CN110851636A - Image searching system, method and device - Google Patents
Image searching system, method and device Download PDFInfo
- Publication number
- CN110851636A CN110851636A CN201810819415.XA CN201810819415A CN110851636A CN 110851636 A CN110851636 A CN 110851636A CN 201810819415 A CN201810819415 A CN 201810819415A CN 110851636 A CN110851636 A CN 110851636A
- Authority
- CN
- China
- Prior art keywords
- image
- target object
- object image
- client
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Processing Or Creating Images (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the application provides an image searching system, method and device. The system comprises: a client and a server. The client sends the clue images to the server; the server receives the clue image sent by the client, detects each object area in the clue image and sends each object area to the client; the client receives each object area sent by the server, determines a target object area from the clue image according to each received object area, and sends the target object area to the server; the server receives a target object area sent by the client, determines a target object image matched with the clue image from a preset object image library according to the target object area, and sends the target object image to the client; the object image library is used for storing each object image. By applying the scheme provided by the embodiment of the application, the object image can be searched from the object image library through the client.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to an image search system, method, and apparatus.
Background
Searching images in a map is a technique for searching an image similar to a known image from an image library based on the image. The searched image contains the same object as that in the known image. The object may be a vehicle, a person, an animal, or other object. The image library may further include information corresponding to each image. After each image is searched from the image library, information corresponding to the images can be obtained from the image library.
When a user obtains a clue image and needs to query an object image and object information matched with the clue image from an object image library, the object image library can be searched for an object image containing the same object as the clue image. In order to more conveniently enable a user to obtain required information from an object image library, the user has a need to search for an object image from the object image library through a client.
Disclosure of Invention
The embodiment of the application aims to provide an image searching system, method and device so as to search an object image from an object image library through a client. The specific technical scheme is as follows.
In a first aspect, an embodiment of the present application provides an image search system, where the system includes: a client and a server;
the client is used for acquiring a clue image and sending the clue image to the server;
the server is used for receiving the clue image sent by the client, detecting each object area in the clue image and sending each object area to the client;
the client is used for receiving each object area sent by the server, determining a target object area from the clue image according to each received object area, and sending the target object area to the server;
the server is used for receiving a target object area sent by the client, determining a target object image matched with the clue image from a preset object image library according to the target object area, and sending the target object image to the client; the object image library is used for storing each object image;
and the client receives the target object image sent by the server.
Optionally, the object image library is specifically configured to store a correspondence between each object image and model data of an object region of the object image;
the server, when determining a target object image matching the cue image from a preset object image library according to the target object area, includes:
determining target model data of the target object area according to a preset modeling algorithm;
matching the target model data with each model data in the object image library respectively;
and determining the object image corresponding to the model data in the object image library which is successfully matched as the target object image matched with the clue image.
Optionally, when determining the target object region from the cue image according to the received object regions, the client includes:
displaying the received respective object regions;
determining a target object area from each object area according to a selection operation input for each displayed object area; alternatively, the target object region is determined from the cue image in accordance with a drawing operation input for a region other than the respective object regions in the displayed cue image.
Optionally, when the server sends the target object image to the client, the server includes:
reducing the data amount of the target object image;
and sending the target object image with the reduced data size to the client.
Optionally, when reducing the data size of the target object image, the server includes:
and determining a thumbnail of each target object image, and taking the thumbnail of each target object image as the target object image with reduced data size.
Optionally, when reducing the data size of the target object image, the server includes:
acquiring the similarity between each target object image and the clue image as reference similarity;
performing resolution reduction processing on one or more target object images according to the reference similarity and a preset processing rule corresponding to the reference similarity;
and sending the target object image subjected to resolution reduction processing and the target object image not subjected to resolution reduction processing to the client.
Optionally, when performing resolution reduction processing on one or more of the target object images, the server includes:
selecting other target object images except the target object image corresponding to the maximum reference similarity from all the target object images;
and performing resolution reduction processing on the other target object images.
In a second aspect, an embodiment of the present application provides an image search method, where the method includes:
obtaining a clue image sent by a client;
detecting each object area in the clue image and sending each object area to the client;
receiving a target object area sent by the client; the target object area is determined from the clue image by the client according to the received object areas;
determining a target object image matched with the clue image from a preset object image library according to the target object area; the object image library is used for storing each object image;
and sending the target object image to the client.
Optionally, the object image library is specifically configured to store a correspondence between each object image and model data of an object region of the object image;
the step of determining a target object image matched with the clue image from a preset object image library according to the target object region comprises the following steps:
determining target model data of the target object area according to a preset modeling algorithm;
matching the target model data with each model data in the object image library respectively;
and determining the object image corresponding to the model data in the object image library which is successfully matched as the target object image matched with the clue image.
Optionally, the step of sending the target object image to the client includes:
reducing the data amount of the target object image;
and sending the target object image with the reduced data size to the client.
Optionally, the step of reducing the data amount of the target object image includes:
and determining a thumbnail of each target object image, and taking the thumbnail of each target object image as the target object image with reduced data size.
Optionally, the step of reducing the data amount of the target object image includes:
acquiring the similarity between each target object image and the clue image as reference similarity;
performing resolution reduction processing on one or more target object images according to the reference similarity and a preset processing rule corresponding to the reference similarity;
and sending the target object image subjected to resolution reduction processing and the target object image not subjected to resolution reduction processing to the client.
Optionally, the step of performing resolution reduction processing on one or more target object images according to the reference similarity and a preset processing rule corresponding to the reference similarity includes:
selecting other target object images except the target object image corresponding to the maximum reference similarity from all the target object images;
and performing resolution reduction processing on the other target object images.
In a third aspect, an embodiment of the present application provides an image search apparatus, including:
the acquisition module is used for acquiring a clue image sent by a client;
a detection module for detecting each object region in the cue image;
the sending module is used for sending each object area to the client;
the receiving module is used for receiving the target object area sent by the client; the target object area is determined from the clue image by the client according to the received object areas;
the determining module is used for determining a target object image matched with the clue image from a preset object image library according to the target object area; the object image library is used for storing each object image;
the sending module is further configured to send the target object image to the client.
Optionally, the object image library is specifically configured to store a correspondence between each object image and model data of an object region of the object image;
the determining module is specifically configured to:
determining target model data of the target object area according to a preset modeling algorithm;
matching the target model data with each model data in the object image library respectively;
and determining the object image corresponding to the model data in the object image library which is successfully matched as the target object image matched with the clue image.
Optionally, the sending module includes:
a reduction submodule for reducing a data amount of the target object image;
and the sending submodule is used for sending the target object image with the reduced data size to the client.
In a fourth aspect, an embodiment of the present application provides an electronic device, where the electronic device includes a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus;
a memory for storing a computer program;
and the processor is used for realizing the image searching method provided by the second aspect when executing the program stored in the memory.
In a fifth aspect, the present application provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the computer program implements the image search method provided in the second aspect.
In the image search system provided by the embodiment of the application, the server may receive the cue image sent by the client, detect each object region in the cue image, send each object region to the client, determine the target object region from the cue image according to each object region by the client, send the determined target object region to the server, determine the matched target object image from the object image library according to the target object region by the server, and send the matched target object image to the client. Through the interaction process between the client and the server, the client can search the object image from the object image library. Of course, not all advantages described above need to be achieved at the same time in the practice of any one product or method of the present application.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the application, and that for a person skilled in the art, other drawings can be derived from them without inventive effort.
Fig. 1 is a schematic structural diagram of an image search system according to an embodiment of the present application;
fig. 2a is a schematic diagram of an interaction between a client and a server according to an embodiment of the present application;
fig. 2b is a schematic diagram of another interaction between a client and a server according to an embodiment of the present application;
3 a-3 d are a series of page displays in an example of a search image provided by an embodiment of the present application;
fig. 4 is a schematic flowchart of an image searching method according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an image searching apparatus according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solution in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. It is to be understood that the described embodiments are merely a few embodiments of the present application and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In order to realize the purpose of searching an object image from an object image library through a client, the embodiment of the application provides an image searching system, method and device. The present application will be described in detail below with reference to specific examples.
Fig. 1 is a schematic structural diagram of an image search system according to an embodiment of the present application. The system comprises: a client 101 and a server 102.
The client 101 is configured to obtain the cue images and send the cue images to the server 102.
The server 102 is configured to receive the cue image sent by the client 101, detect each object region in the cue image, and send each object region to the client 101.
And the client 101 is configured to receive each object region sent by the server 102, determine a target object region from the cue image according to the received each object region, and send the target object region to the server 102.
And the server 102 is configured to receive the target object area sent by the client 101, determine a target object image matched with the cue image from a preset object image library according to the target object area, and send the target object image to the client 101. The object image library is used for storing each object image.
The client 101 receives the target object image transmitted by the server 102.
Referring to fig. 2a, fig. 2a is a schematic diagram of an interaction process between a client and a server according to an embodiment of the present application. The client sends the clue image to the server, and after receiving the clue image, the server detects each object area from the clue image and sends each object area to the client. And after receiving each object area sent by the server, the client determines a target object area from the clue image according to each received object area and sends the target object area to the server. And after receiving the target object area sent by the client, the server determines a target object image matched with the clue image from the object image library according to the target object area and sends the target object image to the client. And the client receives the target object image sent by the server.
Here, the cue image may be understood as an image of an object region containing an object. The object may include a vehicle, a person, an animal, or other item. The object region may be understood as a region inside an object frame that frames the object. For example, the object region may be a body region, an animal region, or an object region. The cue image may be an image of an arbitrary background of an object region containing the object. For example, in the case where the object is a vehicle, the cue image may be an object image taken on a road; or an image of a subject captured in a parking lot. The present application does not limit the shooting scenes of the cue images. The clue image may include an object region of one object or may include object regions of a plurality of objects.
The clue image obtained by the client may be specifically obtained from other devices, or may be an image acquired by a camera included in the terminal device where the client is located. When the client side obtains the clue image, the clue image can be obtained according to the input operation of the user.
The server may specifically detect each object region from the cue image according to a preset object detection algorithm. In the detection, the detection may be performed based on the set number of pixels of the target region so as to detect the target region corresponding to the set number of pixels of the target region. For example, the minimum value of the number of pixels in the object region can be set to 256px × 256px, and the object regions in which the number of pixels in the cue image is not less than 256px × 256px can be detected. When the server sends each object area to the client, the server may send the coordinate information of each object area to the client.
The client may display a target frame representing the object area in the cable image when receiving the coordinate information of each object area.
The client determines the target object region from the cue image according to the received object regions, and specifically may include: displaying the received object areas, and determining target object areas from the object areas according to selection operations input aiming at the displayed object areas; alternatively, the target object region is determined from the cue image in accordance with a rendering operation input for a region other than the respective object regions in the displayed cue image. The determined target object regions may be one or more of the respective object regions, or may be other object regions in the cue image besides the respective object regions.
The client may display the cue image when acquiring the cue image, or may display the cue image and each object region when receiving each object region.
The client may receive a selection operation input by a user for each object region, and determine a target object region from each object region according to the selection operation.
When there is no object region that the user wants to select among the object regions displayed by the client, the client may provide a drawing function to the user so that the user may draw a desired object region in the line index image. When receiving a drawing operation input by a user for a displayed clue image, the client determines a target object area from the clue image according to the drawing operation.
The client may detect each coordinate point indicated in the user drawing operation, and determine the coordinates of the target object region according to each coordinate point.
The target object region may be a preset shape, such as a rectangle; or irregular shapes such as irregular polygons.
When the client sends the target object area to the server, the client may specifically send the coordinate information of the target object area to the server. And the server receives the coordinate information of the target object area sent by the client.
In the object image library, each object image may include different objects or may include the same object. Each object image in the object image library may include an object region of one object, or may include object regions of a plurality of objects. This is not a particular limitation of the present application.
The target object image matched with the cue image may be understood as a similar object between the object in the cue image and the object in the target object image. The number of the determined target object images may be one or more.
As can be seen from the above, in the image search system provided in this embodiment, the server may receive the cue image sent by the client, detect each object region in the cue image, send each object region to the client, determine, by the client, a target object region from the cue image according to each object region, send the determined target object region to the server, determine, by the server, a matched target object image from the object image library according to the target object region, and send the matched target object image to the client. Through the interaction process between the client and the server, the client can search the object image from the object image library.
In another embodiment of the present application, the object image library may be further configured to store object information corresponding to each object image. The object image library may be understood as a database. Wherein, when the object is a vehicle, the object information is vehicle information. The vehicle information may include a time when the vehicle passes a place in the vehicle image, place information where the vehicle is located, a vehicle color, a license plate number, a vehicle brand, a vehicle size type, and the like. The location information of the vehicle may be a gate location or the like. When the object is a person, the object information may include the time when the person passes through the image capturing place, the sex, the height, and the like of the person. In the following description, the object is described as an example.
When determining the target object image, the server 102 may determine object information corresponding to the target object image from the object image library, and send the object information to the client. When receiving the target object image and the corresponding object information sent by the server, the client may display the target object image and the corresponding object information.
In another embodiment of the present application, the object image library is specifically configured to store a correspondence relationship between each object image and model data of an object region of the object image. The model data in the object image library is determined in advance according to a preset modeling algorithm. Wherein, the modeling algorithm can be an object structured modeling algorithm in the related art. The model data of the object region of each object image in the object image library may be obtained in advance in the following manner: and detecting an object region from each object image according to a preset object detection algorithm, and determining model data of the object region according to a preset modeling algorithm.
When the server 102 determines the target object image matched with the cue image from the preset object image library according to the target object region, specifically, the target model data of the target object region may be determined according to a preset modeling algorithm, the target model data is respectively matched with each model data in the object image library, and the object image corresponding to the model data in the object image library which is successfully matched is determined as the target object image matched with the cue image.
Specifically, during matching, the server may respectively determine similarity between the model data and each model data in the object image library, and when the similarity is greater than a preset threshold, it is determined that the model data is successfully matched with the model data in the object image library; and when the similarity is not greater than a preset threshold value, determining that the model data fails to be matched with the model data in the object image library. The preset threshold may be that the client sends to the server.
When the model data is successfully matched with the model data in the object image library, the object corresponding to the target object region and the object in the object image corresponding to the model data in the object image library are considered to be similar objects.
In summary, in this embodiment, the target image corresponding to each model data in the successfully matched target image library may be determined as the target object image according to the matching result between the model data of the target object area and the model data of the object area in the target image library, so that the target object image can be determined more accurately.
Compared with the scheme that after the server detects each object area in the clue image, the server determines the model data of each object area according to the preset modeling algorithm, then sends each object area to the client, receives the target object area sent by the client, and determines the target object image matched with the clue image from the object image library according to the model data of the target object area, the server determines the model data of the target object area according to the modeling algorithm after determining the target object area, when part of the object areas in each object area of the target object area are determined, the server does not need to determine the model data of each object area, and the processing time of the server can be saved. In addition, after each object area is detected, the object areas are sent to the client, the client can be responded in time, and user experience is improved.
For example, it is known that there are 8 vehicles in the cue image, and the server detects 8 vehicles from the cue image, which takes 1 s. The server determines model data respectively for the detected images of 8 vehicles, namely modeling is carried out respectively, and if the modeling process of each vehicle takes 1s, the total time of the modeling process takes 8 s. After the model data is determined, the body areas of 8 vehicles are returned to the client, so that clue images are sent from the client to the server until the client receives 8 body areas, at least 9 seconds are needed, in the process, the user waits all the time, and the user experience is very poor.
According to the scheme of this embodiment, the time consumed when the client and the server interact with each other can be seen from fig. 2 b. The time spent on sending the clue images to the server by the client is 0.3s, the time spent on detecting the vehicle body areas from the clue images by the server after receiving the clue images is 1s, the time spent on sending each vehicle body area to the client by the server is 0.1s, the time spent on sending the target vehicle body areas to the server by the client is 0.1s, and when one target vehicle body area is formed, the server only needs to model one target vehicle body area for 1 s. Therefore, in the embodiment, the client sends the cue images to the server, and the client receives 8 body regions, which approximately needs 0.3s +1 s-1.3 s, and the modeling process approximately needs 1 s. This saves a lot of time.
After receiving each body area sent by the server, the client can display each body area in the cable image and prompt the user to select a target body area from each body area or draw the target body area by hand in the cable image. When the user selects the hand-drawn target body region, it is considered that there is no vehicle of interest to the user in each of the displayed body regions. And after the client determines the target vehicle body area, submitting the target vehicle body area to the server.
In order to further shorten the time for the server to respond to the client and improve the user experience, the following embodiments are also provided in the present application. In another embodiment of the present application, when the server 102 sends the target object image to the client 101, the method may include:
the data amount of the target object image is reduced, and the target object image with the reduced data amount is transmitted to the client 101.
In this embodiment, the server and the client may be connected via a network, and when the data amount of the target object image is reduced, time consumed for sending the target object image to the client may be reduced, so that the time for the server to respond to the client may be shortened, and the user experience may be improved.
Various embodiments may be included in reducing the amount of data of the target object image. For example, the server 102 may determine a thumbnail of each target object image as a target object image with a reduced data amount.
In another embodiment, the server 102 may be specifically configured to reduce the data amount of the target object image by:
acquiring the similarity between each target object image and the clue image as reference similarity; performing resolution reduction processing on one or more of the target object images according to the reference similarity and a preset processing rule corresponding to the reference similarity; both the target object image after the resolution reduction processing and the target object image without the resolution reduction processing are transmitted to the client 101.
The similarity may be a similarity between model data of the object region of the target object image and model data of the object region of the cue image.
When the server performs resolution reduction processing on one or more of the target object images, the resolution of the target object image which needs to be reduced in resolution may be reduced to a preset resolution.
When determining which target object image is to be subjected to the resolution reduction processing, the server 102 may specifically select another target object image other than the target object image corresponding to the maximum reference similarity from the respective target object images, and perform the resolution reduction processing on the other target object images.
The object in the target object image corresponding to the maximum reference similarity is most similar to the object in the target object region, and the resolution of the target object image may not be reduced, so that the clearest image may be provided to the user. The similarity between the object in the other target object image and the object in the target object region is low, and the resolution of the image can be reduced. This makes it possible to reduce the amount of image data transmitted while taking into account the user's feeling of use as much as possible.
In another embodiment of the present application, the server may include an analysis server, a comparison server, and a storage server. The analysis server is used for receiving the clue images sent by the client, detecting each object area in the clue images, sending each object area to the client, receiving the target object area sent by the client, determining the model data of the target object area according to a preset modeling algorithm, and sending the model data of the target object area to the comparison server. The comparison server receives the model data of the target object area sent by the analysis server, matches the model data of the target object area with the model data of the object area of each object image in a preset object image library, and determines the object image corresponding to the model data in the object image library which is successfully matched as the target object image matched with the clue image.
The storage server is used for storing a preset object image library. The comparison server may read data in the object image library from the storage server.
The present application will be described in detail with reference to specific examples.
Referring to fig. 3a to 3d, the images are schematic diagrams of a process of searching for an image from a server through a client.
And uploading the pictures (clue images) of the vehicles to be analyzed on a client web interface of the front end. The server at the rear end receives the clue image uploaded by the web interface, the server adopts a vehicle body detection algorithm to perform full-image detection on the clue image, and the corresponding vehicle coordinates can be generated as long as the number of vehicle target pixel points in the image is in accordance with 256 px-256 px. The server sends the vehicle coordinates to the web interface.
The client receives the vehicle coordinates sent by the server, changes the vehicle coordinates into a target frame, and positions the vehicle in the frame. Referring to fig. 3a, fig. 3a is a reference diagram of a web page. The browsing area of the interface displays clue images, 6 vehicles in the clue images are detected, and other vehicles cannot be detected due to the fact that the number of pixel points is too small. The client may then submit the vehicle of interest selected by the user to the server (submission target body area). Referring to fig. 3b, the frame of the body region selected by the user is displayed differently from the other frames, and the vehicle selected by the user is displayed enlarged on the right side. The client can also send the vehicle body similarity (preset threshold) or the feature similarity set by the user to the server.
If the user is not interested in the automatically generated vehicle target frames, the target frames can be erased, the interested area is drawn manually, the area of the rectangular frame in fig. 3c is the vehicle body area obtained by the client according to the drawing operation of the user, and the vehicle selected by the user is displayed on the right side in an enlarged manner.
After the server determines the target vehicle images from the vehicle image library according to the target vehicle body areas, the server sends each target vehicle image and corresponding vehicle information to the client, and the client can display the target vehicle images and the vehicle information on a web interface. Referring to fig. 3d, 3 images searched from the server are shown, information such as the passing vehicle section, the vehicle brand, the vehicle body color and the vehicle sub-brand is also shown, and the comprehensive similarity between each image and the clue image is also shown.
Fig. 4 is a schematic flowchart of an image searching method according to an embodiment of the present application. The method is applied to the electronic equipment. The electronic device may include a server, a general computer, or the like. The method includes the following steps S401 to S405.
Step S401: and obtaining a clue image sent by the client.
Step S402: and detecting each object area in the clue image and sending each object area to the client.
Specifically, each object region may be detected from the cue image according to a preset object detection algorithm. In the detection, the detection may be performed based on the set number of pixels of the target region so as to detect the target region corresponding to the set number of pixels of the target region.
When each object region is sent to the client, the coordinate information of each object region may be sent to the client.
Step S403: and receiving the target object area sent by the client.
And determining the target object area from the clue image for the client according to the received object areas. Specifically, the coordinate information of the target object area sent by the client is received.
Step S404: and determining a target object image matched with the clue image from a preset object image library according to the target object area. The object image library is used for storing each object image.
Step S405: and sending the target object image to the client.
As can be seen from the above, in the embodiment, the cue image sent by the client may be received, each object region in the cue image is detected, each object region is sent to the client, the client determines a target object region from the cue image according to each object region, sends the determined target object region to the electronic device, and the electronic device determines a matched target object image from the object image library according to the target object region, and sends the matched target object image to the client. Through the interaction process between the client and the electronic equipment, the client can search the object image from the object image library.
In another embodiment of the present application, the object image library is specifically configured to store a correspondence between each object image and model data of an object region of the object image;
the step of determining a target object image matched with the clue image from a preset object image library according to the target object region comprises the following steps:
determining target model data of the target object area according to a preset modeling algorithm;
matching the target model data with each model data in the object image library respectively;
and determining the object image corresponding to the model data in the object image library which is successfully matched as the target object image matched with the clue image.
In another embodiment of the present application, the step of sending the target object image to the client includes:
reducing the data amount of the target object image;
and sending the target object image with the reduced data size to the client.
In another embodiment of the present application, the step of reducing the data amount of the target object image includes:
and determining a thumbnail of each target object image, and taking the thumbnail of each target object image as the target object image with reduced data size.
In another embodiment of the present application, the step of reducing the data amount of the target object image includes:
acquiring the similarity between each target object image and the clue image as reference similarity;
performing resolution reduction processing on one or more target object images according to the reference similarity and a preset processing rule corresponding to the reference similarity;
and sending the target object image subjected to resolution reduction processing and the target object image not subjected to resolution reduction processing to the client.
In another embodiment of the present application, the step of performing resolution reduction processing on one or more of the target object images according to the reference similarity and a preset processing rule corresponding to the reference similarity includes:
selecting other target object images except the target object image corresponding to the maximum reference similarity from all the target object images;
and performing resolution reduction processing on the other target object images.
Fig. 5 is a schematic structural diagram of an image searching apparatus according to an embodiment of the present application. The embodiment is applied to electronic equipment. This embodiment corresponds to the embodiment of the method shown in fig. 4, and the apparatus includes:
an obtaining module 501, configured to obtain a cue image sent by a client;
a detection module 502, configured to detect each object region in the cue image;
a sending module 503, configured to send each object region to the client;
a receiving module 504, configured to receive a target object area sent by the client; the target object area is determined from the clue image by the client according to the received object areas;
a determining module 505, configured to determine, according to the target object region, a target object image matching the cue image from a preset object image library; the object image library is used for storing each object image;
the sending module 503 is further configured to send the target object image to the client.
In another embodiment of the present application, in the embodiment shown in fig. 5, the object image library is specifically configured to store a correspondence between each object image and model data of an object area of the object image;
the determining module is specifically configured to:
determining target model data of the target object area according to a preset modeling algorithm;
matching the target model data with each model data in the object image library respectively;
and determining the object image corresponding to the model data in the object image library which is successfully matched as the target object image matched with the clue image.
In another embodiment of the present application, in the embodiment shown in fig. 5, the sending module includes:
a reduction submodule for reducing a data amount of the target object image;
and the sending submodule is used for sending the target object image with the reduced data size to the client.
In another embodiment of the present application, in the embodiment shown in fig. 5, the reduction sub-module is specifically configured to:
and determining a thumbnail of each target object image, and taking the thumbnail of each target object image as the target object image with reduced data size.
In another embodiment of the present application, in the embodiment shown in fig. 5, the reduction sub-module is specifically configured to:
acquiring the similarity between each target object image and the clue image as reference similarity;
performing resolution reduction processing on one or more target object images according to the reference similarity and a preset processing rule corresponding to the reference similarity;
and sending the target object image subjected to resolution reduction processing and the target object image not subjected to resolution reduction processing to the client.
In another embodiment of the present application, in the embodiment shown in fig. 5, the reduction sub-module is specifically configured to:
selecting other target object images except the target object image corresponding to the maximum reference similarity from all the target object images;
and performing resolution reduction processing on the other target object images.
Since the device embodiment is obtained based on the method embodiment and has the same technical effect as the method, the technical effect of the device embodiment is not described herein again. For the apparatus embodiment, since it is substantially similar to the method embodiment, it is described relatively simply, and reference may be made to some descriptions of the method embodiment for relevant points.
Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application. The electronic device comprises a processor 601, a communication interface 602, a memory 603 and a communication bus 604, wherein the processor 601, the communication interface 602 and the memory 603 complete mutual communication through the communication bus 604;
a memory 603 for storing a computer program;
the processor 601 is configured to implement the image searching method provided in the embodiment of the present application when executing the program stored in the memory 603. The method comprises the following steps:
obtaining a clue image sent by a client;
detecting each object area in the clue image and sending each object area to the client;
receiving a target object area sent by the client; the target object area is determined from the clue image by the client according to the received object areas;
determining a target object image matched with the clue image from a preset object image library according to the target object area; the object image library is used for storing each object image;
and sending the target object image to the client.
As can be seen from the above, in the embodiment, the cue image sent by the client may be received, each object region in the cue image is detected, each object region is sent to the client, the client determines a target object region from the cue image according to each object region, sends the determined target object region to the electronic device, and the electronic device determines a matched target object image from the object image library according to the target object region, and sends the matched target object image to the client. Through the interaction process between the client and the electronic equipment, the client can search the object image from the object image library.
The communication bus 604 mentioned in the above electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus 604 may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface 602 is used for communication between the above-described electronic apparatus and other apparatuses.
The Memory 603 may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory 603 may also be at least one storage device located remotely from the aforementioned processor.
The Processor 601 may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware component.
The embodiment of the application also provides a computer readable storage medium, and a computer program is stored in the computer readable storage medium, and when being executed by a processor, the computer program realizes the image searching method provided by the embodiment of the application. The method comprises the following steps:
obtaining a clue image sent by a client;
detecting each object area in the clue image and sending each object area to the client;
receiving a target object area sent by the client; the target object area is determined from the clue image by the client according to the received object areas;
determining a target object image matched with the clue image from a preset object image library according to the target object area; the object image library is used for storing each object image;
and sending the target object image to the client.
As can be seen from the above, in the embodiment, the cue image sent by the client may be received, each object region in the cue image is detected, each object region is sent to the client, the client determines a target object region from the cue image according to each object region, sends the determined target object region to the electronic device, and the electronic device determines a matched target object image from the object image library according to the target object region, and sends the matched target object image to the client. Through the interaction process between the client and the electronic equipment, the client can search the object image from the object image library.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the method embodiment, since it is substantially similar to the system embodiment, it is relatively simple to describe, and reference may be made to the partial description of the system embodiment for relevant points.
The above description is only for the preferred embodiment of the present application, and is not intended to limit the scope of the present application. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application are included in the protection scope of the present application.
Claims (18)
1. An image search system, comprising: a client and a server;
the client is used for acquiring a clue image and sending the clue image to the server;
the server is used for receiving the clue image sent by the client, detecting each object area in the clue image and sending each object area to the client;
the client is used for receiving each object area sent by the server, determining a target object area from the clue image according to each received object area, and sending the target object area to the server;
the server is used for receiving a target object area sent by the client, determining a target object image matched with the clue image from a preset object image library according to the target object area, and sending the target object image to the client; the object image library is used for storing each object image;
and the client receives the target object image sent by the server.
2. The system according to claim 1, wherein the object image library is specifically configured to store a correspondence relationship between each object image and model data of an object region of the object image;
the server, when determining a target object image matching the cue image from a preset object image library according to the target object area, includes:
determining target model data of the target object area according to a preset modeling algorithm;
matching the target model data with each model data in the object image library respectively;
and determining the object image corresponding to the model data in the object image library which is successfully matched as the target object image matched with the clue image.
3. The system of claim 1, wherein the client determines the target object region from the cue image according to the received object regions, and comprises:
displaying the received respective object regions;
determining a target object area from each object area according to a selection operation input for each displayed object area; alternatively, the target object region is determined from the cue image in accordance with a drawing operation input for a region other than the respective object regions in the displayed cue image.
4. The system of claim 1, wherein the server, when sending the target object image to the client, comprises:
reducing the data amount of the target object image;
and sending the target object image with the reduced data size to the client.
5. The system according to claim 4, wherein the server, when reducing the data amount of the target object image, comprises:
and determining a thumbnail of each target object image, and taking the thumbnail of each target object image as the target object image with reduced data size.
6. The system according to claim 4, wherein the server, when reducing the data amount of the target object image, comprises:
acquiring the similarity between each target object image and the clue image as reference similarity;
performing resolution reduction processing on one or more target object images according to the reference similarity and a preset processing rule corresponding to the reference similarity;
and sending the target object image subjected to resolution reduction processing and the target object image not subjected to resolution reduction processing to the client.
7. The system of claim 6, wherein the server, when performing the resolution reduction processing on one or more of the respective target object images, comprises:
selecting other target object images except the target object image corresponding to the maximum reference similarity from all the target object images;
and performing resolution reduction processing on the other target object images.
8. An image search method, characterized in that the method comprises:
obtaining a clue image sent by a client;
detecting each object area in the clue image and sending each object area to the client;
receiving a target object area sent by the client; the target object area is determined from the clue image by the client according to the received object areas;
determining a target object image matched with the clue image from a preset object image library according to the target object area; the object image library is used for storing each object image;
and sending the target object image to the client.
9. The method according to claim 8, wherein the object image library is specifically configured to store correspondence between each object image and model data of an object region of the object image;
the step of determining a target object image matched with the clue image from a preset object image library according to the target object region comprises the following steps:
determining target model data of the target object area according to a preset modeling algorithm;
matching the target model data with each model data in the object image library respectively;
and determining the object image corresponding to the model data in the object image library which is successfully matched as the target object image matched with the clue image.
10. The method of claim 8, wherein the step of sending the target object image to the client comprises:
reducing the data amount of the target object image;
and sending the target object image with the reduced data size to the client.
11. The method of claim 10, wherein the step of reducing the amount of data of the target object image comprises:
and determining a thumbnail of each target object image, and taking the thumbnail of each target object image as the target object image with reduced data size.
12. The method of claim 10, wherein the step of reducing the amount of data of the target object image comprises:
acquiring the similarity between each target object image and the clue image as reference similarity;
performing resolution reduction processing on one or more target object images according to the reference similarity and a preset processing rule corresponding to the reference similarity;
and sending the target object image subjected to resolution reduction processing and the target object image not subjected to resolution reduction processing to the client.
13. The method according to claim 12, wherein the step of performing resolution reduction processing on one or more of the target object images according to the reference similarity and a preset processing rule corresponding to the reference similarity comprises:
selecting other target object images except the target object image corresponding to the maximum reference similarity from all the target object images;
and performing resolution reduction processing on the other target object images.
14. An image search apparatus, characterized in that the apparatus comprises:
the acquisition module is used for acquiring a clue image sent by a client;
a detection module for detecting each object region in the cue image;
the sending module is used for sending each object area to the client;
the receiving module is used for receiving the target object area sent by the client; the target object area is determined from the clue image by the client according to the received object areas;
the determining module is used for determining a target object image matched with the clue image from a preset object image library according to the target object area; the object image library is used for storing each object image;
the sending module is further configured to send the target object image to the client.
15. The apparatus according to claim 14, wherein the object image library is specifically configured to store a correspondence relationship between each object image and model data of an object region of the object image;
the determining module is specifically configured to:
determining target model data of the target object area according to a preset modeling algorithm;
matching the target model data with each model data in the object image library respectively;
and determining the object image corresponding to the model data in the object image library which is successfully matched as the target object image matched with the clue image.
16. The apparatus of claim 14, wherein the sending module comprises:
a reduction submodule for reducing a data amount of the target object image;
and the sending submodule is used for sending the target object image with the reduced data size to the client.
17. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any of claims 8 to 13 when executing a program stored in the memory.
18. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of the claims 8-13.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810819415.XA CN110851636B (en) | 2018-07-24 | 2018-07-24 | Image searching system, method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810819415.XA CN110851636B (en) | 2018-07-24 | 2018-07-24 | Image searching system, method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110851636A true CN110851636A (en) | 2020-02-28 |
| CN110851636B CN110851636B (en) | 2023-05-02 |
Family
ID=69594331
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810819415.XA Active CN110851636B (en) | 2018-07-24 | 2018-07-24 | Image searching system, method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110851636B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101639858A (en) * | 2009-08-21 | 2010-02-03 | 深圳创维数字技术股份有限公司 | Image search method based on target area matching |
| US20110218984A1 (en) * | 2008-12-22 | 2011-09-08 | Adi Gaash | Method and system for searching for information pertaining target objects |
| CN102831216A (en) * | 2012-08-17 | 2012-12-19 | 广东工业大学 | Image retrieval system and method for maintaining geometrical shape information of object |
| CN107783709A (en) * | 2017-10-20 | 2018-03-09 | 维沃移动通信有限公司 | The inspection method and mobile terminal of a kind of image |
| CN108229314A (en) * | 2017-11-28 | 2018-06-29 | 深圳市商汤科技有限公司 | Searching method, device and the electronic equipment of target person |
-
2018
- 2018-07-24 CN CN201810819415.XA patent/CN110851636B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110218984A1 (en) * | 2008-12-22 | 2011-09-08 | Adi Gaash | Method and system for searching for information pertaining target objects |
| CN101639858A (en) * | 2009-08-21 | 2010-02-03 | 深圳创维数字技术股份有限公司 | Image search method based on target area matching |
| CN102831216A (en) * | 2012-08-17 | 2012-12-19 | 广东工业大学 | Image retrieval system and method for maintaining geometrical shape information of object |
| CN107783709A (en) * | 2017-10-20 | 2018-03-09 | 维沃移动通信有限公司 | The inspection method and mobile terminal of a kind of image |
| CN108229314A (en) * | 2017-11-28 | 2018-06-29 | 深圳市商汤科技有限公司 | Searching method, device and the electronic equipment of target person |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110851636B (en) | 2023-05-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108229531B (en) | Object feature extraction method and device, storage medium and electronic equipment | |
| CN107808111B (en) | Method and apparatus for pedestrian detection and attitude estimation | |
| JP2016530593A (en) | Assessing the clarity of an image | |
| CN110660102B (en) | Speaker recognition method, device and system based on artificial intelligence | |
| CN113627411A (en) | Super-resolution-based commodity identification and price matching method and system | |
| US9715701B2 (en) | Image-based listing using image of multiple items | |
| CN113222970A (en) | Vehicle loading rate detection method and device, computer equipment and storage medium | |
| CN112348686A (en) | Claim settlement picture acquisition method and device and communication equipment | |
| CN114267029A (en) | Lane line detection method, device, equipment and storage medium | |
| CN111126096A (en) | Two-dimensional code size determination method, two-dimensional code display method, device and equipment | |
| CN114494751A (en) | License information identification method, device, equipment and medium | |
| US20180336243A1 (en) | Image Search Method, Apparatus and Storage Medium | |
| CN111104915B (en) | Method, device, equipment and medium for peer analysis | |
| CN112419432A (en) | Method and device for controlling food in refrigerator, electronic equipment and storage medium | |
| CN110610178A (en) | Image recognition method, device, terminal and computer readable storage medium | |
| CN116931732A (en) | Vehicle exhibition implementation method, system, equipment and medium based on cloud exhibition | |
| CN108289177B (en) | Information interaction method, device and system | |
| CN110851636B (en) | Image searching system, method and device | |
| US20220207585A1 (en) | System and method for providing three-dimensional, visual search | |
| CN111127310B (en) | Image processing method and device, electronic equipment and storage medium | |
| CN112860060B (en) | Image recognition method, device and storage medium | |
| US9798932B2 (en) | Video extraction method and device | |
| CN114782579A (en) | Image rendering method and device and storage medium | |
| CN110348898B (en) | Information pushing method and device based on human body identification | |
| CN112633143A (en) | Image processing system, method, head-mounted device, processing device, and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |