CN104765796A - Image recognizing searching method and device - Google Patents
Image recognizing searching method and device Download PDFInfo
- Publication number
- CN104765796A CN104765796A CN201510134843.5A CN201510134843A CN104765796A CN 104765796 A CN104765796 A CN 104765796A CN 201510134843 A CN201510134843 A CN 201510134843A CN 104765796 A CN104765796 A CN 104765796A
- Authority
- CN
- China
- Prior art keywords
- image
- feature information
- data base
- image feature
- described image
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses an image recognizing searching method and device, and aims at increasing the user search efficiency and quickly searching the information matched with the demand. The method comprises the steps of acquiring an image; storing the image into an image database; selecting the image from the image database; extracting the image feature information; acquiring search keywords; searching according to the search keywords and the image feature information. With the adoption of the method and the device, the search efficiency can be increased, the search time is reduced, and the information in match with the demand can be quickly searched.
Description
Technical field
The present invention relates to Internet technical field, particularly a kind of image identification search method and device.
Background technology
Through the development of Internet technology in recent years, the business of internet constantly increases, and people need to search for various information on the internet, and more and more higher to the requirement of the speed of searching for and efficiency.
But in existing way of search, the Word message mainly through input is searched for, and due to the continuous increase of Various types of data type in internet, quantity of information is too huge, makes the inefficiency of searching for, searches for consuming time long.And under the prerequisite of not knowing the interested information of user, user is also difficult to search the relevant information of to search for target information with self and mating.
Summary of the invention
The invention provides a kind of image identification search method and device, in order to improve efficiency when user searches for, and realize the fast search of the information of mating with self-demand.
According to the first aspect of the embodiment of the present invention, a kind of image identification search method is provided, comprises:
Obtain image and described image is stored in image data base;
Selected digital image in described image data base also extracts image feature information;
Obtain search keyword, and search for according to described search keyword and described image feature information.
In one embodiment, described image is also stored in image data base by described acquisition image, comprising:
Face or article are taken, obtains the rear image of shooting;
Detect in described image data base the similar image whether existing and reach preset standard with the matching degree of described image;
When existence reaches the similar image of preset standard with the matching degree of described image, described image is being stored to the homogeneous region in image data base with described similar image.
In one embodiment, described selected digital image in described image data base also extracts image feature information, comprising:
Selected digital image in described image data base;
To comprising, the homogeneous region of the described image data base of selected digital image is detected, and therefrom extracts image feature information;
Image feature information list is stored to after being sorted according to predetermined order rule by described image feature information.
In one embodiment, described selected digital image in described image data base also extracts image feature information, also comprises:
According to default redaction rule, correcting process is carried out to the image feature information be stored in described image feature information list or/and expand process.
In one embodiment, described acquisition search keyword, and search for according to described search keyword and described image feature information, comprising:
Obtain the search keyword of User Defined input;
User Defined is selected or is selected the image feature information in described image feature information list voluntarily according to default selective rule by default;
Described image feature information according to described search keyword and selection is searched for.
According to the second aspect of the embodiment of the present invention, a kind of image identification search device is also provided, comprises:
First acquisition module, for obtaining image and being stored in image data base by described image;
Extraction module, extracts image feature information for selected digital image in described image data base;
Search module, for obtaining search keyword, and searches for according to described search keyword and described image feature information.
In one embodiment, described first acquisition module, comprising:
First obtains submodule, for taking face or article, obtains the rear image of shooting;
Detection sub-module, for detecting in described image data base the similar image whether existing and reach preset standard with the matching degree of described image;
First sub module stored, for when existence reaches the similar image of preset standard with the matching degree of described image, is being stored to the homogeneous region in image data base by described image with described similar image.
In one embodiment, described extraction module, comprising:
First chooser module, for selected digital image in described image data base;
Extract submodule, the homogeneous region for the described image data base of the selected digital image to comprising is detected, and therefrom extracts image feature information;
Second sub module stored, is stored to image feature information list after being sorted according to predetermined order rule by described image feature information.
In one embodiment, described extraction module, also comprises:
Revision submodule, for carrying out correcting process according to default redaction rule to the image feature information be stored in described image feature information list or/and expand process.
In one embodiment, described search module, comprising:
Second obtains submodule, for obtaining the search keyword of User Defined input;
Second chooser module, for selecting at User Defined or selecting the image feature information in described image feature information list by default according to default selective rule voluntarily;
Search submodule, for searching for according to the described image feature information of described search keyword and selection.
The technical scheme that the embodiment of the present invention provides can produce following beneficial effect: by obtaining image and being stored to after in image data base by described image, selected digital image in described image data base also extracts image feature information, and searches for according to the search keyword obtained and described image feature information.Video is searched for again after being combined by the search keyword that the image feature information extracted in image data base and User Defined input, greatly reduce the data volume of image identification search, improve search efficiency, decrease search duration, achieve the fast search of the information of mating with self-demand.
Other features and advantages of the present invention will be set forth in the following description, and, partly become apparent from instructions, or understand by implementing the present invention.Object of the present invention and other advantages realize by structure specifically noted in write instructions, claims and accompanying drawing and obtain.
Below by drawings and Examples, technical scheme of the present invention is described in further detail.
Accompanying drawing explanation
Accompanying drawing is used to provide a further understanding of the present invention, and forms a part for instructions, together with embodiments of the present invention for explaining the present invention, is not construed as limiting the invention.
In the accompanying drawings:
Fig. 1 is the process flow diagram of the image identification search method of the present invention according to an exemplary embodiment;
Fig. 2 is the embodiment process flow diagram of step S10 in the image identification search method of the present invention according to an exemplary embodiment;
Fig. 3 is a kind of embodiment process flow diagram of step S20 in the image identification search method of the present invention according to an exemplary embodiment;
Fig. 4 is the another kind of embodiment process flow diagram of step S20 in the image identification search method of the present invention according to an exemplary embodiment;
Fig. 5 is the embodiment process flow diagram of step S30 in the image identification search method of the present invention according to an exemplary embodiment;
Fig. 6 is the block diagram of the image identification search device of the present invention according to an exemplary embodiment;
Fig. 7 is the block diagram of the first acquisition module 61 in the image identification search device of the present invention according to an exemplary embodiment;
Fig. 8 is the block diagram of a kind of extraction module 62 in the image identification search device of the present invention according to an exemplary embodiment;
Fig. 9 is the block diagram of another kind of extraction module 62 in the image identification search device of the present invention according to an exemplary embodiment;
Figure 10 is the block diagram of search module 63 in the image identification search device of the present invention according to an exemplary embodiment.
Embodiment
Below in conjunction with accompanying drawing, the preferred embodiments of the present invention are described, should be appreciated that preferred embodiment described herein is only for instruction and explanation of the present invention, is not intended to limit the present invention.
Disclosure embodiment provides a kind of image identification search method, for improving search efficiency, reducing search duration, realizing the fast search of the information of mating with self-demand.As shown in Figure 1, the method comprising the steps of S10-S30:
In step slo, obtain image and described image is stored in image data base.Wherein, described image data base be for user obtain image after database that its subregion is stored.
In one embodiment, as shown in Figure 2, step S10 can comprise:
Step S101, face or article to be taken, obtain image after shooting;
Wherein, described image can be taken by capture apparatus, and described capture apparatus can be camera; And camera, mobile phone, panel computer etc. are with the various equipment of camera; And the object of its shooting can carry out the applicable object of the article searched for required for user, the clothing that such as user needs purchase itself to be suitable for, then directly can take the head portrait of oneself; Or the object of shooting also can be all kinds of article to be searched itself or similar article; Meanwhile, in the disclosure, described image also can be the various pictures that User Defined is stored into image data base, and is not limited to be the image that user takes immediately.
Step S102, detect in described image data base the similar image whether existing and reach preset standard with the matching degree of described image; Also namely, when image is stored into image data base by user, first can detect this image and image data base, judge whether to there is the image similar with image to be stored; And this examination criteria is user-defined matching degree, such as, whether image is face, whether the sex of image be the male sex, whether the age of image be the criterions such as 20-30 one full year of life; And above-mentioned self-defining criterion is set a corresponding matching degree, matching degree after judging is added whether reach default matching degree standard, if reach default matching degree standard, then illustrate that image to be stored exists similar image in described image data base.
Step S103, when exist reach the similar image of preset standard with the matching degree of described image time, described image is being stored to the homogeneous region in image data base with described similar image.
When detecting that existence reaches the similar image of preset standard with the matching degree of described image in step s 102, then described image is being stored to the homogeneous region in image data base with described similar image; Stored people homogeneous region, transferred all similar images so that more convenient in follow-up extraction image feature information.
In step S20, selected digital image in described image data base also extracts image feature information.
Wherein, described image feature information can comprise each category feature of selected digital image, if such as image face, then described image feature information can be the age, sex etc. of people; If article, then described image feature information can be the title, purposes etc. of article.
In one embodiment, as shown in Figure 3, described step S20 can comprise:
Step S201, in described image data base selected digital image.Also be, first the image be stored in above-mentioned steps S10 in image data base is chosen in this step, so that position article to be searched or information, such as, search for middle aged men's clothing, the image of image data base middle-aged male can be chosen or/and the image of men's clothing that is suitable for of middle-aged male.
Step S202, to comprising, the homogeneous region of the described image data base of selected digital image is detected, and therefrom extracts image feature information.Homogeneous region in the above-mentioned image data base being selected image place is detected, all similar images are identified and extract image feature information; Such as, if all kinds of image is the men's clothing of middle-aged male, image feature information can be extracted as: middle age+men's clothing; Also can by its image feature information such as age level and sex thereof of face Direct Recognition of middle-aged male.
Step S203, described image feature information is sorted according to predetermined order rule after be stored to image feature information list.After multiple image feature informations of said extracted are carried out the sequence of priority according to predetermined order rule, can so that select it, described predetermined order rule can need sets itself according to user, such as, can be that the many persons of occurrence number are preferential, sex is preferential, the age is preferential, Item Title priority scheduling principle.
In one embodiment, as shown in Figure 4, also can comprise in described step S20:
Step S204, according to default redaction rule, correcting process is carried out to the image feature information be stored in described image feature information list or/and expand process.Also be, when the image feature information being stored to described image feature information list in above-mentioned steps S203 needs to carry out adjusting or occur some deviations, can revise described image feature information, this revision process can be that user manually revises, and also can revise voluntarily according to preset rules, such as, if want to search for the age be 30-40 year the clothes of the male sex, and extracted age and sex and be stored in image feature information list as image feature information, suppose extract image feature information in Age estimation be 40-50 year, then its manual correction can be 30-40 year by user in image feature information list, also can preset 30-40 year is conventional image feature information to be searched, if occur, the image feature information extracted does not belong to this scope, then point out user's amendment or automatically modify, under this rule, image feature information list can revise these data voluntarily or prompting user manually modifies.Now, if search for this image feature information, then not setting the range of age 30-40 year in male sex's clothes can be filtered.In like manner, if there is the information of wrongly written or mispronounced characters or mistake in image feature information, also can revise it or delete, to avoid searching under error message.
In step s 30, obtain search keyword, and search for according to described search keyword and described image feature information.
In one embodiment, as shown in Figure 5, described step S30 can comprise:
The search keyword of step S301, the input of acquisition User Defined; Also namely, described search keyword is inputted by user's self-defining, and such as, user can input " trousers ", with show its want search for be fitted pants instead of jacket.After user inputs this search keyword and confirms in search column, described search keyword is automatically obtained as the authentication information.
Step S302, User Defined are selected or are selected the image feature information in described image feature information list voluntarily according to default selective rule by default.
By default, the image feature information in described image feature information list can be selected automatically according to the rule preset, such as, set using priority sequence at the image feature information of front two as alternative.Meanwhile, this selection course also can be selected by user voluntarily, and such as, can select to show described image feature information list, user manually can select in this image feature information list, more to meet the demand of user.
Step S303, to search for according to the described image feature information of described search keyword and selection.
The described search keyword inputted voluntarily by above-mentioned image feature information and user carries out image identification search in the lump, greatly strengthen the specific aim of search undoubtedly, improves search efficiency, shorten search duration.
The said method that the embodiment of the present invention provides, by obtaining image and described image being stored to after in image data base, selected digital image in described image data base also extracts image feature information, and searches for according to the search keyword obtained and described image feature information.Video is searched for again after being combined by the search keyword that the image feature information extracted in image data base and User Defined input, greatly reduce the data volume of image identification search, improve search efficiency, decrease search duration, achieve the fast search of the information of mating with self-demand.
The image identification search method that the corresponding embodiment of the present invention provides, the present invention also provides image identification search device, and as shown in Figure 6, this device can comprise:
First acquisition module 61, for obtaining image and being stored in image data base by described image;
Extraction module 62, extracts image feature information for selected digital image in described image data base;
Search module 63, for obtaining search keyword, and searches for according to described search keyword and described image feature information.
In one embodiment, as shown in Figure 7, described first acquisition module 61, comprising:
First obtains submodule 611, for taking face or article, obtains the rear image of shooting;
Detection sub-module 612, for detecting in described image data base the similar image whether existing and reach preset standard with the matching degree of described image;
First sub module stored 613, for when existence reaches the similar image of preset standard with the matching degree of described image, is being stored to the homogeneous region in image data base by described image with described similar image.In one embodiment, as shown in Figure 8, described extraction module 62, comprising:
First chooser module 621, for selected digital image in described image data base;
Extract submodule 622, the homogeneous region for the described image data base of the selected digital image to comprising is detected, and therefrom extracts image feature information;
Second sub module stored 623, is stored to image feature information list after being sorted according to predetermined order rule by described image feature information.
In one embodiment, as shown in Figure 9, described extraction module 62, also comprises:
Revision submodule 624, for carrying out correcting process according to default redaction rule to the image feature information be stored in described image feature information list or/and expand process.
In one embodiment, as shown in Figure 10, described search module 63, comprising:
Second obtains submodule 631, for obtaining the search keyword of User Defined input;
Second chooser module 632, for selecting at User Defined or selecting the image feature information in described image feature information list by default according to default selective rule voluntarily;
Search submodule 633, for searching for according to the described image feature information of described search keyword and selection.
Those skilled in the art should understand, embodiments of the invention can be provided as method, system or computer program.Therefore, the present invention can adopt the form of complete hardware embodiment, completely software implementation or the embodiment in conjunction with software and hardware aspect.And the present invention can adopt in one or more form wherein including the upper computer program implemented of computer-usable storage medium (including but not limited to magnetic disk memory and optical memory etc.) of computer usable program code.
The present invention describes with reference to according to the process flow diagram of the method for the embodiment of the present invention, equipment (system) and computer program and/or block scheme.Should understand can by the combination of the flow process in each flow process in computer program instructions realization flow figure and/or block scheme and/or square frame and process flow diagram and/or block scheme and/or square frame.These computer program instructions can being provided to the processor of multi-purpose computer, special purpose computer, Embedded Processor or other programmable data processing device to produce a machine, making the instruction performed by the processor of computing machine or other programmable data processing device produce device for realizing the function of specifying in process flow diagram flow process or multiple flow process and/or block scheme square frame or multiple square frame.
These computer program instructions also can be stored in can in the computer-readable memory that works in a specific way of vectoring computer or other programmable data processing device, the instruction making to be stored in this computer-readable memory produces the manufacture comprising command device, and this command device realizes the function of specifying in process flow diagram flow process or multiple flow process and/or block scheme square frame or multiple square frame.
These computer program instructions also can be loaded in computing machine or other programmable data processing device, make on computing machine or other programmable devices, to perform sequence of operations step to produce computer implemented process, thus the instruction performed on computing machine or other programmable devices is provided for the step realizing the function of specifying in process flow diagram flow process or multiple flow process and/or block scheme square frame or multiple square frame.
Obviously, those skilled in the art can carry out various change and modification to the present invention and not depart from the spirit and scope of the present invention.Like this, if these amendments of the present invention and modification belong within the scope of the claims in the present invention and equivalent technologies thereof, then the present invention is also intended to comprise these change and modification.
Claims (10)
1. an image identification search method, is characterized in that, comprising:
Obtain image and described image is stored in image data base;
Selected digital image in described image data base also extracts image feature information;
Obtain search keyword, and search for according to described search keyword and described image feature information.
2. the method for claim 1, is characterized in that, described image is also stored in image data base by described acquisition image, comprising:
Face or article are taken, obtains the rear image of shooting;
Detect in described image data base the similar image whether existing and reach preset standard with the matching degree of described image;
When existence reaches the similar image of preset standard with the matching degree of described image, described image is being stored to the homogeneous region in image data base with described similar image.
3. the method for claim 1, is characterized in that, described selected digital image in described image data base also extracts image feature information, comprising:
Selected digital image in described image data base;
To comprising, the homogeneous region of the described image data base of selected digital image is detected, and therefrom extracts image feature information;
Image feature information list is stored to after being sorted according to predetermined order rule by described image feature information.
4. method as claimed in claim 3, it is characterized in that, described selected digital image in described image data base also extracts image feature information, also comprises:
According to default redaction rule, correcting process is carried out to the image feature information be stored in described image feature information list or/and expand process.
5. the method as described in claim 3 or 4, is characterized in that, described acquisition search keyword, and searches for according to described search keyword and described image feature information, comprising:
Obtain the search keyword of User Defined input;
User Defined is selected or is selected the image feature information in described image feature information list voluntarily according to default selective rule by default;
Described image feature information according to described search keyword and selection is searched for.
6. an image identification search device, is characterized in that, comprising:
First acquisition module, for obtaining image and being stored in image data base by described image;
Extraction module, extracts image feature information for selected digital image in described image data base;
Search module, for obtaining search keyword, and searches for according to described search keyword and described image feature information.
7. device as claimed in claim 6, it is characterized in that, described first acquisition module, comprising:
First obtains submodule, for taking face or article, obtains the rear image of shooting;
Detection sub-module, for detecting in described image data base the similar image whether existing and reach preset standard with the matching degree of described image;
First sub module stored, for when existence reaches the similar image of preset standard with the matching degree of described image, is being stored to the homogeneous region in image data base by described image with described similar image.
8. device as claimed in claim 6, it is characterized in that, described extraction module, comprising:
First chooser module, for selected digital image in described image data base;
Extract submodule, the homogeneous region for the described image data base of the selected digital image to comprising is detected, and therefrom extracts image feature information;
Second sub module stored, is stored to image feature information list after being sorted according to predetermined order rule by described image feature information.
9. device as claimed in claim 8, it is characterized in that, described extraction module, also comprises:
Revision submodule, for carrying out correcting process according to default redaction rule to the image feature information be stored in described image feature information list or/and expand process.
10. device as claimed in claim 8 or 9, it is characterized in that, described search module, comprising:
Second obtains submodule, for obtaining the search keyword of User Defined input;
Second chooser module, for selecting at User Defined or selecting the image feature information in described image feature information list by default according to default selective rule voluntarily;
Search submodule, for searching for according to the described image feature information of described search keyword and selection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510134843.5A CN104765796A (en) | 2015-03-25 | 2015-03-25 | Image recognizing searching method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510134843.5A CN104765796A (en) | 2015-03-25 | 2015-03-25 | Image recognizing searching method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104765796A true CN104765796A (en) | 2015-07-08 |
Family
ID=53647627
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510134843.5A Pending CN104765796A (en) | 2015-03-25 | 2015-03-25 | Image recognizing searching method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104765796A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106951477A (en) * | 2017-03-08 | 2017-07-14 | 深圳市赛亿科技开发有限公司 | A kind of picture recognition and extracting method |
| CN107229707A (en) * | 2017-05-26 | 2017-10-03 | 北京小米移动软件有限公司 | Search for the method and device of image |
| CN108124478A (en) * | 2017-12-05 | 2018-06-05 | 深圳前海达闼云端智能科技有限公司 | Picture searching method and apparatus |
| CN110377626A (en) * | 2019-06-19 | 2019-10-25 | 深圳壹账通智能科技有限公司 | Information displaying method, device, equipment and storage medium |
| CN110879849A (en) * | 2019-11-09 | 2020-03-13 | 广东智媒云图科技股份有限公司 | Similarity comparison method and device based on image-to-character conversion |
| CN111524518A (en) * | 2020-04-01 | 2020-08-11 | Oppo广东移动通信有限公司 | Augmented reality processing method and device, storage medium and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1952935A (en) * | 2006-09-22 | 2007-04-25 | 南京搜拍信息技术有限公司 | Search system and technique comprehensively using information of graphy and character |
| CN102262642A (en) * | 2011-01-28 | 2011-11-30 | 北京理工大学 | Web image search engine and realizing method thereof |
| CN102902821A (en) * | 2012-11-01 | 2013-01-30 | 北京邮电大学 | Methods for labeling and searching advanced semantics of imagse based on network hot topics and device |
| CN103838724A (en) * | 2012-11-20 | 2014-06-04 | 百度在线网络技术（北京）有限公司 | Image search method and device |
-
2015
- 2015-03-25 CN CN201510134843.5A patent/CN104765796A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1952935A (en) * | 2006-09-22 | 2007-04-25 | 南京搜拍信息技术有限公司 | Search system and technique comprehensively using information of graphy and character |
| CN102262642A (en) * | 2011-01-28 | 2011-11-30 | 北京理工大学 | Web image search engine and realizing method thereof |
| CN102902821A (en) * | 2012-11-01 | 2013-01-30 | 北京邮电大学 | Methods for labeling and searching advanced semantics of imagse based on network hot topics and device |
| CN103838724A (en) * | 2012-11-20 | 2014-06-04 | 百度在线网络技术（北京）有限公司 | Image search method and device |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106951477A (en) * | 2017-03-08 | 2017-07-14 | 深圳市赛亿科技开发有限公司 | A kind of picture recognition and extracting method |
| CN107229707A (en) * | 2017-05-26 | 2017-10-03 | 北京小米移动软件有限公司 | Search for the method and device of image |
| CN107229707B (en) * | 2017-05-26 | 2021-12-28 | 北京小米移动软件有限公司 | Method and device for searching image |
| CN108124478A (en) * | 2017-12-05 | 2018-06-05 | 深圳前海达闼云端智能科技有限公司 | Picture searching method and apparatus |
| CN110377626A (en) * | 2019-06-19 | 2019-10-25 | 深圳壹账通智能科技有限公司 | Information displaying method, device, equipment and storage medium |
| WO2020253110A1 (en) * | 2019-06-19 | 2020-12-24 | 深圳壹账通智能科技有限公司 | Information display method, apparatus and device, and storage medium |
| CN110879849A (en) * | 2019-11-09 | 2020-03-13 | 广东智媒云图科技股份有限公司 | Similarity comparison method and device based on image-to-character conversion |
| CN111524518A (en) * | 2020-04-01 | 2020-08-11 | Oppo广东移动通信有限公司 | Augmented reality processing method and device, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111368893B (en) | Image recognition method, device, electronic equipment and storage medium | |
| US11120078B2 (en) | Method and device for video processing, electronic device, and storage medium | |
| CN104765796A (en) | Image recognizing searching method and device | |
| US9367756B2 (en) | Selection of representative images | |
| US10134165B2 (en) | Image distractor detection and processing | |
| CN109284729B (en) | Method, device and medium for acquiring face recognition model training data based on video | |
| WO2017045443A1 (en) | Image retrieval method and system | |
| CN107885430B (en) | Audio playing method and device, storage medium and electronic equipment | |
| CN106462766A (en) | Image capturing parameter adjustment in preview mode | |
| US20170109339A1 (en) | Application program activation method, user terminal, and server | |
| CN110019675B (en) | Keyword extraction method and device | |
| CN107918496B (en) | Input error correction method and device for input error correction | |
| CN111046197A (en) | Searching method and device | |
| CN105468716A (en) | Picture search device and method, and terminal | |
| CN108009251A (en) | A kind of image file searching method and device | |
| CN109408652B (en) | Picture searching method, device and equipment | |
| CN109521888A (en) | A kind of input method, device and medium | |
| CN113869063A (en) | Data recommendation method and device, electronic equipment and storage medium | |
| CN112148192A (en) | Image display method and device and electronic equipment | |
| US9648112B2 (en) | Electronic device and method for setting network model | |
| KR20170077983A (en) | User equipment, control method thereof and computer readable medium having computer program recorded thereon | |
| KR20150101846A (en) | Image classification service system based on a sketch user equipment, service equipment, service method based on sketch and computer readable medium having computer program recorded therefor | |
| CN106649296B (en) | Method and device for providing photographing prompt information and searching business object | |
| CN103164504A (en) | Smartphone refined picture searching system and method | |
| US20160162752A1 (en) | Retrieval apparatus, retrieval method, and computer program product |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150708 |
|
| RJ01 | Rejection of invention patent application after publication |