CN107016368A - The information acquisition method and server of a kind of object - Google Patents
The information acquisition method and server of a kind of object Download PDFInfo
- Publication number
- CN107016368A CN107016368A CN201710224864.5A CN201710224864A CN107016368A CN 107016368 A CN107016368 A CN 107016368A CN 201710224864 A CN201710224864 A CN 201710224864A CN 107016368 A CN107016368 A CN 107016368A
- Authority
- CN
- China
- Prior art keywords
- image
- target
- object image
- target object
- candidate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Library & Information Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the present invention provides a kind of information acquisition method and server of object, and this method includes:The Target Photo that client is uploaded is obtained, the Target Photo carries target object image;Recognize the target object image in the Target Photo;Extract the corresponding characteristics of image of target object image;The characteristics of image of the preset each candidate's object image of described image feature and database is matched, the database presets the image of each candidate, characteristics of image, and corresponding keyword;It is determined that the characteristics of image with the target object image, the characteristics of image of candidate's object image of matching, transfer corresponding keyword from the database;Scanned for according to the keyword, draw search result, and the search result is fed back into the client.The embodiment of the present invention can reduce the limitation of the information acquiring pattern of object, to help the information of the unacquainted object of user's acquisition to provide possibility.
Description
Technical field
The present invention relates to technical field of information processing, and in particular to the information acquisition method and server of a kind of object.
Background technology
Current user obtains an object (the object such as user such as commodity, plant, building wishes to obtain the object of information)
The common approach of information be that the keyword of object is searched for by search engine, in the search result fed back from search engine
Understand the information of object;Such as user wants to know about the prices of a commodity, parameter during information, user can be in search website
Or e-commerce website searches for the keyword of the commodity, so that user can recognize the price of commodity, ginseng based on search result
The information such as number.
This keyword by searching for object, recognizes to obtain the mode of information of object, it is necessary to set up in user
Know object, in the case of the keyword (title of such as object) for understanding object, but user does not recognize all mesh
Thing is marked, this results in the existing keyword by searching for object, come the mode of the information that obtains object, existed certain
Limitation;Therefore, the limitation of the information acquiring pattern of object how is reduced, becoming those skilled in the art needs solution
Certainly the problem of.
The content of the invention
In view of this, the embodiment of the present invention provides a kind of information acquisition method and server of object, to reduce target
The limitation of the information acquiring pattern of thing, to help the information of the unacquainted object of user's acquisition to provide possibility.
To achieve the above object, the embodiment of the present invention provides following technical scheme:
A kind of information acquisition method of object, including:
The Target Photo that client is uploaded is obtained, the Target Photo carries target object image;
Recognize the target object image in the Target Photo;
Extract the corresponding characteristics of image of target object image;
The characteristics of image of the preset each candidate's object image of described image feature and database is matched, the data
Preset the image of each candidate, characteristics of image, and corresponding keyword in storehouse;
It is determined that the characteristics of image with the target object image, the characteristics of image of candidate's object image of matching, from the data
Corresponding keyword is transferred in storehouse;
Scanned for according to the keyword, draw search result, and the search result is fed back into the client
End.
Optionally, the target object image in the identification Target Photo includes:
The Target Photo is pre-processed;
From pretreated Target Photo, the edge boundary of object and edge background is detected, according to edge boundary
Target object image is identified from the Target Photo.
Optionally, the edge boundary that object and edge background are detected from pretreated Target Photo,
Identify that target object image includes from the Target Photo according to edge boundary:
Dividing processing is carried out to pretreated picture, each picture block is obtained;
The edge boundary of object and edge background is detected from each picture block after dividing processing, according to segmentation portion
The edge boundary in each picture block after reason, extracts the object image block in each picture after dividing processing, by each target
Object image agllutination is combined into target object image.
Optionally, it is described that Target Photo progress pretreatment is included:
It is predetermined pictures color mode by the picture color patten transformation of the Target Photo, and to the predetermined pictures
The Target Photo of color mode carries out picture noise reduction process.
Optionally, the extraction corresponding characteristics of image of target object image includes:
Target object image is scanned according to the image scanning order of setting, from the pixel scanned in proportion
The pixel of setting quantity is extracted, the corresponding characteristics of image of target object image is used as.
Optionally, the image scanning order according to setting target object image is scanned including:
Branch is carried out to target object image, the pixel of target object image is progressively scanned;
The pixel of the extraction setting quantity from the pixel scanned in proportion, it is corresponding as target object image
Characteristics of image includes:
The pixel of the quantity of extraction first in the pixel scanned from each row in proportion, the pixel that each row is extracted is used as mesh
The corresponding characteristics of image of object image is marked, wherein, the pixel summation for the first quantity that each row is extracted is, the picture of the setting quantity
Element.
Optionally, the determination and the characteristics of image of the target object image, the characteristics of image of candidate's object image of matching
Including:
Calculate the characteristics of image of target object image, the degree of approximation with the characteristics of image of each candidate's object image;
According to the characteristics of image of target object image, the degree of approximation with the characteristics of image of each candidate's object image is determined and institute
State the characteristics of image of target object image, the characteristics of image of candidate's object image of matching.
The embodiment of the present invention also provides a kind of server, including:
Picture acquisition module, the Target Photo for obtaining client upload, the Target Photo carries object figure
Picture;
Picture recognition module, for recognizing the target object image in the Target Photo;
Image characteristics extraction module, for extracting the corresponding characteristics of image of target object image;
Characteristic matching module, for by the characteristics of image of described image feature and the preset each candidate's object image of database
Matched, the database presets the image of each candidate, characteristics of image, and corresponding keyword;
Matching result determining module, for determining the characteristics of image with the target object image, candidate's object image of matching
Characteristics of image, corresponding keyword is transferred from the database;
Search for and feedback module, for being scanned for according to the keyword, draw search result, and by the search
As a result the client is fed back to.
Optionally, described image identification module, for recognizing the target object image in the Target Photo, is specifically included:
The Target Photo is pre-processed;
From pretreated Target Photo, the edge boundary of object and edge background is detected, according to edge boundary
Target object image is identified from the Target Photo.
Optionally, described image characteristic extracting module, for extracting the corresponding characteristics of image of target object image, tool
Body includes:
Target object image is scanned according to the image scanning order of setting, from the pixel scanned in proportion
The pixel of setting quantity is extracted, the corresponding characteristics of image of target object image is used as.
Based on above-mentioned technical proposal, in embodiments of the present invention, server can obtain the Target Photo of client upload,
The Target Photo carries target object image;The target object image in the Target Photo is can recognize that so as to server, is extracted
The corresponding characteristics of image of target object image;And then by described image feature and the preset each candidate's object image of database
Characteristics of image is matched, it is determined that the characteristics of image with the target object image, the characteristics of image of candidate's object image of matching,
And corresponding keyword is transferred from the database;Scanned for the keyword, and search result is fed back into client
End, realizes the acquisition of information of object.In the information acquisition method of object provided in an embodiment of the present invention, user can be not
In the case of the keyword that object need to be inputted, the information of object is got, the information acquiring pattern of object is reduced
Limitation, improves the use scope of the information acquiring pattern of object, to help user to obtain the letter of unacquainted object
Breath is provided may.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will to embodiment or
The accompanying drawing used required in description of the prior art is briefly described, it should be apparent that, drawings in the following description are only
Embodiments of the invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with
Other accompanying drawings are obtained according to the accompanying drawing of offer.
Fig. 1 is the structured flowchart of the Information Acquisition System of object provided in an embodiment of the present invention;
Fig. 2 is the signaling process figure of the information acquisition method of object provided in an embodiment of the present invention;
Fig. 3 is the schematic diagram for obtaining Target Photo;
Fig. 4 is another schematic diagram for obtaining Target Photo;
Fig. 5 is the method flow diagram provided in an embodiment of the present invention for recognizing the target object image in Target Photo;
Fig. 6 is the flow chart of the information acquisition method of object provided in an embodiment of the present invention;
Fig. 7 is the structured flowchart of server provided in an embodiment of the present invention;
Fig. 8 is the hardware block diagram of server provided in an embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art obtained under the premise of creative work is not made it is all its
His embodiment, belongs to the scope of protection of the invention.
Fig. 1 is the structured flowchart of the Information Acquisition System of object provided in an embodiment of the present invention, reference picture 1, the target
The Information Acquisition System of thing can include:Client 1 and server 2;
Wherein, client 1 can be arranged on the user equipmenies such as smart mobile phone, tablet personal computer, notebook computer;It is optional
, client 1 can have web page browsing function, and such as client 1 is browser;Optionally, client 1 is also likely to be this hair
Bright developed APP (application program) client;
Server 2 is arranged at network side, and the acquisition of information for realizing object can be interacted with client 1;Server 2 can be with
It is to be realized by single server, it is also possible to which the server farm being made up of multiple servers is realized;Server 2 and client 1
It can be communicated by network (internet etc.).
Based on system shown in Figure 1, the embodiment of the present invention is to realize the acquisition of information of object, and client 1 will can be carried
The picture of target object image uploads onto the server;Server can identify target object image from the picture of upload, and determine institute
The keyword of the target object image of identification, and then can be by the information of identified key word search targets thing, by search result
Feed back to client so that client gets the information of object.
One kind of the information acquisition method of the object proposed based on this thinking, the embodiment of the present invention is optional to improve letter
Make flow can be with as shown in Fig. 2 with reference to shown in Fig. 1 and Fig. 2, the distance can include:
Step S100, client obtain Target Photo, and the Target Photo carries target object image.
Optionally, client can obtain Target Photo by way of taking pictures or transferring local picture;Such as client
End can take pictures to object, get Target Photo, and for example client can be chosen from local picture and carry object
The picture of image, so as to get Target Photo.
Optionally, target object image, which may be considered displaying, the image of object.
Step S101, client upload onto the server the Target Photo.
Optionally, client can be by the navigation mechanism built in browser or client (as built in APP clients
Navigation mechanism) the display upload page, the upload page is associated with the upload interface IP address of server, so that client will can be obtained
The Target Photo taken is associated with uploading interface IP address, and group bag forms upload request and is sent to server, realizes the mesh
Piece mark on a map to the upload of server.
Optionally, client can upload interface IP address by uploading the association of the transmitting assembly in the page, so that server can
Target Photo is obtained by transmitting assembly triggering, camera photographing objective thing is such as called by transmitting assembly, target is got
Picture, or, local picture is transferred by transmitting assembly, the Target Photo for carrying target object image is selected;
As shown in figure 3, showing transmitting assembly in the upload page that client is shown, user is operated after the transmitting assembly,
Client can be activated and call camera, and object (printer shown in Fig. 3 can preferred form of this for one kind of object) is clapped
According to getting Target Photo;
Again as shown in figure 4, showing transmitting assembly in the upload page that client is shown, user operates the transmitting assembly
Afterwards, client can calling and obtaining user equipment data storage path so that user can pass through data storage path choose target figure
Piece.
Obviously, camera photographing objective thing is called by transmitting assembly shown in Fig. 3, obtains Target Photo, and, Fig. 4
The shown data storage path that client place user equipment is transferred by transmitting assembly, is chosen by data storage path
The mode of Target Photo, can select a use (such as client can possess the corresponding Target Photo acquisition modes of Fig. 3 and Fig. 4, but
User can select one and use one of which).
Step S102, server recognize the target object image in the Target Photo.
Optionally, the target object image in server identification Target Photo, it is believed that be from target by target object image
The process extracted in picture, relates generally in Target Photo the detection of target object image and edge background image and separates.
Optionally, server can be pre-processed first after Target Photo is received to Target Photo, then from advance
In Target Photo after reason, the edge boundary of object and edge background is detected, so as to be based on the edge boundary from target figure
Target object image is identified in piece.
Optionally, the process of pretreatment can be divided into:Picture color patten transformation, picture noise reduction etc.;Wherein, typically recognize
For, the graphic form handled by server can be predetermined pictures color mode (such as HSV, wherein, H is tone, and S is saturation
Degree, V is lightness), therefore server is after Target Photo is received, and can be by the picture color patten transformation of Target Photo
Predetermined pictures color mode (it is HSV color modes such as by rgb color patten transformation, wherein, R is red in RGB, and G is green, and B is
It is blue).
Step S103, server extract the corresponding characteristics of image of target object image.
Characteristics of image may be considered the data message with certain rule included in image information, and certain type objects exists
Certain rule can be shown in image information, therefore similar object can be found out by characteristics of image.
Optionally, the embodiment of the present invention can extract mesh by way of extracting the image characteristic point in target object image
The corresponding characteristics of image of object image is marked, image characteristic point refers to have distinct characteristic in image and can effectively reflect image sheet
Matter feature can be identified for that the point of object in image, can use SIFT (Scale invariant features transform) algorithm, and SURF (accelerates
Robust feature) algorithm etc. realizes.
Optionally, the embodiment of the present invention can be scanned according to the image scanning order of setting to target object image, from
The pixel of extraction setting quantity in the pixel scanned in proportion, is used as the corresponding characteristics of image of target object image;
Can such as branch be carried out to target object image, so that the pixel of target object image is progressively scanned, the picture scanned from each row
The pixel of the quantity of extraction first in element in proportion, so that the pixel that each row is extracted is used as the corresponding image of target object image
Feature, wherein, the pixel summation for the first quantity that each row is extracted is, the pixel of the setting quantity;
Obviously, a point row can be also carried out to target object image, so as to scan by column the pixel of target object image, are swept from each row
The pixel of the quantity of extraction second in the pixel retouched in proportion, so that the pixel that each row are extracted is corresponding as target object image
Characteristics of image, wherein, the pixel summation for the second quantity that each row are extracted is, the pixel of the setting quantity.
Step S104, server enter the characteristics of image of the preset each candidate's object image of described image feature and database
Row matching, the database presets the image of each candidate, characteristics of image, and corresponding keyword.
Optionally, database can be set in the embodiment of the present invention, for each candidate, the recordable corresponding time of database
Select the image of thing, the characteristics of image of the image of candidate, and the corresponding keyword of candidate;So as to which server is obtaining mesh
After the characteristics of image for marking object image, characteristics of image and the Image Feature Matching of target object image can be matched from database
Candidate's object image, and then in the way of picture processing, search out the approximate subject image of target object image.
Optionally, it is the accuracy for the characteristics of image for ensureing each candidate's object image recorded in database, the present invention is implemented
Example by way of machine learning is trained, can constantly strengthen the standard of the characteristics of image of candidate's object image for each candidate
True property;Such as each candidate, the training data that the embodiment of the present invention can increase candidate (includes the figure of candidate
Picture) matter (degree of accuracy) and amount (quantity), and then by way of machine learning algorithm and manual control are combined, continuous iteration
The accuracy for the characteristics of image that each candidate training of tuning is drawn;Further, the embodiment of the present invention can reduce the instruction of candidate
Practice the granularity of data.
The embodiment of the present invention carries out the preset each candidate's object image of database in the characteristics of image by target object image
Characteristics of image matching when, the matching based on characteristics of image in itself can be carried out, remove picture tag from, so as to match and mesh
Candidate's object image that mark object image matches, and then again by the candidate framing of matching to candidate, get candidate
The keyword of thing.
Step S105, server determine the characteristics of image with the target object image, the image of candidate's object image of matching
Feature, transfers corresponding keyword from the database.
Optionally, when carrying out the matching of characteristics of image, server can calculate the characteristics of image of target object image, and each
The degree of approximation of the characteristics of image of candidate's object image, so that according to the characteristics of image of target object image, the figure with each candidate's object image
As the degree of approximation of feature, the characteristics of image with the target object image, the characteristics of image of candidate's object image of matching are determined;
The characteristics of image of degree of approximation highest candidate's object image can be such as chosen, the image with the target object image is used as
Feature, the characteristics of image of candidate's object image of matching;And for example exportable degree of approximation highest a number of candidate's object image
Characteristics of image, is used as the characteristics of image with the target object image, the characteristics of image of candidate's object image of matching.
, can be from number it is determined that after characteristics of image with the target object image, the characteristics of image of candidate's object image of matching
According to the candidate for determining to match with object in storehouse, corresponding keyword is transferred out.Optionally, the candidate recorded in database
The keyword of thing, can exist in the form of the label of corresponding candidate object image.
Step S106, server are scanned for according to the keyword, draw search result.
Optionally, server can carry out the whole network search, draw search result after the keyword is obtained;Search result
It can include to contents such as introduction, web page interlinkage, approximate picture, the prices of search object;The content-form of search result can
Set, do not fixed according to situations such as the Type of website.
The search result is fed back to the client by step S107, server.
So far, client can include target object image in the case where being not required to input the keyword of object by uploading
Picture to server, by server by way of pictorial information is handled, get the search result of object;User can
It is being not required to input the keyword of object, in the case of even not recognizing object, is getting the information of object, reduce
The limitation of the information acquiring pattern of object, improves the use scope of the information acquiring pattern of object, to help user
The information for obtaining unacquainted object provides possible.
As can be seen that in embodiments of the present invention, server can obtain the Target Photo of client upload, the target
Picture carries target object image;The target object image in the Target Photo is can recognize that so as to server, the target is extracted
The corresponding characteristics of image of object image;And then by the characteristics of image of described image feature and the preset each candidate's object image of database
Matched, it is determined that the characteristics of image with the target object image, the characteristics of image of candidate's object image of matching, and from described
Corresponding keyword is transferred in database;Scanned for the keyword, and search result is fed back into client, realized
The acquisition of information of object.In the information acquisition method of object provided in an embodiment of the present invention, user can be not required to input mesh
In the case of the keyword for marking thing, the information of object is got, the limitation of the information acquiring pattern of object is reduced,
The use scope of the information acquiring pattern of object is improved, to help the information of the unacquainted object of user's acquisition to provide
May.
Optionally, in flow shown in Fig. 2, the process of the target object image in server identification Target Photo can be related to
Pretreatment, rim detection etc.;Fig. 5 shows the method flow diagram of the target object image in server identification Target Photo, reference
Fig. 5, this method can include:
Step S200, Target Photo is pre-processed.
Optionally, the process of pretreatment can be divided into:It is predetermined pictures color mode by picture color patten transformation, enters
Row picture noise reduction etc..
Step S201, to pretreated picture carry out dividing processing, obtain each picture block.
Optionally, can be to numerical value change trend progress piecemeal of the pretreated picture according to pictorial information, it is therefore an objective to subtract
Low interference and amount of calculation.
Step S202, the edge boundary for detecting from each picture block after dividing processing object and edge background, root
According to the edge boundary in each picture block after dividing processing, the object image block in each picture after dividing processing is extracted,
Each object image block is combined into target object image.
Optionally, same object can typically have obvious distinguishing limit in picture with background graphics, according to pixel with
The diversity factor of peripheral information, can be by setting threshold value to carry out edge judgement, so as to detect the side of object and edge background
Edge boundary.
It is preferred that, from the perspective of server, Fig. 6 shows that the information of object provided in an embodiment of the present invention is obtained
The flow chart of method is taken, this method can be applied to server, and reference picture 6, this method can include:
Step S300, the Target Photo for obtaining client upload, the Target Photo carry target object image.
Step S301, the Target Photo is pre-processed.
Step S302, from pretreated Target Photo, detect the edge boundary of object and edge background, root
Target object image is identified from Target Photo according to the edge boundary.
Optionally, step S302 optional realization can be as shown in Fig. 5 steps S201 to step S202.
Step S303, the pixel for target object image progressively scan target object image in lines, are scanned from each row
The pixel of the quantity of extraction first in pixel in proportion, the pixel that each row is extracted is special as the corresponding image of target object image
Levy.
Optionally, step S303 is a kind of optional realization for extracting the corresponding characteristics of image of target object image, except logical
Cross outside step S303 realizations, the embodiment of the present invention can also carry out the corresponding characteristics of image of target object image by other means
Extract.
Step S304, the characteristics of image for calculating target object image, the image of preset each candidate's object image is special with database
The degree of approximation levied, the database presets the image of each candidate, characteristics of image, and corresponding keyword.
Step S305, the characteristics of image according to target object image, the degree of approximation with the characteristics of image of each candidate's object image,
Determine the characteristics of image with the target object image, the characteristics of image of candidate's object image of matching, and from the database
Transfer corresponding keyword.
Step S306, scanned for according to the keyword, draw search result.
Step S307, the search result fed back into the client.
Optionally, in the embodiment of the present invention, the matching that picture recognition interface carries out characteristics of image can be set in server, i.e.,
The realization of Image Feature Matching is carried out by the picture recognition interface of server.
Optionally, an application of the information acquisition method of object provided in an embodiment of the present invention can be as follows:
When user wants to know about the price of printer (keyword that user understands printer is not excluded for, but uses the present invention
Embodiment realizes the possibility that printer price is obtained), client clicks on electronics business by browser access e-commerce website
The transmitting assembly being engaged in website, calls camera to take pictures printer;
Client is by the server belonging to the photo upload to e-commerce website of printer;
Server uses the printer image in scheme provided in an embodiment of the present invention, identification photo, and it is special to extract image
Levy, degree of approximation calculating is carried out with the characteristics of image of each commodity image in database;
Server determines the degree of approximation highest commodity image (printer image) with the characteristics of image of printer image,
And determine the keyword of commodity image corresponding goods (printer);
Server carries out the whole network search by identified keyword in e-commerce website, obtains the search of printer
As a result, and client is fed back to.
It can be seen that, using the information acquisition method of object provided in an embodiment of the present invention, may be such that user can be not required to it is defeated
Enter the keyword of object, in the case of even not recognizing object, get the information of object, reduce object
The limitation of information acquiring pattern.
Server provided in an embodiment of the present invention is introduced below, server described below may be considered for
The information acquisition method of object provided in an embodiment of the present invention is realized, the functional module framework set is needed in the server;Under
Literary description content can with it is cross-referenced above.
Fig. 7 is the structured flowchart of server provided in an embodiment of the present invention, and reference picture 7, the server can include:
Picture acquisition module 10, the Target Photo for obtaining client upload, the Target Photo carries object
Image;
Picture recognition module 20, for recognizing the target object image in the Target Photo;
Image characteristics extraction module 30, for extracting the corresponding characteristics of image of target object image;
Characteristic matching module 40, for the image of described image feature and the preset each candidate's object image of database is special
Levy and matched, the database presets the image of each candidate, characteristics of image, and corresponding keyword;
Matching result determining module 50, for determining the characteristics of image with the target object image, the candidate figure of matching
The characteristics of image of picture, transfers corresponding keyword from the database;
Search for and feedback module 60, for being scanned for according to the keyword, draw search result, and search described
Hitch fruit feeds back to the client.
Optionally, picture recognition module 20, for recognizing the target object image in the Target Photo, are specifically included:
The Target Photo is pre-processed;
From pretreated Target Photo, the edge boundary of object and edge background is detected, according to edge boundary
Target object image is identified from the Target Photo.
Optionally, picture recognition module 20, for from pretreated Target Photo, detecting object and edge
The edge boundary of background, identifies target object image according to edge boundary from the Target Photo, specifically includes:
Dividing processing is carried out to pretreated picture, each picture block is obtained;
The edge boundary of object and edge background is detected from each picture block after dividing processing, according to segmentation portion
The edge boundary in each picture block after reason, extracts the object image block in each picture after dividing processing, by each target
Object image agllutination is combined into target object image.
Optionally, picture recognition module 20, for being pre-processed to the Target Photo, are specifically included:
It is predetermined pictures color mode by the picture color patten transformation of the Target Photo, and to the predetermined pictures
The Target Photo of color mode carries out picture noise reduction process.
Optionally, image characteristics extraction module 30, for extracting the corresponding characteristics of image of target object image, specifically
Including:
Target object image is scanned according to the image scanning order of setting, from the pixel scanned in proportion
The pixel of setting quantity is extracted, the corresponding characteristics of image of target object image is used as.
Optionally, image characteristics extraction module 30, is carried out for the image scanning order according to setting to target object image
Scanning, is specifically included:
Branch is carried out to target object image, the pixel of target object image is progressively scanned;
Accordingly, image characteristics extraction module 30, for the extraction setting quantity from the pixel scanned in proportion
Pixel, as the corresponding characteristics of image of target object image, is specifically included:
The pixel of the quantity of extraction first in the pixel scanned from each row in proportion, the pixel that each row is extracted is used as mesh
The corresponding characteristics of image of object image is marked, wherein, the pixel summation for the first quantity that each row is extracted is, the picture of the setting quantity
Element.
Optionally, matching result determining module 50, for determining the characteristics of image with the target object image, matching
The characteristics of image of candidate's object image, is specifically included:
Calculate the characteristics of image of target object image, the degree of approximation with the characteristics of image of each candidate's object image;
According to the characteristics of image of target object image, the degree of approximation with the characteristics of image of each candidate's object image is determined and institute
State the characteristics of image of target object image, the characteristics of image of candidate's object image of matching.
Optionally, the hardware configuration of server provided in an embodiment of the present invention can with as shown in figure 8, including:It can wrap
Include:At least one processor 100, at least one communication interface 200, at least one memory 300 and at least one communication bus
400;
In embodiments of the present invention, processor 100, communication interface 200, memory 300, the quantity of communication bus 400 are
At least one, and processor 100, communication interface 200, memory 300 complete mutual communication by communication bus 400;It is aobvious
So, shown in Fig. 8 the communication connection signal shown in processor 100, communication interface 200, memory 300 and communication bus 400 is only
It is optional;
Optionally, communication interface 200 can be the interface of communication module, the interface of such as gsm module;
Processor 100 is probably a central processor CPU, or specific integrated circuit ASIC (Application
Specific Integrated Circuit), or be arranged to implement the one or more integrated of the embodiment of the present invention
Circuit.
Memory 300 may include high-speed RAM memory, it is also possible to also including nonvolatile memory (non-
Volatile memory), for example, at least one magnetic disk storage.
Wherein, processor 100 specifically for:
The Target Photo that client is uploaded is obtained, the Target Photo carries target object image;
Recognize the target object image in the Target Photo;
Extract the corresponding characteristics of image of target object image;
The characteristics of image of the preset each candidate's object image of described image feature and database is matched, the data
Preset the image of each candidate, characteristics of image, and corresponding keyword in storehouse;
It is determined that the characteristics of image with the target object image, the characteristics of image of candidate's object image of matching, from the data
Corresponding keyword is transferred in storehouse;
Scanned for according to the keyword, draw search result, and the search result is fed back into the client
End.
The embodiment of each in this specification is described by the way of progressive, and what each embodiment was stressed is and it
Between the difference of his embodiment, each embodiment identical similar portion mutually referring to.For being filled disclosed in embodiment
For putting, because it is corresponded to the method disclosed in Example, so description is fairly simple, related part is referring to method portion
Defend oneself bright.
Professional further appreciates that, with reference to the list of each example of the embodiments described herein description
Member and algorithm steps, can be realized with electronic hardware, computer software or the combination of the two, hard in order to clearly demonstrate
The interchangeability of part and software, generally describes the composition and step of each example according to function in the above description.
These functions are performed with hardware or software mode actually, depending on the application-specific and design constraint of technical scheme.
Professional and technical personnel can realize described function to each specific application using distinct methods, but this reality
Now it is not considered that beyond the scope of this invention.
Hardware, processor can be directly used with reference to the step of the method or algorithm that the embodiments described herein is described
The software module of execution, or the two combination are implemented.Software module can be placed in random access memory (RAM), internal memory, only
Read memory (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or
In any other form of storage medium well known in technical field.
The foregoing description of the disclosed embodiments, enables professional and technical personnel in the field to realize or using the present invention.
A variety of modifications to these embodiments will be apparent for those skilled in the art, defined herein
General Principle can not depart from the present invention core concept or scope in the case of, realize in other embodiments.Cause
This, the present invention is not intended to be limited to the embodiments shown herein, and is to fit to and principles disclosed herein and new
The consistent most wide scope of clever feature.
Claims (10)
1. a kind of information acquisition method of object, it is characterised in that including:
The Target Photo that client is uploaded is obtained, the Target Photo carries target object image;
Recognize the target object image in the Target Photo;
Extract the corresponding characteristics of image of target object image;
The characteristics of image of the preset each candidate's object image of described image feature and database is matched, the database is preset
There are the image of each candidate, characteristics of image, and corresponding keyword;
It is determined that the characteristics of image with the target object image, the characteristics of image of candidate's object image of matching, from the database
Transfer corresponding keyword;
Scanned for according to the keyword, draw search result, and the search result is fed back into the client.
2. the information acquisition method of object according to claim 1, it is characterised in that the identification Target Photo
In target object image include:
The Target Photo is pre-processed;
From pretreated Target Photo, the edge boundary of object and edge background is detected, according to edge boundary from institute
State and target object image is identified in Target Photo.
3. the information acquisition method of object according to claim 2, it is characterised in that described from pretreated target
In picture, the edge boundary of object and edge background is detected, mesh is identified from the Target Photo according to edge boundary
Mark object image includes:
Dividing processing is carried out to pretreated picture, each picture block is obtained;
The edge boundary of object and edge background is detected from each picture block after dividing processing, after dividing processing
Edge boundary in each picture block, extracts the object image block in each picture after dividing processing, by each target object image
Agllutination is combined into target object image.
4. the information acquisition method of object according to claim 2, it is characterised in that described to enter to the Target Photo
Row pretreatment includes:
It is predetermined pictures color mode by the picture color patten transformation of the Target Photo, and to the predetermined pictures color mould
The Target Photo of formula carries out picture noise reduction process.
5. the information acquisition method of object according to claim 1, it is characterised in that the extraction object figure
As corresponding characteristics of image includes:
Target object image is scanned according to the image scanning order of setting, the extraction from the pixel scanned in proportion is set
The pixel of fixed number amount, is used as the corresponding characteristics of image of target object image.
6. the information acquisition method of object according to claim 5, it is characterised in that described to be swept according to the image of setting
Retouch order target object image is scanned including:
Branch is carried out to target object image, the pixel of target object image is progressively scanned;
The pixel of the extraction setting quantity from the pixel scanned in proportion, it is special as the corresponding image of target object image
Levy including:
The pixel of the quantity of extraction first in the pixel scanned from each row in proportion, the pixel that each row is extracted is used as object figure
As corresponding characteristics of image, wherein, the pixel summation for the first quantity that each row is extracted is, the pixel of the setting quantity.
7. the information acquisition method of object according to claim 1, it is characterised in that the determination and the object
The characteristics of image of image, the characteristics of image of candidate's object image of matching includes:
Calculate the characteristics of image of target object image, the degree of approximation with the characteristics of image of each candidate's object image;
According to the characteristics of image of target object image, the degree of approximation with the characteristics of image of each candidate's object image is determined and the mesh
Mark the characteristics of image of object image, the characteristics of image of candidate's object image of matching.
8. a kind of server, it is characterised in that including:
Picture acquisition module, the Target Photo for obtaining client upload, the Target Photo carries target object image;
Picture recognition module, for recognizing the target object image in the Target Photo;
Image characteristics extraction module, for extracting the corresponding characteristics of image of target object image;
A characteristic matching module, for the characteristics of image of described image feature and the preset each candidate's object image of database to be carried out
Match somebody with somebody, the database presets the image of each candidate, characteristics of image, and corresponding keyword;
Matching result determining module, for determining the characteristics of image with the target object image, the figure of candidate's object image of matching
As feature, corresponding keyword is transferred from the database;
Search for and feedback module, for being scanned for according to the keyword, draw search result, and the search result is anti-
Feed the client.
9. server according to claim 8, it is characterised in that described image identification module, for recognizing the target
Target object image in picture, is specifically included:
The Target Photo is pre-processed;
From pretreated Target Photo, the edge boundary of object and edge background is detected, according to edge boundary from institute
State and target object image is identified in Target Photo.
10. server according to claim 8, it is characterised in that described image characteristic extracting module, described for extracting
The corresponding characteristics of image of target object image, is specifically included:
Target object image is scanned according to the image scanning order of setting, the extraction from the pixel scanned in proportion is set
The pixel of fixed number amount, is used as the corresponding characteristics of image of target object image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710224864.5A CN107016368A (en) | 2017-04-07 | 2017-04-07 | The information acquisition method and server of a kind of object |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710224864.5A CN107016368A (en) | 2017-04-07 | 2017-04-07 | The information acquisition method and server of a kind of object |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107016368A true CN107016368A (en) | 2017-08-04 |
Family
ID=59445442
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710224864.5A Pending CN107016368A (en) | 2017-04-07 | 2017-04-07 | The information acquisition method and server of a kind of object |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107016368A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107491512A (en) * | 2017-08-07 | 2017-12-19 | 上海斐讯数据通信技术有限公司 | A kind of method and system that content search is carried out based on picture recognition |
CN109635144A (en) * | 2018-12-12 | 2019-04-16 | 广州蓝深科技有限公司 | A kind of e-commerce picture search purchase system |
CN111506758A (en) * | 2020-04-16 | 2020-08-07 | 腾讯科技(深圳)有限公司 | Method and device for determining article name, computer equipment and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101571875A (en) * | 2009-05-05 | 2009-11-04 | 程治永 | Realization method of image searching system based on image recognition |
CN101840577A (en) * | 2010-06-11 | 2010-09-22 | 西安电子科技大学 | Image automatic segmentation method based on graph cut |
US8504547B1 (en) * | 2008-04-23 | 2013-08-06 | Google Inc. | Customizing image search for user attributes |
WO2014004536A2 (en) * | 2012-06-25 | 2014-01-03 | Apple Inc. | Voice-based image tagging and searching |
CN104346370A (en) * | 2013-07-31 | 2015-02-11 | 阿里巴巴集团控股有限公司 | Method and device for image searching and image text information acquiring |
CN105824928A (en) * | 2016-03-17 | 2016-08-03 | 广东欧珀移动通信有限公司 | Mobile terminal, server, content-based image recognition searching method and system |
-
2017
- 2017-04-07 CN CN201710224864.5A patent/CN107016368A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8504547B1 (en) * | 2008-04-23 | 2013-08-06 | Google Inc. | Customizing image search for user attributes |
CN101571875A (en) * | 2009-05-05 | 2009-11-04 | 程治永 | Realization method of image searching system based on image recognition |
CN101840577A (en) * | 2010-06-11 | 2010-09-22 | 西安电子科技大学 | Image automatic segmentation method based on graph cut |
WO2014004536A2 (en) * | 2012-06-25 | 2014-01-03 | Apple Inc. | Voice-based image tagging and searching |
CN104346370A (en) * | 2013-07-31 | 2015-02-11 | 阿里巴巴集团控股有限公司 | Method and device for image searching and image text information acquiring |
CN105824928A (en) * | 2016-03-17 | 2016-08-03 | 广东欧珀移动通信有限公司 | Mobile terminal, server, content-based image recognition searching method and system |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107491512A (en) * | 2017-08-07 | 2017-12-19 | 上海斐讯数据通信技术有限公司 | A kind of method and system that content search is carried out based on picture recognition |
CN109635144A (en) * | 2018-12-12 | 2019-04-16 | 广州蓝深科技有限公司 | A kind of e-commerce picture search purchase system |
CN111506758A (en) * | 2020-04-16 | 2020-08-07 | 腾讯科技(深圳)有限公司 | Method and device for determining article name, computer equipment and storage medium |
WO2021208633A1 (en) * | 2020-04-16 | 2021-10-21 | 腾讯科技(深圳)有限公司 | Method and device for determining item name, computer apparatus, and storage medium |
CN111506758B (en) * | 2020-04-16 | 2024-05-03 | 腾讯科技(深圳)有限公司 | Method, device, computer equipment and storage medium for determining article name |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109829453B (en) | Method and device for recognizing characters in card and computing equipment | |
US9245043B2 (en) | Embedded media markers and systems and methods for generating and using them | |
JP5972468B2 (en) | Detect labels from images | |
US9002066B2 (en) | Methods, systems and processor-readable media for designing a license plate overlay decal having infrared annotation marks | |
US8537409B2 (en) | Image summarization by a learning approach | |
US8811734B2 (en) | Color determination device, color determination system, color determination method, information recording medium, and program | |
US8891860B2 (en) | Color name determination device, color name determination method, information recording medium, and program | |
WO2017000109A1 (en) | Search method, search apparatus, user equipment, and computer program product | |
CN107688772A (en) | Method, apparatus, computer equipment and the storage medium of policy information typing | |
US9946949B2 (en) | Techniques including URL recognition and applications | |
US9177199B2 (en) | Semantic magazine pages | |
CN107016368A (en) | The information acquisition method and server of a kind of object | |
US20210072880A1 (en) | Method and electronic device for generating at least one data item from screenshot | |
CN111310750B (en) | Information processing method, device, computing equipment and medium | |
CN110807110A (en) | Image searching method and device combining local and global features and electronic equipment | |
US9934250B2 (en) | Server computing device and image search system based on contents recognition using the same | |
CN110781195B (en) | System, method and device for updating point of interest information | |
CN112200844A (en) | Method, device, electronic equipment and medium for generating image | |
CN107529071A (en) | A kind of video data handling procedure and device | |
CN108230220A (en) | Watermark adding method and device | |
CN111465963A (en) | System, server, program, and method for confirming acquisition of object | |
CN113627242A (en) | Text processing method and related device | |
CN108052525B (en) | Method and device for acquiring audio information, storage medium and electronic equipment | |
US20230377356A1 (en) | Method and system for detecting and extracting price region from digital flyers and promotions | |
JP7478628B2 (en) | Image processing device, control method, and control program |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170804 |
|
RJ01 | Rejection of invention patent application after publication |