KR20180022990A - Image-based information retrieval method and apparatus - Google Patents

Abstract

The present application discloses an image-based information retrieval method and apparatus. One specific embodiment of the method comprises: extracting first feature information of a target to be searched in a first image input to a terminal; A step of executing a circulation step based on the first feature information, wherein in the circulation step, it is judged whether or not a search target matching the first feature information exists in a default search database, Extracts second characteristic information of a target to be searched in a second image input to the terminal, and combines the second characteristic information and the first characteristic information to obtain a first characteristic information Continuously executing the circulation step by using the characteristic information as the characteristic information; And displaying the search result corresponding to the name information and the name information of the target to be searched in the terminal, wherein the first image includes the target to be searched. This embodiment improves the accuracy of image-based information retrieval.

Description

Image-based information retrieval method and apparatus

This application claims the priority of Chinese patent application No. 201610037780.6 filed on January 20, 2016, the entire contents of which are incorporated herein by reference.

The present invention relates to the field of computer technology, specifically to the field of Internet technology, and more particularly to a method and apparatus for image-based information retrieval.

Traditional information retrieval typically finds the information users need from existing information sets through text, such as keywords. However, as the Internet technology advances, users are no longer satisfied with proceeding to search for information through text, and many users are searching for an internet picture or an object in life through a search engine Image-based information retrieval technology has appeared.

[0002] Currently, image-based information retrieval technology generally involves taking an image of a target object, acquiring a single image containing the target object, then proceeding with the retrieval based on the image, And obtains inquiry result information and the like. However, since the existing image-based information retrieval result is not highly accurate, an image-based information retrieval method with high accuracy is urgently needed.

The object of the present invention is to provide an improved image-based information retrieval method and apparatus for solving the technical problems presented in the background section above.

In a first aspect, the present application provides an image-based information retrieval method, comprising: extracting first feature information of a target to be searched in a first image input to a terminal; A step of executing a circulation step based on the first feature information, wherein in the circulation step, it is judged whether or not a search target matching the first feature information exists in a default search database, Extracts second characteristic information of a target to be searched in a second image input to the terminal, and combines the second characteristic information and the first characteristic information to obtain a first characteristic information Continuously executing the circulation step by using the characteristic information as the characteristic information; And displaying the search result corresponding to the name information and the name information of the target to be searched in the terminal, wherein the first image includes the target to be searched.

In some embodiments, the default search database includes at least a search target, feature information of the search target, and / or name information of the search target.

In some embodiments, the first feature information of the target to be searched in the first image and the second feature information of the target to be searched in the second image are not completely identical.

In some embodiments, the step of extracting the second feature information of the target to be searched in the second image input to the terminal determines whether or not the number of times of executing the circulation step is smaller than a predetermined threshold value Extracting the second characteristic information of the target to be searched from the second image input to the terminal, and generating presentation information for presenting the search failure to the terminal.

In some embodiments, the step of extracting the second feature information of the target to be searched in the second image input to the terminal generates presentation information that indicates inputting of the second image to the terminal, Extracting second feature information of the target to be searched from the second image input by the first image input unit, and the second image includes the target to be searched.

In some embodiments, the method further comprises: obtaining the first image and / or the second image taken with respect to the target to be searched by the terminal; Or the first image and / or the second image stored locally in the terminal; Or obtaining the first image and / or the second image retrieved from the Internet gallery by the terminal.

In a second aspect, the present application provides an image-based information retrieval apparatus, wherein the apparatus is configured to extract first feature information of a target to be searched in a first image input to a terminal, An extraction module including the target to be searched; Wherein the search step is configured to execute a circulation step based on the first feature information, wherein in the circulation step, it is determined whether or not a search target matching the first feature information exists in a default search database, Extracts second characteristic information of a target to be searched in a second image input to the terminal, and combines the second characteristic information with the first characteristic information A circulation step execution module that continuously uses the circulation step as the first feature information; And a display module configured to display a search result corresponding to the name information and the name information of the target to be searched in the terminal.

In some embodiments, the default search database includes at least a search target, feature information of the search target, and / or name information of the search target.

In some embodiments, the first feature information of the target to be searched in the first image and the second feature information of the target to be searched in the second image are not completely identical.

In some embodiments, the circulation step execution module determines whether the number of times of executing the circulation step is smaller than a predetermined threshold value, and if the number of times of execution of the circulation step is smaller than a predetermined threshold value, Extracts the second characteristic information, or generates presentation information for presenting a search failure to the terminal.

In some embodiments, the circulation step execution module may generate presentation information that suggests inputting a second image to the terminal, generate second information of the target to be searched in the second image input to the terminal, The target to be searched is included in the second image.

In some embodiments, the apparatus further comprises: a terminal that acquires the first image and / or the second image captured for the target to be searched by the terminal, or the first image stored locally by the terminal and / And an acquisition module configured to acquire the second image, or acquire the first image and / or the second image retrieved from the Internet gallery by the terminal.

 The image-based information searching method and apparatus provided in the present application extracts first characteristic information of a target to be searched for a first image input to a terminal, and then extracts first characteristic information of the target from the first characteristic information The second feature information of the target to be searched and the first feature information of the target to be searched in the second image input to the terminal, if the search target is not present, Is used as the first feature information. Then, it is determined whether or not a search target matching the first feature information exists in the default search database, and after the matching has been performed a number of times, By displaying the acquired name information of the target to be searched and the search result corresponding to the corresponding name information, The accuracy improves.

Other features, objects, and advantages of the present application will become more apparent from the following detailed description of non-limiting embodiments, which proceeds with reference to the accompanying drawings, in which: FIG.
Figure 1 is a system architecture diagram to which this application is applicable.
2 is a flow diagram of one embodiment of an image-based information retrieval method according to the present application.
Figure 3 is an illustration of one application scene of an image-based information retrieval method according to the present application.
4 is an exemplary flow chart of one implementation method for updating first feature information in a recursive step in an image-based information retrieval method according to the present application.
5 is an exemplary configuration diagram of an embodiment of an image-based information retrieval apparatus according to the present application.
6 is an exemplary configuration diagram of a computer system suitable for implementing a terminal device or server in an embodiment of the present application.

BRIEF DESCRIPTION OF THE DRAWINGS The present invention will now be described more fully hereinafter with reference to the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are for interpretation of the relevant invention only and are not intended to limit the invention in any way. In addition, for convenience of explanation, it is explained that only the parts related to the related invention are shown in the attached drawings.

It should be noted that the features of the embodiments and embodiments of the present application can be combined with one another without inconsistency. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Reference will now be made in detail to the present application, examples of which are illustrated in the accompanying drawings.

FIG. 1 shows an exemplary system architecture 100 that can be applied to embodiments of the image-based information retrieval method or image-based information retrieval apparatus of the present application.

1, the system architecture 100 may include terminal devices 101, 102 and 103, a network 104 and a server 105. As shown in FIG. The network 104 is used as a medium for providing a communication link between the terminal devices 101, 102, 103 and the server 105. [ The network 104 may include various types of connections, such as, for example, wired communication links, wireless communication links, or fiber optic cables.

A user may receive or transmit messages, etc., in exchange with the server 105 via the network 104 using the terminal devices 101, 102, Various communication client applications may be installed on the terminal devices 101, 102, 103, such as camera software, search type applications, web browser applications, shopping type applications, instant communication means, email clients, social platform software,

The terminal devices 101, 102, and 103 may be various electronic devices having a screen and supporting information retrieval, and may be a smart phone, a tablet PC, an electronic book reader, an MP3 player (Moving Picture Experts Group Audio Layer III Layer 3), MP4 (Moving Picture Experts Group Audio Layer 4) player, laptop-type computer, and desktop-type computer.

The server 105 may be a server that provides various services, for example, a background information inquiry server that provides support for a search engine on the terminal devices 101, 102, The background information inquiry server can perform processing such as extraction and analysis on the received image data, and can feed back processing results to the terminal device.

It is to be noted that the image-based information retrieval method provided by the embodiment of the present application is typically executed by the server 105, and therefore, the image-based information retrieval apparatus is usually installed in the server 105.

It should be understood that the number of terminal devices, networks, and servers in FIG. 1 is exemplary only. Depending on the implementation demand, any number of terminal devices, networks and servers may be provided.

Referring now to FIG. 2, FIG. 2 illustrates a flow 200 of an embodiment of an image-based information retrieval method according to the present application. The image-based information retrieval method includes the following steps.

In step 201, the first feature information of the target to be searched in the first image input to the terminal is extracted.

In the present embodiment, an electronic device (for example, a server shown in FIG. 1) in which an image-based information retrieving method is operated may be a terminal And the electronic device can then extract the first feature information of the target to be searched in the first image, wherein the first image includes the target to be searched. Here, the target to be searched may be any object capable of expressing its characteristic as an image, and includes, but is not limited to, a cellular phone, a building, a clothing, a bag, etc., And the outline information of the object included in the image may be viewed as one of the graphic information), but the present invention is not limited thereto. The wireless connection method includes a 3G / 4G connection, a WiFi connection, a Bluetooth connection, a WiMAX connection, a Zigbee connection, an ultra wideband (UWB) connection, It should be clear that the present invention is not limited thereto.

Typically, the user searches for information using a search engine or the like installed in the terminal, and the user can input a first image including the target to be searched in the search window of the search engine. In the present embodiment, the image may include images in the jpg format, jpeg format, gif format, png format, bmp format, tiff format, pcx format, or other types of images to be developed in the future.

In this embodiment, first feature information can be extracted from the first image by a method such as extraction of color features, extraction of feature images, extraction of shape features, or extraction of spatial relation features. It is a well-known technology that is widely studied and applied, and a redundant description thereof will be omitted.

In step 202, a cycling step is performed based on the first feature information, wherein the cycling step includes the following steps.

In step 2021, it is determined whether or not a search target matching the first feature information exists in the default search database.

In this embodiment, a search database is created in advance on the electronic device, and the search database can store and store the image of the search target, the feature information related to the search target in each image, and the name information of the search target have. The feature information related to the search target may be matched with the extracted first feature information to determine whether or not there is a search target matching the first feature information in the database, If there is a search target matching the one feature information, the process moves to step 2022; If it is determined that there is no search target matching the first feature information, the process moves to step 2023.

In some selectable implementations of this embodiment, the search target may include a cell phone, a building, a clothing, a bag, etc., and the name information may include attributes of a search target, a brand, a model number, . For example, if the search target is a mobile phone, the corresponding name may be the brand or model number of the corresponding mobile phone, such as iPhone 6s; If the search target is a building, the name corresponding to the search target may be a name and a point of a corresponding building such as a Beijing Bird's Nest, a Beijing Forbidden City, and the like.

In some selectable implementations of this embodiment, the electronic device matches the first feature information with the feature information of each search target, and if the similarity of the matching result of the feature information of the first search target with the feature information of the one search target If the search target is larger than the threshold value, it is determined that the search target and the first feature information are matched with each other. Otherwise, it is determined that the search target and the first feature information do not match with each other.

In step 2022, name information corresponding to the search target is obtained.

In the present embodiment, based on the determination result obtained in step 2021, the electronic device (e.g., the server shown in Fig. 1) searches for a search target matching the first feature information and a name corresponding to the search target Information can be obtained. Here, the obtained name information is the name information of the target to be searched.

In step 2023, the second feature information of the target to be searched in the second image input to the terminal is extracted, and the second feature information and the first feature information are combined and used as the first feature information.

In the present embodiment, the electronic device acquires a second image input to the terminal, and the second image also includes the target to be searched. Then, the electronic device extracts second characteristic information of the target to be searched in the second image, uses the extracted second characteristic information and the first characteristic information later as the first characteristic information, 2021), and then determines whether there is a search target matching the first feature information in the default search database.

In some selectable implementations of this embodiment, the first feature information of the target to be searched in the first image and the second feature information of the target to be searched in the second image are not completely identical. For example, the first image is a front view of the target to be searched, and the second image is a side view of the target to be searched; Alternatively, the first image is an overall view of the target to be viewed, and the second image is a local view of the target to be viewed.

In some selectable implementations of this embodiment, the electronic device may be configured to acquire a first image and / or a second image taken with respect to the target to be searched by the terminal, or to acquire a first image and / And / or acquire a second image, or obtain a first image and / or a second image retrieved from an internet gallery with the terminal.

In step 205, the terminal displays a search result corresponding to the target name information and the name information to be searched.

In this embodiment, in the electronic device in which the image-based information retrieval method is operated, the name information obtained in step 202 and the search result corresponding to the corresponding name information are transmitted to the terminal, And displays the search result corresponding to the name information of the target and the corresponding name information.

In some selectable implementations of this embodiment, the search result corresponding to the name information may be a web site address or a web link related to the name information.

Referring now to FIG. 3, FIG. 3 is an example of an application scene of an image-based information retrieval method according to the present embodiment. In the application scene shown in Fig. 3, the user first inputs the first image 301. Fig. Then, the information search server acquires the first image and extracts first feature information of the target to be searched in the first image (for example, shape feature information of the target to be searched) in the first image. Next, a circulation step as described below is executed, and in the circulation step, it is judged whether or not there exists a search target matching the shape information in the default search database, and the judgment result may be "yes" or "no" , And the information search server transmits different presentation information to the user according to the result of the different determination. That is, if the result of the determination is " NO ", the user can instruct the user to upload a second image, as shown; The information search server obtains a second image uploaded by the user, extracts second feature information of a target to be searched in the second image, and then combines the extracted second feature information and the first feature information to obtain a first And the circulation step is continued using the feature information. Later, name information corresponding to the search target (e.g., Beijing Bird Nest) is acquired, and a search corresponding to the obtained name information Beijing Bird Nest and Beijing Bird Nest (Beijing Bird Nest) Results are displayed.

The image-based information search method provided by the present application extracts first feature information of a target to be searched in a first image input to a terminal, and a search target matching the first feature information exists in a default search database The second feature information of the target to be searched in the input second image is combined with the first feature information to use as the first feature information, And the search result corresponding to the name information of the target to be searched and the search result corresponding to the name information to be searched is finally displayed in the terminal, thereby improving the accuracy of the image-based information search .

In some selectable ways, as shown in Fig. 4, the second feature information of the target to be searched in the second image input to the terminal in step 2023 is extracted, and the second feature information and the first feature Using the information as the first feature information can be realized by the following steps.

In step 401, it is determined whether the number of times the circulation step is executed is less than a predetermined threshold value.

In this implementation, the electronic device (e.g., the server shown in FIG. 1) in which the image-based information retrieving method runs can set a threshold value in advance for the number of times of execution of the circulation step. Then, the electronic device determines whether the number of times the circulation step is performed is smaller than the threshold value. If it is determined that the number of times the circulation step is performed is equal to or greater than the threshold value, the electronic apparatus proceeds to step 402 , And if it is determined that the number of times the circulation step is executed is smaller than the threshold value, the flow proceeds to step 403.

In step 402, the terminal generates presentation information indicating a search failure.

In this implementation, if the number of times that the circulation step is already performed is equal to or greater than the threshold value, the electronic device immediately ends the circulation step, even if it has not acquired the inquiry target matched with the first feature information, And transmits presentation information of the search failure to the terminal. Here, the presentation information of the search failure may be character information informing the user of the search failure, and may be the search result information informing the user that the query is not completely accurate.

In step 403, presentation information is presented that suggests inputting a second picture to the terminal.

In this implementation, if the electronic device fails to acquire an inquiry target that matches the first feature information, but the number of times the circulation step is performed is less than the threshold value, To be displayed.

In step 404, the second feature information of the target to be searched is extracted from the second image input to the terminal.

In this implementation, when the user inputs a second image based on the presentation information in step 403, the electronic device acquires the second image, and as the second feature information, And acquires feature information of the target. Here, the second image includes the target to be searched.

In step 405, the second feature information and the first feature information are combined and used as the first feature information.

In the present embodiment, the electronic device uses the obtained second feature information and the first feature information as a first feature information, and searches for a match that matches the first feature information in the default search database It is determined whether or not a target exists. Here, the first feature information is more complete in comparison with the first feature information. For example, if the threshold value is 3, the electronic device first executes the circulation step, and in the circulation step, assuming that there is no search target matching the first feature information in the default search database , Presentation information for presenting a second image to the terminal is generated and the second feature information extracted from the second image and the first feature information are combined and used as the first feature information. The electronic device executes the second circulation step, and if it is assumed that there is no search target still matching the first feature information in the default search database in the circulation step, Presentation information for presenting input of an image is generated and the second feature information extracted from the second image is combined with the first feature information to use as the first feature information. The electronic device executes the third circulation step, and if the search target matching the first feature information does not yet exist in the default search database, the circulation step is terminated and the search failure is presented And if there is a search target matching the first feature information in the default search database, the name information corresponding to the search target is obtained.

The method provided by the implementation method of the above-described embodiment of the present application can conveniently control the number of images input to the terminal by setting the number of times the circulation step is executed, thereby controlling the time consumed for information search Thereby improving the efficiency of information retrieval.

Referring now to FIG. 5, in an implementation of the method shown in each of the figures, the present application provides an embodiment of an image-based information retrieval apparatus, which corresponds to the method embodiment shown in FIG. 2 And the device can be specifically applied to various electronic devices.

5, the image-based information retrieval apparatus 500 described in this embodiment includes an extraction module 501, a circulation step execution module 502, and a display module 503. [ Here, the extraction module 501 is configured to extract the first feature information of the target to be searched in the first image input to the terminal, and the first image includes the target to be searched. The circulation step execution module 502 is configured to execute the circulation step based on the first feature information, and in the circulation step, whether or not a search target matching the first feature information exists in the default search database Extracts second characteristic information of the target to be searched in the second image input to the terminal, and if the second characteristic information matches the second characteristic information, The first feature information is combined and used as the first feature information to continue the cyclic step. The display module 503 is configured to display a search result corresponding to the name information of the target to be searched and the corresponding name information in the terminal.

In the present embodiment, the image-based information retrieving apparatus 500 further includes an acquiring module (not shown), and the acquiring module (not shown) acquires a first image and / Or acquire a first image and / or a second image locally stored in the terminal, or acquire a first image and / or a second image retrieved from the internet gallery with the terminal.

In some selectable implementations of this embodiment, the first feature information of the target to be searched in the first image acquired by the extraction module 501 and the first feature information of the target to be searched in the second image acquired by the cyclic phase execution module 502 The second characteristic information of the target is not completely the same.

In some selectable implementations of this embodiment, the default search database of the circulation step execution module 502 includes at least a search target, feature information of the search target, and name information of the search target.

In some selectable implementations of this embodiment, the cycling phase execution module 502 determines whether the number of times the cycling phase is performed is less than a predetermined threshold value, and if so, Extracts second characteristic information of the target to be searched in the image, and generates presentation information for presenting a search failure to the terminal.

In some selectable implementations of this embodiment, the cycling step execution module 502 generates presentation information that suggests inputting a second image to the terminal, and includes presentation information to include in the second image the target to be searched Composed of forward; And further to extract the second feature information of the target to be searched from the second image input to the terminal.

The image-based information retrieval apparatus 500 further includes some other known configurations, such as, for example, a processor, a storage device, etc., and such known configurations are shown in FIG. 5 so as not to unnecessarily obscure the embodiments of the present disclosure. Which will be apparent to those skilled in the art.

Referring now to Figure 6 below, Figure 6 shows an exemplary configuration diagram of a computer system 600 suitable for implementing a terminal device or server in an embodiment of the present application.

6, the computer system 600 includes a central processing unit 601, in which the CPU 601 reads a program stored in a read-only memory device 602 (ROM) Various suitable operations and processes can be performed by the program loaded in the random access memory device 603 (RAM). The RAM 603 further stores various programs and data necessary for operating the system 600. [ The CPU 601, the ROM 602 and the RAM 603 are connected to each other via a bus 604. [ An input / output (I / O) interface 605 is also coupled to the bus 604.

The input unit 606 includes a keyboard, a mouse, and the like. The output unit 606 includes a cathode ray tube (CRT), a liquid crystal display (LCD) A storage unit 608 including a hard drive or the like and a communication unit 609 including a network interface card such as a LAN card or a modem. The communication unit 609 executes a communication process through a network such as the Internet. The driver 610 is also connected to the I / O interface 605 according to demand. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory device, or the like, is installed in the drive 610 according to demand to install the computer program read from such medium in the storage 608, do.

In particular, and in accordance with the embodiments of the present disclosure, the processes described with reference to the flowcharts may be implemented in a computer software program. For example, an embodiment of the present disclosure includes a computer program product, wherein the computer program product comprises a computer program tangibly embodied in a machine-readable medium, the computer program comprising computer executable instructions for executing the method Includes computer code. In this embodiment, the computer program may be downloaded and installed from the network via the communication unit 609 and / or installed from the removable medium 611. [ When the computer program is executed by the central processing unit 601 (CPU), the function defined in the method of the present application is executed.

The flowcharts and block diagrams in the accompanying drawings illustrate the system structures, functions, and operations of the systems, methods, and computer program products according to the embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a portion of a code, and the module, program segment, or portion of code may include one or more Executable instructions. It should be noted that for some alternative implementations, the functions indicated in the blocks may occur in an order different from the order indicated in the accompanying drawings. For example, two sequentially displayed blocks may be executed substantially concurrently, or in some cases in reverse order, depending on the function involved. Each block and / or block diagram in the block diagrams and / or flowchart illustrations and / or combinations of blocks in the flowchart illustrations may be embodied in a hardware-based, dedicated system that performs the specified functions or operations, or may be implemented in a combination of dedicated hardware and computer instructions .

The related modules described in the embodiments of the present application may be implemented in a software manner or in a hardware manner. The described modules may be installed in the processor, for example, the processor may be described as including an extraction module, a circulation step execution module, and a display module. For example, the extraction module may include a module for extracting the first feature information of the target to be searched in the first image input to the terminal, ".

In another aspect, the present application further provides a non-volatile computer storage medium, wherein the non-volatile computer storage medium may be a non-volatile computer storage medium included in the apparatus described in the embodiments; Or may be a non-volatile computer storage medium that is not located in a terminal but is present separately. Wherein one or a plurality of programs are stored in the nonvolatile computer storage medium and the one or more programs are executed by one device, Extracting feature information;

A step of executing a circulation step based on the first feature information, wherein in the circulation step, it is judged whether or not a search target matching the first feature information exists in a default search database, Extracts second characteristic information of a target to be searched in a second image input to the terminal, and combines the second characteristic information and the first characteristic information to obtain first characteristic information To continue the cycling step; The terminal displays the name information of the target to be searched and the search result corresponding to the name information, and the first image includes the target to be searched.

The foregoing description is merely an illustration of the relatively preferred embodiments of the present application and the technical principles in operation. It is to be understood that the scope of the invention as claimed in the present application is not limited to technical solutions made up of specific combinations of the technical features but may be applied to other technical solutions made up of any combination of the technical features or their equivalent features without departing from the gist of the invention It should be understood by those skilled in the art. For example, technical measures made by replacing the above-described features with technical features having similar functions as those disclosed in this application, but not limited thereto, are also included.

100: System architecture 101, 102, 103: Terminal device
104: Network 105: Server
500: Image-based information retrieval apparatus 501: Extraction module
502: circulation step execution module 503: display module

Claims (14)

In an image-based information retrieval method,
Extracting first feature information of a target to be searched in a first image input to the terminal;
A step of executing a circulation step based on the first feature information, wherein in the circulation step, it is judged whether or not a search target matching the first feature information exists in a default search database, Extracts second characteristic information of a target to be searched in a second image input to the terminal, and combines the second characteristic information and the first characteristic information to obtain a first characteristic information Continuously executing the circulation step by using the characteristic information as the characteristic information; And
And displaying the search result corresponding to the name information and the name information of the target to be searched in the terminal,
Wherein the first image includes the target to be searched. The method according to claim 1,
Wherein the default search database includes at least a search target, feature information of a search target, and name information of a search target. 3. The method of claim 2,
Wherein the first feature information of the target to be searched in the first image and the second feature information of the target to be searched in the second image are not completely identical. The method of claim 3,
Wherein the extracting of the second feature information of the target to be searched in the second image input to the terminal comprises:
Determining whether the number of times of executing the circulation step is less than a predetermined threshold value,
Extracts second characteristic information of the target to be searched from the second image input to the terminal,
Or generating presentation information for presenting a search failure to the terminal. The method according to claim 1 or 4,
Wherein the extracting of the second feature information of the target to be searched in the second image input to the terminal comprises:
Generating presentation information for presenting a second image to the terminal,
And extracting second characteristic information of the target to be searched from the second image input to the terminal,
And the second image includes the target to be searched. The method according to claim 1,
Obtaining the first image and / or the second image captured with respect to the target to be searched by the terminal; or
Obtaining the first image and / or the second image locally stored in the terminal; or
Further comprising the step of acquiring the first image and / or the second image retrieved from the Internet gallery by the terminal. In an image-based information retrieval apparatus,
An extraction module configured to extract first feature information of a target to be searched in a first image input to the terminal, the extraction module including the target to be searched in the first image;
Wherein the search step is configured to execute a circulation step based on the first feature information, wherein in the circulation step, it is determined whether or not a search target matching the first feature information exists in a default search database, Extracts second characteristic information of a target to be searched in a second image input to the terminal, and combines the second characteristic information with the first characteristic information A circulation step execution module that continuously uses the circulation step as the first feature information; And
And a display module configured to display the name information of the target to be searched and the search result corresponding to the name information in the terminal. 8. The method of claim 7,
Wherein the default search database includes at least a search target, feature information of the search target, and name information of the search target. 9. The method of claim 8,
Wherein the first feature information of the target to be searched in the first image and the second feature information of the target to be searched in the second image are not completely identical. 10. The method of claim 9,
Wherein the circulation step execution module comprises:
Determining whether the number of times of executing the circulation step is less than a predetermined threshold value,
Extracts second characteristic information of the target to be searched from the second image input to the terminal,
Or the presentation information indicating the failure of the search to the terminal. 11. The method according to claim 7 or 10,
Wherein the circulation step execution module comprises:
Generating presentation information for presenting a second image to the terminal,
And the second feature information of the target to be searched is extracted from the second image input to the terminal,
And the second image includes the target to be searched. 8. The method of claim 7,
Acquiring the first image and / or the second image captured with respect to the target to be searched by the terminal,
Acquiring the first image and / or the second image locally stored in the terminal,
And an acquiring module configured to acquire the first image and / or the second image retrieved from the Internet gallery by the terminal. In the device,
A processor; And
A storage device,
Wherein the storage device stores computer readable instructions executable by the processor and, when the computer readable instructions are executed, the processor executes an image based information retrieval method,
Extracting first feature information of a target to be searched in a first image input to the terminal;
A step of executing a circulation step based on the first feature information, wherein in the circulation step, it is judged whether or not a search target matching the first feature information exists in a default search database, Extracts second characteristic information of a target to be searched in a second image input to the terminal, and combines the second characteristic information and the first characteristic information to obtain a first characteristic information Continuously executing the circulation step by using the characteristic information as the characteristic information; And
And displaying the search result corresponding to the name information and the name information of the target to be searched in the terminal,
Wherein the first image includes the target to be searched. For non-volatile computer storage media,
Wherein the computer storage medium stores computer readable instructions that can be executed by a processor and, when the computer readable instructions are executed by a processor, the processor executes an image based information retrieval method,
Extracting first feature information of a target to be searched in a first image input to the terminal;
A step of executing a circulation step based on the first feature information, wherein in the circulation step, it is judged whether or not there exists a search target matching the first feature information in a default search database, Extracts second characteristic information of a target to be searched in a second image input to the terminal, and combines the second characteristic information and the first characteristic information to obtain a first characteristic information Continuously executing the circulation step by using the characteristic information as the characteristic information; And
And displaying the search result corresponding to the name information and the name information of the target to be searched in the terminal,
Wherein the first image includes the target to be searched.

Images