to the embodiments of the present application, and subsequent embodiments will not describe this one by one.

In some existing solutions, when performing image recognition, only the basic information (such as the name) of the object to be recognized in the image can be recognized, and the user needs to search separately to obtain other related information of the object to be recognized.

For example, when a user sees a new car he likes, he takes a picture of the car, and then uses the existing image recognition technology to recognize the car picture, only the brand, model and other information of the car can be obtained. If the user wants to obtain this When car performance parameters, 4S shop quotation and other information, you also need to enter the car brand, model and other information in the search engine to perform a second search, but can not only obtain the relevant information of the car through the existing image recognition technology, increase the operation The cumbersomeness reduces the efficiency of information acquisition.

Or, when the user sees a singer’s poster, he takes a picture of the singer, and then uses the existing image recognition technology to identify the singer’s picture. Only the name of the singer can be obtained. If the user wants to get the singer’s birthday, height and weight, For more information such as education experience, performing arts experience, and recent concerts, the user also needs to enter the singer's name into the search engine for a second search to obtain more related information of the singer, which is cumbersome to operate and inefficient in obtaining information.

In order to solve the above technical problems, the embodiments of the present application provide an image recognition method, device, equipment, and storage medium. After obtaining the name of the object to be recognized in the image, use a preset library to continue to obtain the associated information of the object to be recognized, which can The associated information corresponding to the object to be identified is directly provided to the user, and the user can obtain more information about the object to be identified in the picture, which is convenient for the user to obtain information.

For ease of understanding, the image recognition method will be described in detail below in conjunction with the accompanying drawings.

FIG. 1 is a schematic flowchart of an image recognition method provided by an embodiment of the application. The method includes:

S1. Obtain the name of the object to be identified in the image.

In the embodiment of the present application, the image uploaded by the user is received, and then the object to be recognized in the image is obtained. The object to be recognized is the object that is expected to be recognized in the image. In practical applications, when the image is a street view, the object to be recognized can be a vehicle, and when the image is a natural scenery, the object to be recognized can be trees, flowers, animals, etc. The specifics are not limited.

In a possible situation, according to the conventional shooting operation, the user generally places the desired recognition object in the central area of the captured image when shooting the object that the user desires to recognize. After receiving the image uploaded by the user, the central area of the image can be intercepted as The object to be recognized, for example, the area of one-half of the center of the intercepted image, the area of one-third, the area of two-thirds, etc. are taken as the object to be recognized, which is not specifically limited. In another case, the user can also specify the object to be recognized in the image.

In actual applications, there may be multiple objects in the image uploaded by the user. In order to determine the object to be recognized in the image, in a possible situation, when there are multiple objects in the received image, the user can select Determine the object to be identified to be identified, and then determine the name of the object to be identified based on the user's selection. In another possible case, manual settings can be made in advance. When there are multiple objects in the received image, set the same type of objects in the received image to be acquired as the object to be recognized, and then determine the same type of object to be acquired. Names of multiple objects to be identified in the image; for example, all trees, all vehicles, all animals, or all flowers in the image can be set to obtain, and the specifics are not limited.

In order to obtain more related information of the object to be identified, the name of the object to be identified needs to be further determined. The object to be identified can be directly received, the name of the object to be identified can be determined, and the name of the object to be identified can also be directly obtained, which is not limited here. The name can be a Chinese name, or it can include both a Chinese name and a foreign name, such as English name, Russian name, Japanese name, Korean name, etc., and the specific name is not limited. After obtaining the name of the object to be identified, any image recognition technology can be used to obtain the name of the object to be identified, and the name of the object to be identified can be used to provide users with more relevant information about the object to be identified. A specific example will be combined below. For explanation, I won't repeat it here.

S2. Based on the name of the object to be identified, use a preset library to obtain the associated information of the object to be identified.

In the embodiment of the present application, the preset library is a pre-established library that stores the name of the object to be identified and the corresponding associated information. In order to obtain the associated information of the object to be identified, after the name of the object to be identified is determined, based on the name of the object to be identified, the preset library can be searched to obtain the associated information of the object to be identified; the associated information of the object to be identified, Including but not limited to: the attributes of the object to be identified, the appearance characteristics of the object to be identified, the distribution area of the object to be identified, the classification of the object to be identified, etc., which are not specifically limited.

In some possible implementation manners, the preset library is pre-established locally. After the user uploads the image, the user determines the name of the object to be identified, and then retrieves the associated information corresponding to the object to be identified in the preset library.

In other possible implementation manners, the preset library is stored in a server, and the server may be a third-party server or a cloud server, which is not specifically limited. After determining the name of the object to be identified, the name of the object to be identified is transmitted to the server. The name can be a Chinese name, or it can include both a Chinese name and a foreign name, and the specific is not limited; the server is based on the received name of the object to be identified Retrieve the associated information corresponding to the object to be identified in the preset library, and give feedback.

Then, based on the name of the object to be identified, using the preset library to obtain the associated information of the object to be identified includes:

The name of the object to be identified is transmitted to the server storing the preset library, so that the server determines the associated information of the object to be identified through the preset library; and the associated information of the object to be identified fed back by the server is received.

In order to obtain the associated information of the object to be identified, the name of the object to be identified is transmitted to the server. A preset library is stored in the server. The server retrieves the associated information of the object to be identified in the preset library and gives feedback.

In one case, a preset library is pre-stored in a third-party server, and after determining the name of the object to be identified in the image uploaded by the user, the name of the object to be identified is transmitted to the third-party server, and the third-party server receives the object to be identified After the name of the object, the related information corresponding to the object to be identified is retrieved in the preset library and feedback is given. In this embodiment, it also includes receiving the associated information of the object to be identified fed back by the server.

In practical applications, there may be multiple ways to transmit the name of the object to be identified to a third-party server that stores a preset library, for example, directly transmitting the name of the object to be identified to the third-party server, which is not specifically limited. Then, in some possible implementation manners, the name of the object to be identified is transmitted to the server storing the preset library, so that the server can determine the associated information of the object to be identified through the preset library, including:

The external source interface of the third-party server is called, and the name of the object to be identified is transmitted to the third-party server, so that the third-party server can determine the associated information of the object to be identified through the preset library.

In order to transmit the name of the object to be identified to the third-party server, after determining the name of the object to be identified in the image, the external source interface of the third-party server can be called through an HTTP request. The third-party server has a preset library and a preset library. The related information of the object to be identified is stored inside. For example, the default library can be Baidu Library, CNKI, Douding Library, Daoke Baba, 360doc Personal Library, etc., which are not specifically limited here; obtain third-party servers After the external source interface, the name of the object to be identified is transmitted to the third-party server through the external interface, and the third-party server retrieves the associated information of the object to be identified in the preset library after receiving the name of the object to be identified.

It is understandable that the third-party server retrieves the associated information of the object to be identified in the preset library, without the need to install the preset library locally, so that users can obtain more associated information of the object to be identified, rather than limited to the basic information carried by the image. .

For example, after receiving a picture uploaded by a user and determining that the tree in the picture is the object to be identified, by identifying the tree in the picture, after determining the Chinese name of the tree in the picture, poplar, the external source of the Baidu server is called through an HTTP request Interface, and then transmit the Chinese name poplar of the tree in the picture to the Baidu server through the external interface of the Baidu server. After receiving the Chinese name poplar of the tree in the picture, the Baidu server searches for the association of poplars stored in the Baidu library Information; For example, the related information of poplars is: Populus classification system is divided into five schools: Tacamahaca, Leuce, Aigeiros, Turanga , Leucoides, the trunk is usually straight; the bark is smooth or longitudinally split, often grayish white, mainly distributed in central China, north China, northwest, northeast and other broad areas. The Baidu server searches the poplar related information stored in the Baidu Library and feeds back the searched poplar related information; receives the related information fed back by the Baidu server, and displays the poplar name and its related information in the image, and then The image, the name of the poplar and the related information of the poplar are displayed to the user, and the display effect diagram can be as shown in Fig. 2 to facilitate the user's browsing.

In another case, a preset library is pre-stored in the cloud server, and after determining the name of the object to be identified in the image uploaded by the user, the name of the object to be identified is transmitted to the cloud server, and the cloud server receives the object to be identified After the name, search the associated information corresponding to the object to be identified in the preset library, and give feedback. In this embodiment, it also includes receiving the associated information of the object to be identified fed back by the server.

In practical applications, any method can be used to transmit the name of the object to be identified to the cloud server storing the preset library, for example, the name of the object to be identified can be directly transmitted to the cloud server, which is not specifically limited. Then, in some possible implementation manners, the name of the object to be identified is transmitted to the server storing the preset library, so that the server can determine the associated information of the object to be identified through the preset library, including:

The communication interface of the cloud server is called, and the name of the object to be identified is transmitted to the cloud server, so that the cloud server can determine the associated information of the object to be identified through the cloud library.

In order to transmit the name of the object to be identified to the cloud server, after determining the name of the object to be identified in the image, you can transfer the name of the object to be identified to the cloud server by calling the communication interface of the cloud server, and the cloud server receives the object to be identified After the name, the associated information of the object to be identified is retrieved in the cloud library, and the associated information of the object to be identified is fed back.

It is understandable that the retrieval of the associated information of the object to be identified through the cloud server in the cloud library facilitates the user to obtain more associated information of the object to be identified, rather than limited to the basic information carried by the image.

After obtaining the associated information based on the name of the object to be identified, the associated information can be directly provided to the user to facilitate the user's information acquisition. In actual applications, the associated information can be provided to the user in any manner, for example, directly displayed to the user, which is not limited here. Then, in some possible implementation manners, the method may also include:

Display the image, the name of the object to be identified and the associated information.

It is understandable that displaying the image, the name of the object to be identified, and the associated information to the user together can facilitate the user to obtain all the information of the object to be identified at one time and improve the user experience.

In practical applications, any method can be used to display the image, the name and associated information of the object to be identified, for example, the name and associated information of the object to be identified are directly displayed in the image, which is not specifically limited here. Then, in some possible implementation manners, the display image, the name and associated information of the object to be recognized may include:

A label of the object to be identified is generated, the label includes the name of the object to be identified and associated information; the image is displayed, and the label is displayed in a preset area of the image.

For the purpose of facilitating the user to quickly and clearly browse the associated information of the object to be identified, the name and associated information of the object to be identified are generated into tags.

For example, in order to display the name and associated information of the object to be identified in the image more clearly and clearly, the label can be divided into the label body and the label content. The label body is located in the image at the position pointing to the object to be identified, so as to achieve The role of pointing and prompting; in practical applications, the label body can be any shape, for example, the label body can be a virtual tail arrow, a dovetail arrow, an arc arrow, etc., which are not specifically limited here. The label content includes the name and associated information of the object to be identified. In actual applications, the label content can be displayed in the image in any shape, for example, it can be in the form of a rectangle label, a rounded rectangle label, a cloud label, an oval label, etc. The label content is displayed in the preset area of the image, which is not specifically limited here.

After generating the label with the name and associated information of the object to be identified, the label is displayed in a preset area in the image. The preset area is an area in the image that does not obscure the object to be identified, for example, the left side of the object to be identified in the image. Or the right side of the object to be identified in the image, etc., which are not specifically limited.

For example, in order to reduce the occlusion of the object to be recognized in the image, the label content can be placed in the lower right corner of the image or the lower left corner of the image, which is not specifically limited. For example, in Fig. 2, a label is generated from the name of the poplar and the associated information of the poplar, and then the label is displayed in the lower left corner of the image to prevent the poplar in the image from being blocked.

It is understandable that the name and associated information of the object to be identified are displayed in the image in the form of tags, which is convenient for the user to browse the associated information of the object to be identified in a simple and clear manner. In practical applications, the received image may be a sensitive image that will spread bad social ethos; then, in some possible implementations, the image, the name of the object to be identified, and related information may also include:

Match the to-be-identified object with the pre-obtained sensitive object; if the to-be-identified object is not successfully matched with the sensitive object, execute the display of the image, the name of the to-be-identified object and the associated information.

In order to prevent the spread of undesirable content, the object to be identified is first matched with the sensitive object, and based on the matching result, it is determined whether to perform the steps of displaying the image, the name of the object to be identified and the associated information. In practical applications, the sensitive object is a pre-established object used to verify whether the object to be identified will spread bad social atmosphere.

For example, in order to check whether the object to be identified will spread bad social ethos, sensitive objects can be pre-stored in the database, and before matching the object to be identified with the preset object, before matching the object to be identified with the preset object After that or while matching the object to be recognized with the preset object, the object to be recognized in the image is matched with the sensitive object in the database. The specifics are not limited; if the matching is successful, it means that the object to be recognized in the image involves sensitive objects. Content. In this case, the image is not displayed to the user or the image is covered. For example, the image can be covered with a white interface, or the image can be mosaicked. There is no specific limitation here; if the object to be recognized in the image is If the sensitive object in the database is not matched successfully, it means that the object to be identified in the image does not involve sensitive content. In this case, the image, the name and associated information of the object to be identified can be displayed to the user.

After inspecting the object to be identified based on the sensitive object, if the object to be identified involves sensitive content, processing the image can effectively prevent the spread of undesirable content and purify the social atmosphere.

In the embodiment of this application, the image uploaded by the user is received, and then the name of the object to be identified in the image is obtained, the associated information of the object to be identified is obtained in the preset library according to the name of the object to be identified, and the association of the object to be identified is displayed to the user Information to facilitate users to obtain the associated information of the object to be identified.

The following will combine an example to illustrate how to obtain the name of the object to be identified.

Refer to Fig. 3, which is an explanation of step S1 in Fig. 1.

In an implementation manner, obtaining the name of the object to be identified in the image may specifically include:

S11. Obtain the object to be identified from the image;

In this embodiment of the application, based on the purpose of obtaining the name of the object to be recognized in the image, the object to be recognized is first obtained from the image; in order to obtain the object to be recognized in the image, a target detection algorithm can be used to detect the object to be recognized in the image. The object to be recognized is the object that is expected to be recognized in the image. In practical applications, when the image is a street view, the object to be recognized can be a vehicle, and when the image is a natural scenery, the object to be recognized can be trees, flowers, animals, etc. The specifics are not limited.

S12. Match the object to be identified with the preset object in the database;

In the embodiments of the present application, based on the purpose of recognizing the object to be identified, a database may be established in advance. The database includes preset objects. The preset objects may be models obtained through three-dimensional modeling. In practical applications, the preset objects may be Vehicle models, tree models, flower models, animal models, etc., are not specifically limited. In order to obtain the name of the object to be identified, after the object to be identified is obtained, the object to be identified can be matched with the preset object, and then the name of the object to be identified can be determined according to the name of the matched preset object.

S13. If there is a preset object matching the object to be identified in the database, the name of the object to be identified is determined based on the matching result.

In this embodiment of the application, in order to obtain the name of the object to be identified as quickly as possible, if the object to be identified is successfully matched with the preset object in the database, the name of the preset object that successfully matches the object to be identified can be obtained as the name of the preset object according to the matching result. The name of the identification object; the name can be a Chinese name, or it can include both a Chinese name and a foreign name, such as an English name, a Russian name, a Japanese name, a Korean name, etc., and the specific name is not limited.

In practical applications, in order to determine the name of the object to be identified as quickly as possible, the database may store the correspondence between the preset object and its name. Then, in some possible implementations, the name of the object to be identified is determined based on the matching result, including : Use the name corresponding to the preset object successfully matched with the object to be identified as the name of the object to be identified.

It is understandable that based on the corresponding relationship between the preset object and its name in the database, after determining the preset object matching the object to be identified, the name of the object to be identified can be quickly determined, so that the user can obtain the association of the object to be identified as soon as possible information.

For example, the database can include a category library, a name library, and a model library. The category library can be the ImageAI library of Python3, and the name library can be the PIP3 library of Python3; the category library is used to filter the types of objects to be identified in the image, for example, The ImageAI library contains the basic outline of the object. The ImageAI library can be used to filter whether the object to be recognized is a vehicle or a tree; the model library includes preset objects. The model library is used to determine the type of the object to be recognized after filtering out the type of the object to be recognized For example, after screening the object to be identified is a tree, it is determined that the object to be identified is a poplar, willow or locust tree, etc.; the name database is used to determine the name of the object to be identified after determining the species of the object to be identified, for example, Determine the Chinese name and foreign name of the object to be identified.

In practical applications, after obtaining the object to be recognized, you can first determine the type of the object to be recognized through the type library, then determine the type of the object to be recognized through the model library based on the type of the object to be recognized, and finally, pass The name library determines the name of the object to be identified; for example, the ImageAI library is used to filter out the type of object to be identified, and then the mathy version of the object to be identified in the form of a matrix in the model library is called, and the model.compile function is run to predict the object to be identified. Identify the specific species of the object, and then call the PIP3 library to obtain the Chinese name and foreign name of the object to be identified.

For example, the electronic device (executive body, hereinafter referred to as the electronic device) that implements the solution can display an interactive interface with the user. In addition, the electronic device stores a PIP3 library, an ImageAI library, and a model library. The user takes a photo of the tree he sees, and inputs the captured image to the electronic device through the interactive interface. After the electronic device receives the picture uploaded by the user, it is first filtered through the ImageAI library and the object to be identified in the output picture is a tree. Then, the object to be recognized is matched with the preset object in the model library to confirm that the type of tree in the picture is poplar, and finally the Chinese name and English name poplar of the poplar are output through the PIP3 library.

It is understandable that the object to be recognized is first obtained from the image, and then the object to be recognized is matched with the preset object in the database, and finally the name of the object to be recognized is determined based on the matching result of the object to be recognized and the preset object, so as to update Quickly feedback the associated information of the object to be identified to the user.

In practical applications, countless objects to be identified may be received, and it is difficult to include preset objects matching all the objects to be identified in the database; then, in some possible implementation manners, the method further includes:

If there is no preset object matching the object to be identified in the database, output prompt information;

Acquiring a new preset object and its name that can match the object to be identified;

The new preset object and its name are stored in the database.

For example, if there is no preset object matching the object to be recognized in the database, a prompt message is output to remind the user that the object to be recognized in the image cannot be recognized; and a new preset object that matches the object to be recognized is obtained, and The name corresponding to the new preset object can be a Chinese name, or a Chinese name and a foreign name, such as English name, Russian name, Japanese name, Korean name, etc., and the specific name is not limited.

In practical applications, when the prompt information is output, the operation and maintenance personnel can manually search for the unmatched object to be recognized, and obtain the new preset object and the Chinese name and foreign name of the object to be recognized; the new preset object to be obtained And the Chinese name and foreign name corresponding to the new preset object are stored in the database, so that when another user uploads the same object to be identified, the user can be fed back so that the user can obtain more related information of the object to be identified.

Continuing the above example, when receiving the picture uploaded by the user, the object to be recognized in the picture cannot be successfully matched with the preset object in the model library, then the picture is saved in the ImageAI2 library, and a prompt message is output, indicating that the object in the picture cannot be recognized Objects to be identified; operation and maintenance personnel perform regular maintenance on the pictures in the ImageAI2 library, manually retrieve the new preset objects of the objects to be identified and the corresponding Chinese and foreign names, and save the new preset objects of the objects to be identified in the model library Inside, save the Chinese name and foreign name of the new preset object in the ImageAI library, so that when another user uploads the same object to be identified, it can provide feedback to the user.

It is understandable that by constructing a new preset object corresponding to the unmatched object to be identified, and querying the Chinese name and foreign name corresponding to the new preset object, and then combining the new preset object and its corresponding Chinese name and foreign language name The name is stored in the database, on the one hand, it is convenient for subsequent users to upload the same object to be identified, and the associated information of the object to be identified can be quickly obtained; on the other hand, the database of the electronic device can be further improved.

It can be seen from the above that the image recognition method first obtains the name of the object to be recognized in the image, and then uses a preset library that stores the name of the object to be recognized and its corresponding associated information to obtain the associated information of the object to be identified; Upload to the electronic device, the electronic device obtains the name of the object to be identified in the image, and then obtains the associated information of the object to be identified in the preset library according to the name of the object to be identified, and displays the associated information of the object to be identified to the user to facilitate the user to obtain More related information about the object to be identified.

The image recognition method in the foregoing embodiment can be implemented in the hardware architecture as shown in FIG. 4.

As shown in Figure 4, the hardware architecture may include an electronic device 101, a server 102.

The electronic device 101 can receive an image uploaded by a user. In an optional implementation manner, the user can also upload images to the electronic device 101 through other user terminals, and the electronic device 101 and the user terminal can be connected via a network, which can specifically include various connection types, such as wired and wireless communication. Link or fiber optic cable, etc. In specific implementation, the electronic device 101 may specifically be a mobile phone, a tablet computer, etc., which is not specifically limited.

The electronic device 101 can store a name library, a category library, and a model library. The category library determines the type of the object to be recognized in the image, and then determines the type of the object to be recognized based on the type of the object to be recognized through the model library, and finally based on the object to be recognized The name of the object to be identified is determined through the name database.

The server 102 can be a third-party server or a cloud server; if the server 102 is a third-party server, the electronic device 101 can transfer information to the server 102 by calling an external source interface; if the server 102 is a cloud server, the electronic device 101 can call The communication interface transmits information to the server 102. A preset library is stored in the server 102, and the server 102 can search the associated information of the object to be identified in its preset library and feed it back to the electronic device 101; the electronic device 101 provides the user with the associated information after receiving the associated information.

It should be noted that the server 102 may be hardware or software. When the server 102 is hardware, it can be implemented as a distributed server cluster composed of multiple servers, or as a single server. When the server 102 is software, it can be implemented as multiple software or software modules (for example, used to provide distributed services), or can be implemented as a single software or software module, which is not specifically limited herein.

In an optional implementation manner, the functions of the electronic device 101 and the server 102 may also be concentrated on one execution body. In this case, the electronic device 101 and the server 102 may be two modules in the same execution body.

It should be understood that the numbers of the electronic device 101 and the server 102 in FIG. 4 are only illustrative. According to implementation needs, the system architecture can have any number of electronic devices and servers.

Fig. 5 is a schematic structural diagram of an image recognition device provided by an embodiment of the application, including:

The name determining module 301 is used to obtain the name of the object to be identified in the image;

The associated information acquisition module 302 is configured to use a preset library to obtain associated information of the object to be identified based on the name of the object to be identified; the preset library stores the name of the object to be identified and its corresponding associated information.

As an implementation manner, the associated information acquisition module 302 includes:

The transmission unit is configured to transmit the name of the object to be identified to the server storing the preset library, so that the server can determine the associated information of the object to be identified through the preset library;

The receiving unit is configured to receive the association information of the object to be identified fed back by the server.

In one embodiment, the name determining module 301 includes:

The to-be-identified object acquiring unit is used to acquire the to-be-identified object from the image;

The matching unit is used to match the object to be identified with the preset object in the database;

The name determining unit is configured to determine the name of the object to be identified based on the matching result if there is a preset object matching the object to be identified in the database.

As an implementation manner, the device further includes a prompt information output module, a new preset object acquisition module, and a storage module (not shown in the figure), wherein:

The prompt information output module is used to output prompt information if there is no preset object matching the object to be identified in the database;

A new preset object acquisition module for acquiring a new preset object and its name that can be matched with the object to be identified;

The storage module is used to store the new preset object and its name in the database.

In one embodiment, the device further includes a display module (not shown in the figure) for displaying the image, the name of the object to be identified, and associated information.

As an implementation manner, the display module includes:

The label generating unit is used to generate a label of the object to be identified, the label including the name of the object to be identified and associated information;

The label display unit is used to display the image and display the label in the preset area of the image.

In one embodiment, the device further includes a sensitive object matching module (not shown in the figure), which is used to compare the object to be identified with the pre-obtained sensitive object before the image, the name of the object to be identified and the associated information are displayed on the display module. Object matching If the object to be identified and the sensitive object are not successfully matched, the image, the name and associated information of the object to be identified will be displayed.

The device in the foregoing embodiment is used to implement the corresponding method in the foregoing embodiment, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

In an embodiment of the present application, there is also provided an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor. The processor implements any of the above-mentioned image recognition methods when the program is executed. .

In an embodiment of the present application, a non-transitory computer-readable storage medium is also provided, and the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to make a computer execute any of the above-mentioned image recognition methods.

Those of ordinary skill in the art should understand that the discussion of any of the above embodiments is only exemplary, and is not intended to imply that the scope of the present disclosure (including the claims) is limited to these examples; under the idea of this application, the above embodiments or The technical features in different embodiments can also be combined, the steps can be implemented in any order, and there are many other changes in different aspects of the present application as described above, which are not provided in the details for the sake of brevity.

In addition, in order to simplify the description and discussion, and in order not to make the application difficult to understand, the provided drawings may show the device in the form of a block diagram in order to avoid making the application difficult to understand, and this also takes into account the following facts, That is, the details of the implementation of these block diagram devices are highly dependent on the platform on which the application will be implemented (that is, these details should be fully within the understanding of those skilled in the art). In the case where specific details (for example, a circuit) are described to describe the exemplary embodiments of the present application, it is obvious to those skilled in the art that it may be possible without these specific details or when these specific details are changed. Implement this application under. Therefore, these descriptions should be considered illustrative rather than restrictive.

Although the present application has been described in conjunction with the specific embodiments of the present application, many substitutions, modifications and variations of these embodiments will be obvious to those of ordinary skill in the art based on the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the discussed embodiments.

The embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of this application shall be included in the protection scope of this application.

Claims

An image recognition method, characterized in that the method includes:

Obtain the name of the object to be identified in the image;

Based on the name of the object to be identified, a preset library is used to obtain the associated information of the object to be identified; the preset library stores the name of the object to be identified and its corresponding associated information.
The method according to claim 1, wherein the obtaining the associated information of the object to be identified by using a preset library based on the name of the object to be identified comprises:

Transmitting the name of the object to be identified to the server storing the preset library, so that the server can determine the associated information of the object to be identified through the preset library;

Receiving the associated information of the object to be identified fed back by the server.
The image recognition method according to claim 1, wherein said obtaining the name of the object to be recognized in the image comprises:

Acquiring the object to be identified from the image;

Matching the object to be identified with a preset object in the database;

If there is a preset object matching the object to be identified in the database, the name of the object to be identified is determined based on the matching result.
The image recognition method according to claim 3, wherein the method further comprises:

If there is no preset object matching the object to be identified in the database, output prompt information;

Acquiring a new preset object and its name that can match the object to be identified;

The new preset object and its name are stored in the database.
The method according to any one of claims 1 to 4, wherein the method further comprises:

The image, the name of the object to be recognized, and the associated information are displayed.
The image recognition method according to claim 5, wherein the displaying the image, the name of the object to be recognized, and the associated information comprises:

Generating a label of the object to be identified, the label including the name of the object to be identified and the associated information;

The image is displayed, and the label is displayed in a preset area of the image.
The image recognition method according to claim 5, wherein the displaying of the image, the name of the object to be recognized, and the associated information beforehand further comprises:

Matching the object to be identified with a pre-obtained sensitive object;

If the object to be identified does not match the sensitive object successfully, then performing the display of the image, the name of the object to be identified, and the associated information.
An image recognition device, characterized in that the device includes:

The name determination module is used to obtain the name of the object to be identified in the image;

The associated information acquisition module is configured to use a preset library to obtain the associated information of the object to be identified based on the name of the object to be identified; the preset library stores the name of the object to be identified and its corresponding associated information .
An electronic device, characterized by comprising a memory, a processor, and a computer program stored on the memory and capable of running on the processor. The processor executes the program as described in any one of claims 1 to 7 The method described.
A non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to make a computer execute the method according to any one of claims 1 to 7.