WO2020007201A1

WO2020007201A1 - Picture search method and device, readable storage medium, and terminal

Info

Publication number: WO2020007201A1
Application number: PCT/CN2019/092128
Authority: WO
Inventors: 李媛
Original assignee: 奇酷互联网络科技（深圳）有限公司
Priority date: 2018-07-04
Filing date: 2019-06-20
Publication date: 2020-01-09
Also published as: CN109033237A

Abstract

A picture search method and device, a readable storage medium, and a terminal. The method comprises: when a picture taken by a camera is detected, performing picture recognition on the picture to determine a type name corresponding to an object in the picture (S11); adding the type name corresponding to the object to attribute information of exif information of the picture (S12); when keywords input by a user in a picture search interface are obtained, querying attribute information of all pictures in a picture gallery to determine target attribute information matching the keywords (S13); and displaying the picture corresponding to the target attribute information (S14). In the method, the object in the picture is recognized by a picture recognition method, and the type name of the determined object is added to the attribute information of the exif information of the picture as auxiliary recognition content. When the user searches for the picture, the corresponding picture can be quickly searched according to the attribute information.

Description

Picture search method, device, readable storage medium and terminal

[Technical Field]

The present invention relates to the field of electronic technology, and in particular, to a picture search method, device, readable storage medium, and terminal.

【Background technique】

With the development of technology, digital cameras and smart terminals with photographing functions are widely used. In addition, people download more and more pictures in life and work through Internet downloads, video capture, and the use of picture drawing software. Finding pictures has become one of the problems that bothers people.

In the prior art, pictures are usually searched according to the picture name, and pictures in the gallery are generally named according to the default naming rule. For example, they can be numbered sequentially or named according to the shooting time. classification. It is also possible for users to manually add picture names or modify picture names. However, due to the large number of pictures and long storage time, users tend to forget the picture name, storage date or stored in that folder. When searching, you need to preview the pictures in the gallery one by one. The search speed is very slow.

[Summary of the Invention]

In view of the foregoing, it is necessary to provide a picture search method, device, readable storage medium, and terminal in response to the problem of slow picture search speed in the prior art.

An image search method includes:

When a picture taken by the camera is detected, image recognition is performed on the picture to determine a type name corresponding to an object in the picture;

Adding a type name corresponding to the object to attribute information of exif information of the picture;

When a keyword entered by a user in the picture search interface is obtained, attribute information of all pictures in the gallery is queried to determine target attribute information matching the keyword;

Display a picture corresponding to the target attribute information.

Further, in the above picture search method, the step of adding a type name corresponding to the object to attribute information of exif information of the picture includes:

Determining whether the number of types of objects in the picture is greater than 1 according to the type name;

If yes, determine the priority of the object according to a preset priority rule, and determine the type of object with the highest priority as the main object;

Adding the type name corresponding to the main object to the attribute information of the exif information of the picture.

Further, in the above picture search method, the step of determining the priority of the object according to a preset priority rule includes:

Calculate the total area area of each type of object in the picture, and determine the priority of each type of object according to the total area area. The type of object with a larger total area area has higher priority.

Further, in the above picture search method, after the step of adding a type name corresponding to the main object to attribute information of exif information of the picture, the method further includes:

When an instruction to store the picture is obtained, among a plurality of picture folders preset in the query gallery, a target picture folder corresponding to the type name of the main object;

The picture is stored in the target picture folder.

Further, in the above picture search method, wherein the attribute information includes first attribute information and second attribute information, and the step of adding a type name corresponding to the object to the attribute information of exif information of the picture includes :

Adding the type name corresponding to the object to the first attribute information of the exif information of the picture.

Further, in the above picture search method, after the step of adding a type name corresponding to the object to the first attribute information of exif information of the picture, the method further includes:

Querying the tag information table corresponding to the type name of the object, and displaying the tag information table on the current interface, where the tag information table includes multiple tags;

When a user's selection instruction for at least one tag in the tag information table is obtained, the tag selected by the user is added to the second attribute information of the exif information.

Further, in the above picture search method, the step of displaying the tag information table on the current interface includes:

A plurality of tags in the tag information table are scrolled and displayed on the current interface with a preset track.

Further, in the above picture search method, the step of performing image recognition on a picture to determine a type name corresponding to an object in the picture includes:

Performing contour division on the picture to obtain at least one contour information;

Query the contour of the object matching the contour information from the contour model database, and obtain the type name corresponding to the contour of the object.

An embodiment of the present invention further provides a picture search apparatus, including:

An image recognition module, configured to perform image recognition on a picture when a picture taken by a camera is detected to determine a type name corresponding to an object in the picture;

A first adding module, configured to add a type name corresponding to the object to attribute information of exif information of the picture;

A first query module, configured to query attribute information of all pictures in a gallery when a keyword entered by a user in a picture search interface is obtained, to determine target attribute information matching the keyword;

The first display module is configured to display a picture corresponding to the target attribute information.

Further, in the above image search device, the first adding module includes:

A judging module, configured to judge whether the number of types of objects in the picture is greater than 1 according to the type name;

A determining module, configured to determine the priority of the object according to a preset priority rule when the number of types of objects in the picture is greater than 1, and determine the type of object with the highest priority as the main object;

An adding sub-module is configured to add a type name corresponding to the main object to attribute information of exif information of the picture.

Further, in the above picture search device, the determining module is specifically configured to:

Further, the above image search device further includes:

A second query module, configured to query a target picture folder corresponding to the type name of the main object among a plurality of picture folders preset in the gallery when an instruction to store the picture is obtained;

A storage module, configured to store the picture in the target picture folder.

Further, in the above picture search device, the attribute information includes first attribute information and second attribute information, and the first adding module is specifically configured to add a type name corresponding to the object to exif information of the picture In the first attribute information.

Further, in the above picture search device, the picture search device further includes:

A third query module, configured to query a tag information table corresponding to the type name of the object;

A second display module that displays the tag information table on the current interface, where the tag information table includes multiple tags;

A second adding module is configured to add a tag selected by the user to the second attribute information of the exif information when a user's selection instruction for at least one tag in the tag information table is obtained.

Further, in the above picture search device, the second display module is specifically configured to:

Further, in the above picture search device, the image recognition module is specifically configured to:

An embodiment of the present invention further provides a readable storage medium on which a program is stored, and when the program is executed by a processor, the steps of any one of the foregoing methods are implemented.

An embodiment of the present invention further provides a terminal, including a memory, a processor, and a program stored on the memory and executable on the processor. When the processor executes the program, the steps of any of the foregoing methods are implemented.

In the embodiment of the present invention, an image recognition method is used to identify an object in a picture, determine a type name corresponding to the object, and add the determined type name to attribute information of exif information as auxiliary identification content. When a user finds a picture, he can quickly search for the corresponding picture according to the attribute information. And the exif information will not be easily modified by the user, and has good stability. At any time, the user can perform image search based on the exif information.

[Brief Description of the Drawings]

FIG. 1 is a flowchart of a picture search method according to a first embodiment of the present invention; FIG.

FIG. 2 is a schematic diagram of an interface of exif information of a picture; FIG.

3 is a flowchart of a picture search method according to a second embodiment of the present invention;

FIG. 4 is a structural block diagram of a picture search apparatus according to a third embodiment of the present invention.

【detailed description】

Hereinafter, embodiments of the present invention will be described in detail. Examples of the embodiments are shown in the drawings, wherein the same or similar reference numerals indicate the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the drawings are exemplary, and are only used to explain the present invention, and should not be construed as limiting the present invention.

These and other aspects of embodiments of the invention will be apparent with reference to the following description and drawings. In these descriptions and drawings, some specific implementations of the embodiments of the present invention are specifically disclosed to represent some ways of implementing the principles of the embodiments of the present invention, but it should be understood that the scope of the embodiments of the present invention is not limited by This limitation. On the contrary, the embodiments of the present invention include all changes, additions, and equivalents falling within the spirit and scope of the appended claims.

Please refer to FIG. 1, which is a picture search method according to a first embodiment of the present invention. The method is applied to a terminal. The terminal is, for example, a mobile phone, a tablet computer, a wearable device, and the like. The terminal has a camera function and generally has a camera. Can take pictures and photography. When the camera takes a picture, the corresponding exif information is generated. The exif information can be attached to files such as JPEG, TIFF, RIFF, etc., to add content about the camera shooting information and index map or version information of image processing software. The exif information contains the attribute information of the picture, as shown in Figure 2. If you view the attributes of a picture, the attribute information includes descriptive information such as title, subject, logo, remarks, etc. In the prior art, the content of the attribute information is empty. , The user can view the attribute information of the picture and manually add content to the picture's title, subject, logo, and notes. In the embodiment of the present invention, when the camera takes a picture, content is automatically added to the attributes of the picture, so as to facilitate subsequent quick search of the picture. The image search method includes steps S11 to S14.

In step S11, when a picture taken by the camera is detected, image recognition is performed on the picture to determine a type name corresponding to an object in the picture.

When the terminal detects a picture taken by the camera, it performs image recognition on the content of the picture. Identify the objects in the picture and the type names of the objects through image recognition. Among them, the objects referred to include multiple types, such as people, animals, landscapes, buildings, or food. Image recognition is an important field of artificial intelligence. It uses computer programs to process, analyze, and understand images in order to identify targets and objects in various modes. In the development of image recognition, there are three main recognition methods: statistical pattern recognition, structural pattern recognition, and fuzzy pattern recognition. In this embodiment, the image recognition method in the prior art can be used to determine the object in the picture and the corresponding type name.

For example, this implementation can extract the shape features of the objects in the picture based on the contour method to identify the image, and determine the objects in the picture and the type names corresponding to the objects. The specific steps include:

Among them, in the prior art, there are various algorithms for dividing and extracting contours, such as a boundary feature method, a Fourier shape description method, and an algorithm for identifying a shape contour of an object through a Fourier descriptor. At least one piece of contour information is obtained by contour-dividing the picture through the current contour-dividing and extraction algorithm, and the contour information is the feature information identifying the contour of the object.

When a contour information is obtained, it is matched with the contour of the object in the contour model database to find the contour of the object that matches the contour information. The contour model database is stored in the terminal in advance. The contour model database includes multiple object contours, and each object contour is provided with a type name. For example, the type name corresponding to the outline of a person is "Person", the type name corresponding to the outline of an animal is "Animal", and the type name corresponding to the outline of a food is "Food".

It can be understood that, as another embodiment of the present invention, the contour database may be stored in a server connected to the terminal through a network, and the process of performing image recognition on pictures may be performed in the server. Specifically, when the terminal detects a picture taken by the camera, the picture is sent to the server, and the server divides the picture into contours to obtain at least one contour information, and queries the contours of the matching objects in the contour model database, and Get the name information of the queried object outline. The server sends the obtained name information to the terminal.

Step S12: Add the type name corresponding to the object to the attribute information of the exif information of the picture.

After the terminal determines the type name of the object in the picture, the type name is added to the attribute information of the exif information. The attribute information includes a plurality of information, such as title, subject, logo, and remark information. The type name corresponding to the object can be added to any attribute information of the exif information of the picture. For example, the terminal adds the determined type name of the object to the content corresponding to the title information.

In the above steps, the number of objects in the picture may be one or more. After performing image recognition on a picture containing only one object, there is only one type name of the object. For a picture containing multiple objects, when multiple objects in the picture are all of the same type, only one type name is obtained for image recognition. When the objects in the picture are different types of objects, the image recognition There are multiple types of names. The terminal determines the number of types of objects in the picture according to the determined number of type names. For example, if a picture contains 3 persons and an animal (cat), the type names of the objects determined from the picture are "person" and "cat", that is, there are two types of objects in the picture.

When there is only one type of object in the picture, the type name of the type of object is directly added to the attribute information of the exif information. When there are multiple types of objects in the picture, the type names corresponding to the multiple types of objects may be added to the attribute information of the exif information of the picture. Of course, the priority of each type of object can also be determined according to a preset priority rule, the type of object with the highest priority is determined as the main object, and the type name corresponding to the main object is added to the attribute information of the exif information.

Specifically, the manner in which the preset priority rule is determined as the main object includes, but is not limited to, one of the following two types:

First, from the preset priority list, the priority of each type of object is queried, and a type of object with the highest priority is determined as the main object. The priority list can be preset and stored in the terminal according to the needs of the user. The preset priority list includes the type names and corresponding priority numbers of multiple types of objects. For example, the type names are objects of people, animals, buildings, food, and scenery, and the corresponding priority numbers are 1, 2 respectively. ... 5, the smaller the priority number, the higher the priority. For example, when both a person and an animal are recognized in the picture, the person is used as the main object of the picture according to the priority order in the priority list.

Secondly, the total area of each type of object in the picture is calculated separately; the priority of each type of object is determined according to the total area, and the type of object with a larger total area has higher priority. Therefore, the terminal may determine that the type of object with the largest area in the picture is the main object.

The area area of each type of object can be obtained by extracting contour features and calculating the total area of the area occupied by the outline of each type of object. The type of object with the largest total area area is used as the main object.

In step S13, when the keywords entered by the user in the picture search interface are obtained, attribute information of all pictures in the gallery is queried to determine target attribute information matching the keywords.

Step S14: Display a picture corresponding to the target attribute information.

The picture search interface is, for example, a search window on a terminal gallery interface, and a user enters keywords of pictures on the search interface. The terminal queries attribute information of all pictures in the gallery according to the keyword to query target attribute information that contains the keyword phase in the attribute information. And open the picture corresponding to the target attribute information on the current interface.

In this embodiment, an image recognition method is used to identify an object in a picture, determine a type name corresponding to the object, and add the determined type name to attribute information of exif information as auxiliary identification content. When a user finds a picture, he can quickly search for the corresponding picture according to the attribute information. And the exif information will not be easily modified by the user, and has good stability. At any time, the user can perform image search based on the exif information.

Please refer to FIG. 3, which is a picture search method according to a second embodiment of the present invention, including steps S21 to S29.

In step S21, when a picture taken by the camera is detected, the picture is divided into outlines to obtain at least one outline information.

When the terminal obtains a picture taken by the camera, it performs image recognition on the picture. Specifically, a contour extraction method may be adopted to divide the contours of the objects in the picture to obtain the contour information of at least one object.

Step S22: Query the contour of the object matching the contour information from the contour model database, and obtain the type name corresponding to the contour of the object.

The contour model is stored in the terminal in advance, and the contour model includes a plurality of object contours, and each object contour is correspondingly provided with a type name. The terminal matches the divided contour information with multiple object contours in the contour model in order to determine an object contour adapted to the current contour information, and obtains the type name of the matched object contour. Understandably, by contour matching, the object contours of a type of object are obtained. For example, the contours of the objects matched by characters of different movements (sideways, bending, squatting) or different heights and shapes are all character contours. , That is, the corresponding type name is "person".

In step S23, it is determined whether the number of types of objects in the picture is greater than 1 according to the type name, and if yes, step S24 is performed.

The contour information obtained by contour segmentation of a picture containing only one object is one or more. For a contour information, there is only one object contour matched from the contour model database, and its corresponding type name is only one. A picture containing multiple objects may match the contours of one or more objects and obtain one or more type names. For example, if a picture contains 3 persons and an animal (cat), the type names of the objects determined from the picture are "person" and "animal", that is, there are two types of objects in the picture.

Step S24: Calculate the total area area of each type of object in the picture, and determine the type of object with the largest total area area as the main object.

Step S25: Add the type name of the main object to the first attribute information of the exif information.

When there are multiple types of objects in the picture, the total area of the area occupied by each type of object is calculated. The total area of each type of object is compared, and the type of object with the largest total area is determined as the main object. For example, in a picture containing three people and one animal, the area occupied by the person is larger than the area occupied by the animal, and the person is the main object. The type name corresponding to the determined main object is added to the first attribute information of the exif information.

If it is determined according to the type name that the number of types of the object in the picture is not greater than 1, that is, equal to 1, the area area is not calculated, and the type name is directly added to the first attribute information of the exif information .

Step S26: Query a tag information table corresponding to the type name of the main object, and display the tag information table on the current interface. The tag information table includes multiple tags.

A plurality of type names and tag information tables corresponding to each type name are pre-stored in the terminal. Each label information table is preset with multiple labels, and the user can add favorite labels to each label information table according to actual needs. The labels in the label information table are used to add more detailed descriptions of various types of objects. For example, the tag information table corresponding to a person type includes old people, children, men, women, etc., or tags indicating kinship (dad, mom, etc.) and age information; the tag information table corresponding to a landscape type includes blue sky, white clouds, flowers , Grass, tree and other tags; the tag information table corresponding to the type of cuisine includes chicken, duck, fish, meat and other tags.

Further, the step of displaying the tag information table on the current interface includes: scrolling and displaying a plurality of tags in the tag information table with a preset track on the current interface.

That is, multiple labels in the label information table are displayed on the current interface in a floating screen manner. The preset trajectory can be designed as an arbitrary movement path, and the speed of label scrolling can be set in advance. For example, multiple labels in the label information table are sequentially moved from the left to the right on the current interface at a speed of 20 cm / min.

Further, in another embodiment, the tag information table may also be displayed on the current interface in the form of a list, and the user may select one or more tags in the list.

Understandably, the user can automatically display the tag information table when starting the picture preview. Controls on the current interface can also be triggered on the interface for previewing pictures to trigger the operation of displaying the tag information table.

Step S27: When a user's selection instruction for at least one tag in the tag information table is obtained, add the tag selected by the user to the second attribute information of the exif information.

The user can select a label by clicking or touching the label on the terminal. When the terminal obtains one or more tags selected by the user, the tag is added to the second attribute information of the exif information.

The second attribute information is one of exif attribute information, which is different from the first attribute information. For example, the first attribute information is title information in the exif information, and the second attribute information is topic information in the exif information. In specific implementation, a label selected by the user is added to the content corresponding to the topic information. Through the design of the second attribute, the description of the picture is more detailed, which facilitates the quick search of the picture.

In step S28, when the keywords entered by the user in the picture search interface are obtained, attribute information of all pictures in the gallery is queried to determine target attribute information matching the keywords.

Step S29: Display a picture corresponding to the target attribute information.

When a user finds a picture, he can enter keywords in the picture search interface, and the terminal queries the attribute information of all pictures in the gallery according to the keyword to query the attribute information that contains the target attribute information of the keyword. And open the picture corresponding to the target attribute information on the current interface.

Further, as an implementable manner of the embodiment of the present invention, on the basis of the second implementation, the method further includes steps after step S25:

Step S31: when an instruction for storing the picture is obtained, query a target picture folder corresponding to the type name of the main object among a plurality of picture folders preset in the gallery;

In step S32, the picture is stored in the target picture folder.

In this embodiment, a plurality of picture folders are pre-stored in the gallery of the terminal, and the picture folders are used to store pictures. The multiple picture files are in one-to-one correspondence with the type names of multiple object outlines in the contour model, and each picture folder may be named with a corresponding type name. When the user takes a picture and saves it, the terminal searches the corresponding target folder in the gallery according to the type name of the main object in the picture, and stores the picture in the target folder. In this embodiment, pictures can be classified and stored automatically. When a user searches for a picture, a corresponding picture folder is found in the gallery according to the type name of the main object of the picture, and then the picture is found from the found picture folder.

It can be understood that, in other embodiments of the present invention, when the user keeps the picture, the identifiers of multiple preset picture folders may pop up. The user selects an identifier and saves the picture in the picture folder corresponding to the identifier.

Please refer to FIG. 4, which is a picture search apparatus according to a fourth embodiment of the present invention, including:

An image recognition module 100, configured to perform image recognition on a picture when a picture taken by a camera is detected to determine a type name corresponding to an object in the picture;

A first adding module 200, configured to add a type name corresponding to the object to attribute information of exif information of the picture;

The first query module 300 is configured to query attribute information of all pictures in a gallery when a keyword entered by a user in a picture search interface is obtained, to determine target attribute information matching the keyword;

The first display module 400 is configured to display a picture corresponding to the target attribute information.

Further, in the above image search device, the first adding module 200 includes:

Further, the above image search device further includes:

A second query module 500, configured to query a target picture folder corresponding to the type name of the main object among a plurality of picture folders preset in the gallery when an instruction to store the picture is obtained;

The storage module 600 is configured to store the picture in the target picture folder.

Further, in the above picture search device, wherein the attribute information includes first attribute information and second attribute information, the first adding module 200 is specifically configured to add a type name corresponding to the object to an exif of the picture The first attribute information of the information;

The picture search device further includes:

A third query module 700, configured to query a tag information table corresponding to the type name of the object;

The second display module 800 displays the tag information table on the current interface, where the tag information table includes multiple tags;

The second adding module 900 is configured to add a tag selected by the user to the second attribute information of the exif information when a user's selection instruction for at least one tag in the tag information table is obtained.

Further, in the above picture search device, the second display module 800 is specifically configured to:

Further, in the above picture search device, the image recognition module 100 is specifically configured to:

The implementation principle and technical effects of the picture search device provided by the embodiment of the present invention are the same as those of the foregoing method embodiments. For a brief description, the parts not mentioned in the device embodiments may refer to the corresponding content in the foregoing method embodiments.

The present invention also proposes a readable storage medium on which a computer program is stored, and when the program is executed by a processor, the above-mentioned picture search method is implemented.

An embodiment of the present invention further provides a terminal, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steps of the foregoing method are implemented.

The logic and / or steps represented in the flowchart or otherwise described herein, for example, a sequenced list of executable instructions that can be considered to implement a logical function, can be embodied in any computer-readable medium, For instruction execution systems, devices, or devices (such as computer-based systems, systems including processors, or other systems that can fetch instructions from and execute instructions) Or equipment. For the purposes of this specification, a "computer-readable medium" may be any device that can contain, store, communicate, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device.

More specific examples (non-exhaustive list) of computer-readable media include the following: electrical connections (electronic devices) with one or more wirings, portable computer cartridges (magnetic devices), random access memory (RAM), Read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program can be printed, because, for example, by optically scanning the paper or other medium, followed by editing, interpretation, or other suitable Processing to obtain the program electronically and then store it in computer memory.

It should be understood that each part of the present invention may be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods may be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it may be implemented using any one or a combination of the following techniques known in the art: Discrete logic circuits, application specific integrated circuits with suitable combinational logic gate circuits, programmable gate arrays (PGA), field programmable gate arrays (FPGA), etc.

In the description of this specification, the description with reference to the terms “one embodiment”, “some embodiments”, “examples”, “specific examples”, or “some examples” and the like means specific features described in conjunction with the embodiments or examples , Structures, materials, or features are included in at least one embodiment or example of the invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

The above-mentioned embodiments only express several implementation manners of the present invention, and their descriptions are more specific and detailed, but they cannot be understood as limiting the scope of the patent of the present invention. It should be noted that, for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can be made, which all belong to the protection scope of the present invention. Therefore, the protection scope of the invention patent shall be subject to the appended claims.

Claims

An image search method, including:

When a picture taken by the camera is detected, image recognition is performed on the picture to determine a type name corresponding to an object in the picture;

Adding a type name corresponding to the object to attribute information of exif information of the picture;

When a keyword entered by a user in the picture search interface is obtained, attribute information of all pictures in the gallery is queried to determine target attribute information matching the keyword;

Display a picture corresponding to the target attribute information.
The picture search method according to claim 1, wherein the step of adding a type name corresponding to the object to attribute information of exif information of the picture comprises:

Determining whether the number of types of objects in the picture is greater than 1 according to the type name;

If yes, determine the priority of the object according to a preset priority rule, and determine the type of object with the highest priority as the main object;

Adding the type name corresponding to the main object to the attribute information of the exif information of the picture.
The picture search method according to claim 2, wherein the step of determining the priority of the object according to a preset priority rule comprises:

Calculate the total area area of each type of object in the picture, and determine the priority of each type of object according to the total area area. The type of object with a larger total area area has higher priority.
The picture search method according to claim 2, wherein after the step of adding a type name corresponding to the main object to attribute information of exif information of the picture further comprises:

When an instruction to store the picture is obtained, among a plurality of picture folders preset in the query gallery, a target picture folder corresponding to the type name of the main object;

The picture is stored in the target picture folder.
The picture search method according to claim 1, wherein the attribute information includes first attribute information and second attribute information, and the type name corresponding to the object is added to attribute information of exif information of the picture The steps include:

Adding the type name corresponding to the object to the first attribute information of the exif information of the picture.
The picture search method according to claim 5, wherein after the step of adding a type name corresponding to the object to the first attribute information of exif information of the picture further comprises:

Querying the tag information table corresponding to the type name of the object, and displaying the tag information table on the current interface, where the tag information table includes multiple tags;

When a user's selection instruction for at least one tag in the tag information table is obtained, the tag selected by the user is added to the second attribute information of the exif information.
The image search method according to claim 6, wherein the step of displaying the tag information table on the current interface comprises:

A plurality of tags in the tag information table are scrolled and displayed on the current interface with a preset track.
The picture search method according to claim 1, wherein the step of performing image recognition on a picture to determine a type name corresponding to an object in the picture comprises:

Performing contour division on the picture to obtain at least one contour information;

Query the contour of the object matching the contour information from the contour model database, and obtain the type name corresponding to the contour of the object.
An image search device, including:

An image recognition module, configured to: when a picture taken by a camera is detected, perform image recognition on the picture to determine a type name corresponding to an object in the picture;

A first adding module, configured to add a type name corresponding to the object to attribute information of exif information of the picture;

A first query module, configured to query attribute information of all pictures in a gallery when a keyword entered by a user in a picture search interface is obtained, to determine target attribute information matching the keyword;

The first display module is configured to display a picture corresponding to the target attribute information.
The picture search apparatus according to claim 9, wherein the first adding module comprises:

A judging module, configured to judge whether the number of types of objects in the picture is greater than 1 according to the type name;

A determining module, configured to determine the priority of the object according to a preset priority rule when the number of types of objects in the picture is greater than 1, and determine the type of object with the highest priority as the main object;

An adding sub-module is configured to add a type name corresponding to the main object to attribute information of exif information of the picture.
The picture search apparatus according to claim 10, wherein the determining module is specifically configured to:

Calculate the total area area of each type of object in the picture, and determine the priority of each type of object according to the total area area. The type of object with a larger total area area has higher priority.
The picture search device according to claim 10, further comprising:

A second query module, configured to query a target picture folder corresponding to the type name of the main object among a plurality of picture folders preset in the gallery when an instruction to store the picture is obtained;

A storage module, configured to store the picture in the target picture folder.
The picture search device according to claim 9, wherein the attribute information includes first attribute information and second attribute information, and the first adding module is specifically configured to add a type name corresponding to the object to the picture The first attribute information of the exif information.
The picture search apparatus according to claim 9, wherein the picture search apparatus further comprises:

A third query module, configured to query a tag information table corresponding to the type name of the object;

A second display module that displays the tag information table on the current interface, where the tag information table includes multiple tags;

A second adding module is configured to add a tag selected by the user to the second attribute information of the exif information when a user's selection instruction for at least one tag in the tag information table is obtained.
The picture search device according to claim 14, wherein the second display module is specifically configured to:

A plurality of tags in the tag information table are scrolled and displayed on the current interface with a preset track.
The picture search device according to claim 9, wherein the image recognition module is specifically configured to:

Performing contour division on the picture to obtain at least one contour information;

Query the contour of the object matching the contour information from the contour model database, and obtain the type name corresponding to the contour of the object.
A readable storage medium having a program stored thereon, wherein when the program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.
A terminal includes a memory, a processor, and a program stored on the memory and executable on the processor, wherein when the processor executes the program, the method according to any one of claims 1 to 8 is implemented.