CN104750791A - Image retrieval method and device - Google Patents
Image retrieval method and device Download PDFInfo
- Publication number
- CN104750791A CN104750791A CN201510109003.3A CN201510109003A CN104750791A CN 104750791 A CN104750791 A CN 104750791A CN 201510109003 A CN201510109003 A CN 201510109003A CN 104750791 A CN104750791 A CN 104750791A
- Authority
- CN
- China
- Prior art keywords
- image
- text message
- retrieved
- sample image
- retrieval
- 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)
Abstract
The embodiment of the invention provides an image retrieval method and device. According to the method, by obtaining an image to be retrieved, text information contained in the image to be retrieved is obtained accordingly; furthermore, the text information is utilized for conducting the retrieval so that a retrieval result matched with the image to be retrieved can be obtained. Therefore, by means of the technical scheme of the method and device, the complexity of image retrieval can be reduced, and the image retrieval efficiency can be raised.
Description
[technical field]
The present invention relates to technical field of information retrieval, particularly relate to a kind of image search method and device.
[background technology]
Along with Internet technology is fast-developing and intelligent terminal universal, image has become the major way of people's record and sharing information, has expedited the emergence of the generation of the application inputted as retrieval using image in a large number thus, has occurred image retrieval technologies.
Current image search method is: need external information, the characteristic such as content characteristic and shape facility of first extracting image to be retrieved, these characteristics are utilized to mate in retrieval model, to obtain the result for retrieval that the image to be retrieved with this matches.
But in current image search method, when utilizing the feature of image to mate in retrieval model, matching primitives amount is comparatively large, and matching primitives complexity is higher, causes image retrieval efficiency comparison low.
[summary of the invention]
In view of this, embodiments provide a kind of image search method and device, the complexity reducing image retrieval can be realized, improve image retrieval efficiency.
The one side of the embodiment of the present invention, provides a kind of image search method, comprising:
Obtain image to be retrieved;
Obtain the text message comprised in described image to be retrieved;
Described text message is utilized to retrieve, to obtain the result for retrieval matched with described image to be retrieved.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, and the text message comprised in the described image to be retrieved of described acquisition, comprising:
Utilize optical character recognition, character recognition process is carried out to described image to be retrieved, to obtain the text message comprised in described image to be retrieved.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, describedly utilizes described text message to retrieve, and to obtain the result for retrieval matched with described image to be retrieved, comprising:
Set up searching database, described searching database comprises the resource identification of text message and the sample image comprised in sample image;
Utilize described text message, retrieve in described searching database, to obtain the sample image matched with described text message;
According to the sample image matched with described text message, obtain the result for retrieval matched with described image to be retrieved.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, describedly sets up searching database, comprising:
Utilize optical character recognition, character recognition process is carried out to sample image, to obtain the text message comprised in described sample image;
Obtain the key message comprised in described sample image;
Obtain the resource identification of described sample image;
According to the key message comprised in the text message comprised in described sample image, described sample image and described resource identification, set up described searching database.
Aspect as above and arbitrary possible implementation, provide a kind of implementation, the sample image that described basis matches with described text message further, obtains the result for retrieval matched with described image to be retrieved, comprising:
Obtain in described image to be detected and comprise key message;
The key message comprised according to comprising key message in described image to be detected, in the sample image that matches with described text message, sorts to the sample image matched with described text message, to obtain described result for retrieval.
The one side of the embodiment of the present invention, provides a kind of image retrieving apparatus, comprising:
Image acquisition unit, for obtaining image to be retrieved;
Text identification unit, for obtaining the text message comprised in described image to be retrieved;
Image retrieval unit, for utilizing described text message to retrieve, to obtain the result for retrieval matched with described image to be retrieved.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, described text identification unit, specifically for:
Utilize optical character recognition, character recognition process is carried out to described image to be retrieved, to obtain the text message comprised in described image to be retrieved.
Aspect as above and arbitrary possible implementation, a kind of implementation is provided further, described device also comprises: Database unit, and for setting up searching database, described searching database comprises the resource identification of text message and the sample image comprised in sample image;
Described image retrieval unit, specifically for: utilize described text message, retrieve in described searching database, to obtain the sample image matched with described text message; And, according to the sample image matched with described text message, obtain the result for retrieval matched with described image to be retrieved.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, described Database unit, specifically for:
Utilize optical character recognition, character recognition process is carried out to sample image, to obtain the text message comprised in described sample image;
Obtain the key message comprised in described sample image;
Obtain the resource identification of described sample image;
According to the key message comprised in the text message comprised in described sample image, described sample image and described resource identification, set up described searching database.
Aspect as above and arbitrary possible implementation, a kind of implementation is provided further, described image retrieval unit is used for the sample image that basis matches with described text message, when obtaining the result for retrieval matched with described image to be retrieved, specifically for:
Obtain in described image to be detected and comprise key message;
The key message comprised according to comprising key message in described image to be detected, in the sample image that matches with described text message, sorts to the sample image matched with described text message, to obtain described result for retrieval.
As can be seen from the above technical solutions, the embodiment of the present invention has following beneficial effect:
In the embodiment of the present invention, the text message obtained from image to be retrieved is utilized to retrieve, to obtain the result for retrieval matched with described image to be retrieved, be converted into text retrieval by image retrieval, and finally still can obtain the result for retrieval matched with image.With existing image search method, utilize the characteristics such as the external information in image to be retrieved, content characteristic and shape facility, the technical scheme realizing image retrieval is compared, text message is utilized to carry out the mode retrieved in the embodiment of the present invention, matching primitives amount is less, computation complexity is lower, therefore, it is possible to reduce the complexity of image retrieval, improves image retrieval efficiency.
[accompanying drawing explanation]
In order to be illustrated more clearly in the technical scheme of the embodiment of the present invention, be briefly described to the accompanying drawing used required in embodiment below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is the schematic flow sheet of the image search method that the embodiment of the present invention provides;
Fig. 2 is the functional block diagram of the image retrieving apparatus that the embodiment of the present invention provides.
[embodiment]
Technical scheme for a better understanding of the present invention, is described in detail the embodiment of the present invention below in conjunction with accompanying drawing.
Should be clear and definite, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making other embodiments all obtained under creative work prerequisite, belong to the scope of protection of the invention.
The term used in embodiments of the present invention is only for the object describing specific embodiment, and not intended to be limiting the present invention." one ", " described " and " being somebody's turn to do " of the singulative used in the embodiment of the present invention and appended claims is also intended to comprise most form, unless context clearly represents other implications.
Should be appreciated that term "and/or" used herein is only a kind of incidence relation describing affiliated partner, can there are three kinds of relations in expression, and such as, A and/or B, can represent: individualism A, exists A and B simultaneously, these three kinds of situations of individualism B.In addition, character "/" herein, general expression forward-backward correlation is to the relation liking a kind of "or".
Although should be appreciated that may adopt in embodiments of the present invention term first, second etc. result for retrieval is described, these result for retrieval should not be limited to these terms.These terms are only used for result for retrieval to be distinguished from each other out.Such as, when not departing from embodiment of the present invention scope, the first result for retrieval also can be called as the second result for retrieval, and similarly, the second result for retrieval also can be called as the first result for retrieval.
Depend on linguistic context, word as used in this " if " can be construed as into " ... time " or " when ... time " or " in response to determining " or " in response to detection ".Similarly, depend on linguistic context, phrase " if determination " or " if detecting (the conditioned disjunction event of statement) " can be construed as " when determining " or " in response to determining " or " when detecting (the conditioned disjunction event of statement) " or " in response to detection (the conditioned disjunction event of statement) ".
Embodiment one
The embodiment of the present invention provides a kind of image search method, please refer to Fig. 1, the schematic flow sheet of its image search method provided for the embodiment of the present invention, and as shown in the figure, the method comprises the following steps:
S101, obtains image to be retrieved.
S102, obtains the text message comprised in described image to be retrieved.
S103, utilizes described text message to retrieve, to obtain the result for retrieval matched with described image to be retrieved.
It should be noted that, terminal involved in the embodiment of the present invention can include but not limited to personal computer (Personal Computer, PC), personal digital assistant (Personal Digital Assistant, PDA), radio hand-held equipment, panel computer (Tablet Computer), mobile phone, MP3 player, MP4 player etc.
It should be noted that, the executive agent of S101 ~ S103 can be image retrieving apparatus, this device can be positioned at the application of local terminal, or can also for being arranged in plug-in unit or SDK (Software Development Kit) (the Software Development Kit of the application of local terminal, the functional unit such as SDK), or can also be positioned at server, the embodiment of the present invention is not particularly limited this.
Be understandable that, described application can be mounted in the application program (nativeApp) in terminal, or can also be a web page program (webApp) of browser in terminal, and the embodiment of the present invention does not limit this.
Embodiment two
Based on the image search method that above-described embodiment one provides, the embodiment of the present invention is in S101, and the method obtaining image to be retrieved is specifically described.This step specifically can comprise:
Preferably, in the embodiment of the present invention, the method obtaining image to be retrieved can include but not limited to: image-input device can be utilized to obtain image to be retrieved, then receives this image to be retrieved from this image-input device.Or the image also can selected in photograph album according to user, obtains image to be retrieved.
Preferably, described image-input device can include but not limited to: the camera etc. in scanner or terminal.
Embodiment three
Based on the image search method that above-described embodiment one provides, the embodiment of the present invention is in S102, and the method obtaining the text message comprised in described image to be retrieved is specifically described.This step specifically can comprise:
Illustrate, in the embodiment of the present invention, the method obtaining the text message comprised in described image to be retrieved can include but not limited to: utilize optical character identification (Optical Character Recognition, OCR) technology, character recognition process is carried out to described image to be retrieved, to obtain the text message comprised in described image to be retrieved.
Illustrate, utilize OCR technology can include but not limited to the method that image to be retrieved carries out character recognition process:
First, binary conversion treatment is carried out to image to be retrieved, be set to 0 or 255 by the gray-scale value of pixel in image to be retrieved, obtain black white image.To the black white image obtained after binary conversion treatment, perform connected domain and extract operation, and the connected domain extracted is analyzed, in order to the fundamental element in image to be retrieved is carried out a point row relax, to the capable segmentation of the fundamental element belonging to different rows.Wherein, described fundamental element can include but not limited to: character and formula; Wherein, character can include but not limited to Chinese character, letter, numeral and special symbol etc.
Then, polarity judgement is carried out to the image obtained after connected domain analysis; If the connected domain of fundamental element needs to represent with black in the image obtained, and polarity judged result is that in the image of acquisition after binary conversion treatment, connected domain is white, and background is black, at this moment just needs to carry out inverse process to image.
Then, to the image judging to obtain after process through polarity, correcting direction of image process is carried out.Because scanning or shooting process relate to manual operation, more or less all can there are some in the image to be retrieved of input, before carrying out identifying processing to the fundamental element in image, need to carry out image direction detection, and correcting image direction.
Then, the connected domain in the image obtained is split, in order to split the fundamental element in image, realize column split, obtain some single fundamental elements after image correction operations.
Then, just character recognition process can be carried out respectively to each fundamental element in image, to obtain the text message in image to be retrieved.Wherein, template matching method or feature extraction can be utilized to carry out character recognition process to single character.Such as, Chinese character template can be utilized to carry out character recognition process respectively to each fundamental element, to obtain the Chinese character in image to be retrieved, using as described text message.
Finally, need to carry out correction process and noise filtering process to the text message obtained after this character recognition process.Wherein, correction process can realize the wrongly written character in review text information.Such as, " my door " is corrected to " we ".Noise filtering process can realize removing character unnecessary in text message, as " our door " being treated to " we ".
Embodiment four
Based on the image search method that above-described embodiment one provides, the embodiment of the present invention, in S103, utilizes described text message to retrieve, and is specifically described with the method obtaining the result for retrieval matched with described image to be retrieved.This step specifically can comprise:
Illustrate, in the embodiment of the present invention, utilize described text message to retrieve, can include but not limited to the method obtaining the result for retrieval matched with described image to be retrieved:
First, set up searching database, described searching database comprises the resource identification of text message and the sample image comprised in sample image.Then, utilize described text message, retrieve in described searching database, to obtain the sample image matched with described text message; Finally, according to the sample image matched with described text message, obtain the result for retrieval matched with described image to be retrieved.
Optionally, the result for retrieval matched with described image to be retrieved is exported.
Illustrate, the method setting up searching database can include but not limited to:
First, utilize optical character recognition, character recognition process is carried out to sample image, to obtain the text message comprised in described sample image.Then, obtain the key message comprised in described sample image, and obtain the resource identification of described sample image.Finally, according to the key message comprised in the text message comprised in described sample image, described sample image and described resource identification, described searching database is set up.
It should be noted that, utilize optical character recognition, the method of sample image being carried out to character recognition process see in above-described embodiment three, can utilize optical character recognition to carry out the associated description of character recognition process to image to be retrieved, repeats no more here.
Preferably, the key message comprised in described sample image can include but not limited to: the symbolic information in the formula info comprised in described sample image and non-formula.
Such as, the symbolic information in described non-formula can include but not limited to numeral, letter and special symbol etc.
Preferably, the method obtaining the formula info comprised in described sample image can include but not limited to: after splitting the fundamental element in image to be retrieved, according to the feature of fundamental element in described image, judge whether described fundamental element region is formula region; According to formal notation, described formula region is divided, obtain at least two formula subregions, the identification of formula individual character is carried out to each formula subregion, complete the identification of formula according to the position relationship of recognition result and described at least two formula subregions, thus realize obtaining the formula info comprised in sample image.
Preferably, the method obtaining in described sample image the symbolic information in the non-formula comprised can include but not limited to: utilize digital template, alphabetical template and special symbol template respectively, character recognition process is carried out to the fundamental element in sample image, to obtain the numeral, letter and the special symbol that comprise in described sample image.
In addition, the resource identification of described sample image can also be obtained, and according to the resource identification of the key message comprised in the text message comprised in described sample image, described sample image and described sample image, set up described searching database.Wherein, utilize the resource identification of described sample image, can sample image be obtained.Such as, described resource identification can be the memory address of described sample image.
Wherein, a large amount of sample images can be configured in advance in Sample Storehouse, and be the resource identification of each sample image configuration correspondence.
Preferably, utilize described text message, retrieve in described searching database, can include but not limited to the method obtaining the sample image matched with described text message:
First, the text message comprised in the image to be retrieved obtained is carried out cutting word process, to obtain multiple participle.Then, utilize the plurality of participle, mate in the text message obtained from sample image comprised in searching database, thus the text message simultaneously comprising the plurality of participle can be obtained from searching database.If described searching database does not comprise the text message of the plurality of participle simultaneously, then remove at least one lower participle of weighted value in multiple participle after, utilize remaining participle again to mate in searching database, thus the text message simultaneously comprising remaining participle can be obtained from searching database.By that analogy, until obtain the text message of some from searching database.Finally, the sample image corresponding to the text message that obtains will be mated from searching database, as the sample image matched with the text message that obtains in image to be retrieved.
Be understandable that the sample image corresponding to described text message obtained from searching database is the resource identification of the sample image described in described searching database corresponding to text message in fact.Further, utilize the resource identification of the sample image obtained after overmatching, corresponding sample image can be found, thus the sample image of acquisition can be exported.
Preferably, according to the sample image matched with described text message, the method obtaining the result for retrieval matched with described image to be retrieved can include but not limited to:
Obtain the key message comprised in image to be retrieved; The key message comprised according to comprising key message in described image to be detected, in the sample image that matches with described text message, sorts to the sample image matched with described text message, to obtain described result for retrieval.
Such as, the similarity between the key message that comprises in the key message comprised in image to be retrieved and the sample image obtained from searching database can be calculated.Then, according to similarity order from high to low, the sample image obtained from searching database is sorted, to obtain ranking results, using as described result for retrieval.
It should be noted that, in the embodiment of the present invention, to the sample image matched with the text message that obtains in image to be retrieved, sort, to obtain result for retrieval, its objective is and preferentially export the higher result for retrieval of correlativity to guarantee, improve the accuracy of image retrieval, and meet the picture search demand of user.
Be understandable that, in the embodiment of the present invention, the result for retrieval matched with described image to be retrieved obtained can be the sample image with described image similarity to be retrieved, or also can comprise can as the answer information of content in image to be retrieved or the sample image of reply message.Such as, the content of image to be retrieved is a problem, and the content as the sample image of result for retrieval is answer or the answer of this problem.
Be understandable that, the image search method that the embodiment of the present invention provides and device can be applied to the image retrieval scene comprising text message.Such as, the image retrieval scene comprising text can include but not limited to: the retrieval of exercise question question and answer, book retrieval, formula or library search etc.
Embodiment five
The embodiment of the present invention provides the device embodiment realizing each step and method in said method embodiment further.
Please refer to Fig. 2, the functional block diagram of its image retrieving apparatus provided for the embodiment of the present invention.As shown in the figure, this device comprises:
Image acquisition unit 201, for obtaining image to be retrieved;
Text identification unit 202, for obtaining the text message comprised in described image to be retrieved;
Image retrieval unit 203, for utilizing described text message to retrieve, to obtain the result for retrieval matched with described image to be retrieved.
Preferably, described text identification unit 202, specifically for:
Utilize optical character recognition, character recognition process is carried out to described image to be retrieved, to obtain the text message comprised in described image to be retrieved.
Optionally, described device also comprises: Database unit 204, and for setting up searching database, described searching database comprises the resource identification of text message and the sample image comprised in sample image;
Described image retrieval unit 203, specifically for: utilize described text message, retrieve in described searching database, to obtain the sample image matched with described text message; And, according to the sample image matched with described text message, obtain the result for retrieval matched with described image to be retrieved.
Preferably, described Database unit 204, specifically for:
Utilize optical character recognition, character recognition process is carried out to sample image, to obtain the text message comprised in described sample image;
Obtain the key message comprised in described sample image;
Obtain the resource identification of described sample image;
According to the key message comprised in the text message comprised in described sample image, described sample image and described resource identification, set up described searching database.
Preferably, the sample image that described image retrieval unit 203 matches for basis and described text message, when obtaining the result for retrieval matched with described image to be retrieved, specifically for:
Obtain in described image to be detected and comprise key message;
The key message comprised according to comprising key message in described image to be detected, in the sample image that matches with described text message, sorts to the sample image matched with described text message, to obtain described result for retrieval.
Because each unit in the present embodiment can perform the method shown in Fig. 1, the part that the present embodiment is not described in detail, can with reference to the related description to Fig. 1.
The technical scheme of the embodiment of the present invention has following beneficial effect:
In the embodiment of the present invention, the text message obtained from image to be retrieved is utilized to retrieve, to obtain the result for retrieval matched with described image to be retrieved, be converted into text retrieval by image retrieval, and finally still can obtain the result for retrieval matched with image.With existing image search method, utilize the characteristics such as the external information in image to be retrieved, content characteristic and shape facility, the technical scheme realizing image retrieval is compared, text message is utilized to carry out the mode retrieved in the embodiment of the present invention, matching primitives amount is less, computation complexity is lower, therefore, it is possible to reduce the complexity of image retrieval, improves image retrieval efficiency.
In addition, in the embodiment of the present invention, do not need to set up the higher image encrypting algorithm of complexity, but set up simple, that text retrieval can be realized database, therefore, the cost of Modling model greatly can be reduced, improve the efficiency of Modling model, thus improve image retrieval efficiency.
Those skilled in the art can be well understood to, and for convenience and simplicity of description, the system of foregoing description, the specific works process of device and unit, with reference to the corresponding process in preceding method embodiment, can not repeat them here.
In several embodiment provided by the present invention, should be understood that, disclosed system, apparatus and method, can realize by another way.Such as, device embodiment described above is only schematic, such as, the division of described unit, is only a kind of logic function and divides, and actual can have other dividing mode when realizing, such as, multiple unit or assembly can in conjunction with or another system can be integrated into, or some features can be ignored, or do not perform.Another point, shown or discussed coupling each other or direct-coupling or communication connection can be by some interfaces, and the indirect coupling of device or unit or communication connection can be electrical, machinery or other form.
The described unit illustrated as separating component or can may not be and physically separates, and the parts as unit display can be or may not be physical location, namely can be positioned at a place, or also can be distributed in multiple network element.Some or all of unit wherein can be selected according to the actual needs to realize the object of the present embodiment scheme.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, also can be that the independent physics of unit exists, also can two or more unit in a unit integrated.Above-mentioned integrated unit both can adopt the form of hardware to realize, and the form that hardware also can be adopted to add SFU software functional unit realizes.
The above-mentioned integrated unit realized with the form of SFU software functional unit, can be stored in a computer read/write memory medium.Above-mentioned SFU software functional unit is stored in a storage medium, comprising some instructions in order to make a computer installation (can be personal computer, server, or network equipment etc.) or processor (Processor) perform the part steps of method described in each embodiment of the present invention.And aforesaid storage medium comprises: USB flash disk, portable hard drive, ROM (read-only memory) (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disc or CD etc. various can be program code stored medium.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, within the spirit and principles in the present invention all, any amendment made, equivalent replacement, improvement etc., all should be included within the scope of protection of the invention.
Claims (10)
1. an image search method, is characterized in that, described method comprises:
Obtain image to be retrieved;
Obtain the text message comprised in described image to be retrieved;
Described text message is utilized to retrieve, to obtain the result for retrieval matched with described image to be retrieved.
2. method according to claim 1, is characterized in that, the text message comprised in the described image to be retrieved of described acquisition, comprising:
Utilize optical character recognition, character recognition process is carried out to described image to be retrieved, to obtain the text message comprised in described image to be retrieved.
3. method according to claim 1 and 2, is characterized in that, describedly utilizes described text message to retrieve, and to obtain the result for retrieval matched with described image to be retrieved, comprising:
Set up searching database, described searching database comprises the resource identification of text message and the sample image comprised in sample image;
Utilize described text message, retrieve in described searching database, to obtain the sample image matched with described text message;
According to the sample image matched with described text message, obtain the result for retrieval matched with described image to be retrieved.
4. method according to claim 3, is characterized in that, describedly sets up searching database, comprising:
Utilize optical character recognition, character recognition process is carried out to sample image, to obtain the text message comprised in described sample image;
Obtain the key message comprised in described sample image;
Obtain the resource identification of described sample image;
According to the key message comprised in the text message comprised in described sample image, described sample image and described resource identification, set up described searching database.
5. method according to claim 4, is characterized in that, the sample image that described basis matches with described text message, obtains the result for retrieval matched with described image to be retrieved, comprising:
Obtain in described image to be detected and comprise key message;
The key message comprised according to comprising key message in described image to be detected, in the sample image that matches with described text message, sorts to the sample image matched with described text message, to obtain described result for retrieval.
6. an image retrieving apparatus, is characterized in that, described device comprises:
Image acquisition unit, for obtaining image to be retrieved;
Text identification unit, for obtaining the text message comprised in described image to be retrieved;
Image retrieval unit, for utilizing described text message to retrieve, to obtain the result for retrieval matched with described image to be retrieved.
7. device according to claim 6, is characterized in that, described text identification unit, specifically for:
Utilize optical character recognition, character recognition process is carried out to described image to be retrieved, to obtain the text message comprised in described image to be retrieved.
8. the device according to claim 6 or 7, is characterized in that,
Described device also comprises: Database unit, and for setting up searching database, described searching database comprises the resource identification of text message and the sample image comprised in sample image;
Described image retrieval unit, specifically for: utilize described text message, retrieve in described searching database, to obtain the sample image matched with described text message; And, according to the sample image matched with described text message, obtain the result for retrieval matched with described image to be retrieved.
9. device according to claim 8, is characterized in that, described Database unit, specifically for:
Utilize optical character recognition, character recognition process is carried out to sample image, to obtain the text message comprised in described sample image;
Obtain the key message comprised in described sample image;
Obtain the resource identification of described sample image;
According to the key message comprised in the text message comprised in described sample image, described sample image and described resource identification, set up described searching database.
10. device according to claim 9, is characterized in that, described image retrieval unit is used for the sample image that basis matches with described text message, when obtaining the result for retrieval matched with described image to be retrieved, specifically for:
Obtain in described image to be detected and comprise key message;
The key message comprised according to comprising key message in described image to be detected, in the sample image that matches with described text message, sorts to the sample image matched with described text message, to obtain described result for retrieval.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510109003.3A CN104750791A (en) | 2015-03-12 | 2015-03-12 | Image retrieval method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510109003.3A CN104750791A (en) | 2015-03-12 | 2015-03-12 | Image retrieval method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104750791A true CN104750791A (en) | 2015-07-01 |
Family
ID=53590475
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510109003.3A Pending CN104750791A (en) | 2015-03-12 | 2015-03-12 | Image retrieval method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104750791A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105260381A (en) * | 2015-09-08 | 2016-01-20 | 百度在线网络技术(北京)有限公司 | Data maintenance method based on image recognition and data maintenance device based on image recognition |
CN105975560A (en) * | 2016-04-29 | 2016-09-28 | 广东小天才科技有限公司 | Question searching method and question searching apparatus for intelligent device |
CN106488300A (en) * | 2016-10-27 | 2017-03-08 | 广东小天才科技有限公司 | A kind of video content inspection method and device |
CN106649562A (en) * | 2016-11-10 | 2017-05-10 | 深圳市金立通信设备有限公司 | Information search method and terminal |
CN106781781A (en) * | 2015-11-24 | 2017-05-31 | 上海谦问万答吧云计算科技有限公司 | The solution approach and device of a kind of class of languages exercise |
CN108257615A (en) * | 2018-01-15 | 2018-07-06 | 北京物灵智能科技有限公司 | A kind of user language appraisal procedure and system |
CN111078724A (en) * | 2019-12-11 | 2020-04-28 | 中国建设银行股份有限公司 | Method, device and equipment for searching test questions in learning system and storage medium |
CN113205046A (en) * | 2021-04-30 | 2021-08-03 | 作业帮教育科技(北京)有限公司 | Method, system, device and medium for identifying question book |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101714160A (en) * | 2009-12-22 | 2010-05-26 | 金星辉 | Picture searching method and system |
CN103678637A (en) * | 2013-12-19 | 2014-03-26 | 北京快乐学网络科技有限公司 | Method and device for acquiring test question information |
CN103914567A (en) * | 2014-04-23 | 2014-07-09 | 北京奇虎科技有限公司 | Objective test question answer matching method and objective test question answer matching device |
CN103984772A (en) * | 2014-06-04 | 2014-08-13 | 百度在线网络技术(北京)有限公司 | Method and device for generating text retrieval subtitle library and video retrieval method and device |
CN104142955A (en) * | 2013-05-08 | 2014-11-12 | 中国移动通信集团浙江有限公司 | Method and terminal for recommending learning courses |
-
2015
- 2015-03-12 CN CN201510109003.3A patent/CN104750791A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101714160A (en) * | 2009-12-22 | 2010-05-26 | 金星辉 | Picture searching method and system |
CN104142955A (en) * | 2013-05-08 | 2014-11-12 | 中国移动通信集团浙江有限公司 | Method and terminal for recommending learning courses |
CN103678637A (en) * | 2013-12-19 | 2014-03-26 | 北京快乐学网络科技有限公司 | Method and device for acquiring test question information |
CN103914567A (en) * | 2014-04-23 | 2014-07-09 | 北京奇虎科技有限公司 | Objective test question answer matching method and objective test question answer matching device |
CN103984772A (en) * | 2014-06-04 | 2014-08-13 | 百度在线网络技术(北京)有限公司 | Method and device for generating text retrieval subtitle library and video retrieval method and device |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105260381A (en) * | 2015-09-08 | 2016-01-20 | 百度在线网络技术(北京)有限公司 | Data maintenance method based on image recognition and data maintenance device based on image recognition |
CN106781781A (en) * | 2015-11-24 | 2017-05-31 | 上海谦问万答吧云计算科技有限公司 | The solution approach and device of a kind of class of languages exercise |
CN105975560A (en) * | 2016-04-29 | 2016-09-28 | 广东小天才科技有限公司 | Question searching method and question searching apparatus for intelligent device |
CN106488300A (en) * | 2016-10-27 | 2017-03-08 | 广东小天才科技有限公司 | A kind of video content inspection method and device |
CN106649562A (en) * | 2016-11-10 | 2017-05-10 | 深圳市金立通信设备有限公司 | Information search method and terminal |
CN108257615A (en) * | 2018-01-15 | 2018-07-06 | 北京物灵智能科技有限公司 | A kind of user language appraisal procedure and system |
CN111078724A (en) * | 2019-12-11 | 2020-04-28 | 中国建设银行股份有限公司 | Method, device and equipment for searching test questions in learning system and storage medium |
CN113205046A (en) * | 2021-04-30 | 2021-08-03 | 作业帮教育科技(北京)有限公司 | Method, system, device and medium for identifying question book |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104750791A (en) | Image retrieval method and device | |
CN107657048B (en) | User identification method and device | |
US10817615B2 (en) | Method and apparatus for verifying images based on image verification codes | |
CN102779140B (en) | A kind of keyword acquisition methods and device | |
CN112347244B (en) | Yellow-based and gambling-based website detection method based on mixed feature analysis | |
CN109685052A (en) | Method for processing text images, device, electronic equipment and computer-readable medium | |
CN109635805B (en) | Image text positioning method and device and image text identification method and device | |
CN111353491A (en) | Character direction determining method, device, equipment and storage medium | |
CN109299235A (en) | Knowledge base searching method, apparatus and computer readable storage medium | |
CN106156794B (en) | Character recognition method and device based on character style recognition | |
CN111061887A (en) | News character photo extraction method, device, equipment and storage medium | |
CN112784009A (en) | Subject term mining method and device, electronic equipment and storage medium | |
CN117011581A (en) | Image recognition method, medium, device and computing equipment | |
CN113205046B (en) | Method, system, device and medium for identifying books | |
CN111177421A (en) | Method and device for generating email historical event axis facing digital human | |
CN114386013A (en) | Automatic student status authentication method and device, computer equipment and storage medium | |
CN113569118A (en) | Self-media pushing method and device, computer equipment and storage medium | |
CN111027533B (en) | Click-to-read coordinate transformation method, system, terminal equipment and storage medium | |
CN110929647B (en) | Text detection method, device, equipment and storage medium | |
CN111783786A (en) | Picture identification method and system, electronic equipment and storage medium | |
CN104598289A (en) | Recognition method and electronic device | |
CN106599275A (en) | Shooting search method and device | |
CN112801960B (en) | Image processing method and device, storage medium and electronic equipment | |
CN110276001B (en) | Checking page identification method and device, computing equipment and medium | |
CN103778210A (en) | Method and device for judging specific file type of file to be analyzed |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C41 | Transfer of patent application or patent right or utility model | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20160201 Address after: 100085, Beijing, Haidian District on the road to entrepreneurship No. 1, 28, 4, room 417 Applicant after: Operation education technology (Beijing) Co., Ltd. Address before: 100085 Beijing, Haidian District, No. ten on the street Baidu building, No. 10 Applicant before: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY Co.,Ltd. |
|
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150701 |
|
RJ01 | Rejection of invention patent application after publication |