CN105824928A - Mobile terminal, server, content-based image recognition searching method and system - Google Patents
Mobile terminal, server, content-based image recognition searching method and system Download PDFInfo
- Publication number
- CN105824928A CN105824928A CN201610153430.6A CN201610153430A CN105824928A CN 105824928 A CN105824928 A CN 105824928A CN 201610153430 A CN201610153430 A CN 201610153430A CN 105824928 A CN105824928 A CN 105824928A
- Authority
- CN
- China
- Prior art keywords
- image
- unknown
- things
- mobile terminal
- server
- 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
- 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
- G06F16/5838—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using colour
Landscapes
- Engineering & Computer Science (AREA)
- Library & Information Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a content-based image recognition searching method, a mobile terminal, a server and a system, wherein the mobile terminal is used for shooting an image of an unknown object, sending the shot image of the unknown object to the server at a cloud side after a plurality of target regions with rich information contents or the classification types of the unknown object are selected, finally receiving inquiry result information pushed by the server and performing display; the server is used for receiving the unknown object image sent by the mobile terminal, performing feature classification to extract image feature values, then, performing searching in an image index relationship table of the unknown object according to the image feature values, and finally pushing the searched unknown object image and the unknown object information to the mobile terminal. The content-based image recognition searching method disclosed by the invention has the advantages that the object searching convenience and accuracy under the condition of only knowing the appearance of the unknown object are improved; high application prospects are realized.
Description
Technical field
The present invention relates to the communication technical field of mobile terminal, particularly to a kind of mobile terminal, server, image identification search method and system based on content.
Background technology
Since entering 21st century, Internet technology develops rapidly, and the business of the Internet is continuously increased, and people need to search on the internet various information, and more and more higher to the speed of search and the requirement of efficiency.
But in existing way of search, the main Word message by inputting scans for, due to being continuously increased of Various types of data type in the Internet, quantity of information is the hugest so that the inefficiency of search, searches for the most long.And on the premise of not knowing the information that user is interested, user also is difficult to search the relevant information mated with self search target information.
The increasing demand of users is to carry out picture search for the various objects in daily life.Such as see certain plant or animal or certain trade mark as user, interested in it, can pass through its image of cameras capture, then by image search apparatus image be identified or search for, to obtain the relevant information of content in image.
Summary of the invention
It is an object of the invention to the shortcoming overcoming prior art with not enough, it is provided that a kind of mobile terminal, server, image identification search method and system based on content.
According to disclosed embodiment, a first aspect of the present invention proposes a kind of image identification search method based on content, is applied to mobile terminal, and described image identification search method includes:
The image of the unknown things of shooting；
The image of described unknown things is sent the server to high in the clouds；
Receive the Query Result information of described server push and show.
Further, after the image of the unknown things of described shooting, also include:
The target area that several information contents selected are abundant on the image of described unknown things.
Further, after the image of the unknown things of described shooting, also include:
Select the class categories of unknown things.
According to disclosed embodiment, a second aspect of the present invention also proposed a kind of image identification search method based on content, is applied to server, and described image identification search method includes:
Receive the unknown things image that mobile terminal sends；
Described unknown things image is carried out tagsort, extracts image feature value；
Scan in the image index relation table of unknown things according to described image feature value；
The unknown things image searched and unknown separate feature are pushed to mobile terminal.
Further, the unknown things image that mobile terminal sends is received；
The target area of described unknown things image is carried out tagsort, extracts the multiple spot eigenvalue of image；
Multiple spot eigenvalue according to described image scans in the image index relation table of unknown things；
The unknown things image searched and unknown separate feature are pushed to mobile terminal.
Further, the target area of the described unknown things image to uploading carries out tagsort, before extracting the multiple spot eigenvalue of image, also includes the image index relation table setting up described unknown things, and it is specific as follows:
Obtain unknown things picture and unknown separate feature from each big search database website, be stored in cloud server visual signature data base；
Obtain the image feature value of unknown things picture in visual signature data base；
Image feature value is according to unknown things classification of things classification in search database website, the sub-category index relative table setting up unknown things picture in visual signature data base, and stores on the server.
Further, described image feature value includes color characteristic, brightness and textural characteristics.
According to disclosed embodiment, a third aspect of the present invention proposes the mobile terminal of a kind of image identification search based on content, and described mobile terminal includes following modules:
Taking module, for shooting the image of unknown things；
First sending module, for sending the server to high in the clouds by the image of described unknown things；
First receiver module, for receiving the Query Result information of described server push and showing.
Further, described mobile terminal also includes:
First option mod, the target area that several information contents selected are abundant on the image in described unknown things.
Further, described mobile terminal also includes:
Second option mod, for selecting the class categories of unknown things.
According to disclosed embodiment, a fourth aspect of the present invention proposes the server of a kind of image identification search based on content, and described server includes following modules:
Second receiver module, for receiving the unknown things image that mobile terminal sends；
Characteristic extracting module, for described unknown things image is carried out tagsort, extracts image feature value；
Image search module, for scanning in the image index relation table of unknown things according to described image feature value；
Second sending module, for being pushed to mobile terminal by the unknown things image searched and unknown separate feature.
Further, described characteristic extracting module carries out tagsort to the target area of described unknown things image, extracts the multiple spot eigenvalue of image；
Described image search module scans in the image index relation table of unknown things according to the multiple spot eigenvalue of described image.
Further, described server also includes image index relation table module, and for setting up the image index relation table of described unknown things, this module includes:
Acquisition of information and memory element, for obtaining unknown things picture and unknown separate feature from each big search database website, be stored in cloud server visual signature data base；
Image feature value acquiring unit, for obtaining the image feature value of unknown things picture in visual signature data base；
Index relative table forms unit, for image feature value according to unknown things classification of things classification in search database website, the sub-category index relative table setting up unknown things picture in visual signature data base, and stores on the server.
According to disclosed embodiment, a fifth aspect of the present invention proposes the system of a kind of image identification search based on content, including:
Mobile terminal, for shooting the image of unknown things, by the image transmission of unknown for shooting things to the server in high in the clouds after selecting the class categories of the abundant target area of several information contents or unknown things, finally receive the Query Result information of server push and show；
Server, for receiving the unknown things image of mobile terminal transmission and carrying out tagsort extraction image feature value, then scan in the image index relation table of unknown things according to described image feature value, finally the unknown things image searched and unknown separate feature are pushed to mobile terminal.
The present invention has such advantages as relative to prior art and effect:
1) image identification search method based on content disclosed by the invention, owing to combining the image feature value of things, when so retrieving, even if not knowing other relevant informations more accurately, remain to rely on powerful cloud server to correctly search for required separate feature, avoid the most artificial view-based access control model feature to retrieve or search for simultaneously, improve convenience and the accuracy searching for things in the case of only knowing unknown things outward appearance.
2) image identification search method disclosed by the invention is widely used, owing to existing hand-held mobile terminal such as smart mobile phone, panel computer all have camera function, user out of doors, market or other etc. place see that the unknown things of concern can take pictures to be dealt on server and accurately search unknown things (such as plant, animal) picture and unknown separate feature easily.
Accompanying drawing explanation
For the technical scheme being illustrated more clearly that in the embodiment of the present invention, the accompanying drawing used required in embodiment or description of the prior art will be briefly described below, apparently, accompanying drawing in describing below is only some embodiments of the present invention, for those of ordinary skill in the art, on the premise of not paying creative work, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is the process step figure of a kind of based on content the image identification search method disclosed in the present embodiment one；
Fig. 2 is the process step figure of image identification search based on the content method of the another kind disclosed in the present embodiment one；
Fig. 3 is the flow chart of steps of a kind of based on content the image identification search method disclosed in the present embodiment two；
Fig. 4 is the flow chart of steps of image identification search based on the content method of the another kind disclosed in the present embodiment two；
Fig. 5 is the flow chart of steps of the image index relation table setting up described unknown things in the present embodiment two；
Fig. 6 is the composition frame chart of a kind of based on content the image identification search mobile terminal disclosed in the present embodiment three；
Fig. 7 is the composition frame chart of a kind of based on content the image identification search mobile terminal disclosed in the present embodiment three；
Fig. 8 is the composition frame chart of a kind of based on content the image identification search server disclosed in the present embodiment four；
Fig. 9 is the composition frame chart of a kind of based on content the image identification search server disclosed in the present embodiment four；
Figure 10 is the structured flowchart of a kind of based on content the image identification search system disclosed in the present embodiment five.
Detailed description of the invention
For making the purpose of the present invention, technical scheme and advantage clearer, clear and definite, the present invention is described in more detail for the embodiment that develops simultaneously referring to the drawings.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not intended to limit the present invention.
Term " first " in description and claims of this specification and above-mentioned accompanying drawing, " second ", " the 3rd " and " the 4th " etc. are for distinguishing different object rather than for describing particular order.Additionally, term " includes " and " having " and their any deformation, it is intended that cover non-exclusive comprising.Such as contain series of steps or the process of unit, method, system, product or equipment are not limited to step or the unit listed, but the most also include step or the unit do not listed, or the most also include other step intrinsic for these processes, method, product or equipment or unit.
It is described in detail respectively below according to embodiment.
Embodiment one
Refer to the process step figure that Fig. 1, Fig. 1 are a kind of based on content the image identification search methods disclosed in the present embodiment one.Image identification search method based on content shown in Fig. 1, it is applied to the intelligent mobile terminal equipped with photographic head, described intelligent mobile terminal includes but not limited to mobile phone, notebook computer, panel computer and palm equipment for surfing the net, multimedia equipment, stream media equipment, mobile internet device (MID, mobileinternetdevice), wearable device or other kinds of terminal unit.
Below in conjunction with Fig. 1, illustrate the process step of a kind of image identification search method based on content, should image identification search method based on content include:
Step S101, the image of the unknown things of shooting；
Wherein, described image can be shot by capture apparatus, and described capture apparatus can be photographic head；And camera, mobile phone, panel computer etc. are with the various equipment of photographic head；And the object of its shooting can be the applicable object of the article scanned for required for user, the trade mark of such as unknown plant, animal, automobile or commodity, the commodity of unknown purposes, head portrait of certain famous person etc..
Step S102, the image of described unknown things is sent the server to high in the clouds；
In this step, unknown things image and the coordinate indexing of shooting are wirelessly sent to cloud server by mobile terminal.The wireless modes such as such as WiFi, 3G or 4G communication network.
Step S103, receive the Query Result information of described server push and show.
In this step, mobile terminal receives the Query Result that cloud server pushes, and is presented to inquiry user by the display device of mobile terminal device.
In another preferred embodiment, in a kind of based on content the image identification search method disclosed in the present embodiment after the image of step S101, the unknown things of shooting, also include:
Step S101X, the target area that several information contents selected are abundant on described unknown things image；
In correlation technique, along with the increase of the pixel that target image comprises, the amount of calculation exponentially of the method contrasting pixel frame by frame increases, thus causes the efficiency of image identification search substantially to reduce.One preferred implementation of the embodiment of the present invention being supported, the target area for unknown things image is selected is retrieved, the information content that unknown things image comprises in being frequently present of certain block or a few pieces of image-regions is big, now, manually several target areas can be selected on unknown things image, it is possible to by the region that information content on the unknown things image in mobile terminal Intelligent Recognition location is abundant by user.
In another preferred embodiment, in a kind of based on content the image identification search method disclosed in the present embodiment after the image of step S101, the unknown things of shooting, also include:
Step S101Y, the class categories of the unknown things of selection.
User is based on cognitive general knowledge and learning intelligence, can tentatively judge the class categories of unknown things, such as user needs the unknown things of inquiry to be the flower do not met, now user can while the unknown things image of shooting or afterwards, the class categories of the most selected unknown things, such as flower belongs to plant, the things class categories that user is now selected " plant ", the inquiry of the most unknown things preferentially will carry out image retrieval comparison in plant classification, this step is conducive to the hunting zone reducing unknown things image to promote unknown things picture search efficiency simultaneously.
Wherein, the selection of the classification of unknown things classification can be carried out by the way of drop-down option menu.
Process step figure including above-mentioned steps S101X and the image identification search method based on content of step S101Y can refer to shown in accompanying drawing 2.
In sum, the method can be transmitted to high in the clouds data server by the picture rich in detail of the unknown things of mobile terminal shooting whenever and wherever possible, server end carries out tagsort to the unknown things picture uploaded beyond the clouds, extract image feature value, then using in the image feature value obtained server picture indices file beyond the clouds and scan for, the pictorial information of lookup is pushed to mobile terminal and consults for user by cloud server.
Embodiment two
Refer to the flow chart of steps that Fig. 3, Fig. 3 are a kind of based on content the image identification search methods disclosed in the present embodiment two.A kind of based on content image identification search method shown in Fig. 3, is applied to remote server, specifically includes following steps:
The unknown things image that step S200, reception mobile terminal send；
When mobile terminal sends propelling movement instruction, the unknown things image that server sends according to instruction wireless receiving mobile terminal.
Step S201, the tagsort that carries out the unknown things image uploaded, extract image feature value；
In the present embodiment, image in the server end unknown things to uploading scans for computing, first, server carries out tagsort after receiving the image of the unknown things that mobile terminal is uploaded, extracting image feature value, image feature value includes but not limited to: color characteristic, brightness and textural characteristics.
Step S202, scan in the image index relation table of unknown things according to described image feature value；
In this step, the image index relation table of the unknown things that the image feature value that use obtains is set up the most in advance scans for.
Step S203, the unknown things image searched and unknown separate feature are pushed to mobile terminal.
In another preferred embodiment, a kind of image identification search method based on content is referring in particular to shown in accompanying drawing 4, and further detailed step is:
The unknown things image that step S200X, reception mobile terminal send；
Step S201X, target area to the unknown things image uploaded carry out tagsort, extract the multiple spot eigenvalue of image；
Corresponding steps behind the target area that this step is artificial according to user in embodiment one or mobile terminal or in the selected unknown things image of intelligence, information content is big.In this step, server end carries out tagsort just for the target area of the unknown things image that mobile terminal is uploaded, the multiple spot eigenvalue of Simultaneous Extracting Image, nontarget area is not the most carried out tagsort,.
Step S202X, scan in the image index relation table of unknown things according to the multiple spot eigenvalue of described image；
The present invention, in order to reduce the efficiency of image identification search further, uses the search of multiple characteristic points to the target area of unknown things image, such that it is able to the shortcoming that the method amount of calculation avoiding contrasting pixel in correlation technique frame by frame is huge；Specifically, contrasting the picture searching time that the method for pixel causes in correlation technique frame by frame is exponentially increased, and the picture searching time that the target image multiple characteristic point searching method in this preferred implementation causes linearly increases.Picture many for pixel, that color is complicated, uses the method that the embodiment of the present invention provides, it is possible to significantly improve characteristic point hit rate, hence it is evident that reduce the picture searching time.
In detailed description of the invention, for a secondary plane picture, the target area of unknown things image is a two-dimentional array of pixels, the image information of the corresponding pixel of each element in array, in array there is the biggest redundancy in the quantity of information between adjacent element, uses multiple characteristic point to search for, and extracts the image information of a pixel by being separated by several positions, form a two-dimensional pixel array simplified, reduce further the operand that target image search is calculated.
Step S203X, the unknown things image searched and unknown separate feature are pushed to mobile terminal.
In another preferred embodiment, also including step S200, set up the image index relation table of described unknown things before described step S201, its process step figure can refer to shown in accompanying drawing 5, and it specifically includes following steps:
S2001, obtain unknown things picture and unknown separate feature from each big search database website, be stored in cloud server visual signature data base；
The image feature value of unknown things picture in S2002, acquisition visual signature data base；
S2003, image feature value are according to unknown things classification of things classification in search database website, the sub-category index relative table setting up unknown things picture in visual signature data base, and store on the server.
This preferred embodiment in, first pass through crawling of the unknown things picture to each big search database website and unknown separate feature, and with the sub-category index file setting up unknown things picture in visual signature data base of characteristics of image property value of unknown things picture, storage is on the server；Then, server carries out the search of similar commodity in the image index relation table of described unknown things according to the characteristics of image property value of the unknown things picture uploaded；Finally according to the Search Results of unknown things, the unknown things picture searched and unknown separate feature are pushed to mobile terminal.
Image feature value described in the present embodiment, includes but not limited to: color characteristic, brightness and textural characteristics.
So, user can use the photographic head of mobile terminal to obtain the image of unknown things by taking pictures, then upload onto the server, in the server, extract the characteristics of image property value of unknown things picture, utilize the characteristics of image property value obtained to carry out the search of corresponding unknown things in the image index relation table of server the unknown things, obtain desired unknown things picture and merchandise news.Owing to combining the characteristics of image property value of unknown things picture, when so retrieving, more precisely search required unknown separate feature, improve convenience and the accuracy searching for more specifically unknown things in the case of knowing unknown things outward appearance.
Embodiment three
Embodiments provide a kind of image identification search mobile terminal based on content, Fig. 6 is the structured flowchart of the disclosed image identification search mobile terminal 1 based on content of the embodiment of the present invention, and this mobile terminal 1 includes: taking module the 301, first sending module the 302, first receiver module 303.Wherein:
Taking module 301, for shooting the image of unknown things；
Above-mentioned image is shot by capture apparatus, and described capture apparatus can be photographic head；And camera, mobile phone, panel computer etc. are with the various equipment of photographic head；And the object of its shooting can be the applicable object of the article scanned for required for user, the trade mark of such as unknown plant, animal, automobile or commodity, the commodity of unknown purposes, head portrait of certain famous person etc..
First sending module 302, for sending the server to high in the clouds by the image of described unknown things.
In this module, unknown things image and the coordinate indexing of shooting are wirelessly sent to cloud server by mobile terminal.The wireless modes such as such as WiFi, 3G or 4G communication network.
First receiver module 303, for receiving the Query Result information of described server push and showing.
In this module, mobile terminal receives the Query Result that cloud server pushes, and is presented to inquiry user by the display device of mobile terminal device.
Another preferred embodiment in, described mobile terminal 1 also includes:
First option mod 304, the target area that several information contents selected are abundant on the image in described unknown things.
Along with the increase of the pixel that target image comprises, the amount of calculation exponentially of the method contrasting pixel frame by frame increases, thus causes the efficiency of image identification search substantially to reduce.In the preferred implementation of the present embodiment, support that the target area for unknown things image is selected is retrieved, the information content that unknown things image comprises in being frequently present of certain block or a few pieces of image-regions is big, now, manually several target areas can be selected on unknown things image, it is possible to by the region that information content on the unknown things image in mobile terminal Intelligent Recognition location is abundant by user.
Another preferred embodiment in, described mobile terminal 1 also includes:
Second option mod 305, for selecting the class categories of unknown things.
User is based on cognitive general knowledge and learning intelligence, can tentatively judge the class categories of unknown things, such as user needs the unknown things of inquiry to be the flower do not met, now user can while the unknown things image of shooting or afterwards, the class categories of the most selected unknown things, such as flower belongs to plant, the things class categories that user is now selected " plant ", the inquiry of the most unknown things preferentially will carry out image retrieval comparison in plant classification, this module is conducive to the hunting zone reducing unknown things image to promote unknown things picture search efficiency simultaneously.
Comprise the structure composition frame chart of image identification search mobile terminal based on content of above-mentioned first option mod 304 and the second option mod 305 referring to the drawings shown in 7.
In sum, the picture rich in detail transmission of unknown things should can be shot to high in the clouds data server whenever and wherever possible by image recognition mobile terminal based on content by the photographic head carried, server end carries out tagsort to the unknown things picture uploaded beyond the clouds, extract image feature value, then using in the image feature value obtained server picture indices file beyond the clouds and scan for, the pictorial information of lookup is pushed to mobile terminal and consults for user by cloud server.
Embodiment four
Embodiments provide a kind of image identification search server based on content, Fig. 8 is the structured flowchart of the disclosed image identification search server 2 based on content of the embodiment of the present invention, and this server 2 includes: the second receiver module 400, characteristic extracting module 401, image search module 402 and the second sending module 403.Wherein:
Second receiver module 400, for receiving the unknown things image that mobile terminal sends.
When mobile terminal sends propelling movement instruction, the unknown things image that server sends according to instruction wireless receiving mobile terminal.
Characteristic extracting module 401, for described unknown things image is carried out tagsort, extracts image feature value.
Image in the server end unknown things to uploading scans for computing, and server receives the target area of the unknown things image that mobile terminal is uploaded and carries out tagsort, extracts the multiple spot eigenvalue of image.Wherein, image feature value includes but not limited to: color characteristic, brightness and textural characteristics.
Image search module 402, for scanning in the image index relation table of unknown things according to described image feature value.
In this module, the multiple spot eigenvalue with specific reference to described image scans in the image index relation table of unknown things；
The present invention, in order to reduce the efficiency of image identification search further, uses the search of multiple characteristic points to the target area of unknown things image, such that it is able to the shortcoming that the method amount of calculation avoiding contrasting pixel in correlation technique frame by frame is huge；Specifically, contrasting the picture searching time that the method for pixel causes in correlation technique frame by frame is exponentially increased, and the picture searching time that the target image multiple characteristic point searching method in this preferred implementation causes linearly increases.Picture many for pixel, that color is complicated, uses the method that the embodiment of the present invention provides, it is possible to significantly improve characteristic point hit rate, hence it is evident that reduce the picture searching time.
Second sending module 403, for being pushed to mobile terminal by the unknown things image searched and unknown separate feature.
Another preferred embodiment in, the disclosed image identification search server based on content of the present embodiment four also includes image index relation table module 40X, for setting up the image index relation table of described unknown things, this image index relation table module 40X includes:
Acquisition of information and memory element 40X1, for obtaining unknown things picture and unknown separate feature from each big search database website, be stored in cloud server visual signature data base；
Image feature value acquiring unit 40X2, for obtaining the image feature value of unknown things picture in visual signature data base；
Index relative table forms unit 40X3, for image feature value according to unknown things classification of things classification in search database website, the sub-category index relative table setting up unknown things picture in visual signature data base, and stores on the server.
Comprise the structured flowchart of above-mentioned image index relation table module 40X as shown in Figure 9.
In sum, user first by the photographic head of mobile terminal by the image obtaining unknown things of taking pictures, then the server disclosed in the present embodiment four it is uploaded to, in the server, extract the characteristics of image property value of unknown things picture, utilize the characteristics of image property value obtained to carry out the search of corresponding unknown things in the image index relation table of server the unknown things, obtain desired unknown things picture and merchandise news.Owing to combining the characteristics of image property value of unknown things picture, when so retrieving, more precisely search required unknown separate feature, improve convenience and the accuracy searching for more specifically unknown things in the case of knowing unknown things outward appearance.
Embodiment five
The embodiment of the invention discloses the system of a kind of image identification search based on content, Figure 10 is the structured flowchart of the system of the image identification search based on content that the embodiment of the present invention provides, and this system includes:
Mobile terminal 1, for shooting the image of unknown things, by the image transmission of unknown for shooting things to the server in high in the clouds after selecting the class categories of the abundant target area of several information contents or unknown things, finally receive the Query Result information of server push and show；
Server, 2 for receiving the unknown things image of mobile terminal transmission and carrying out tagsort extraction image feature value, then scan in the image index relation table of unknown things according to described image feature value, finally the unknown things image searched and unknown separate feature are pushed to mobile terminal.
Wherein, mobile terminal 1 and server 2 are by based on wide area network (WideAreaNetwork, WAN) it is mutual that communications platform carries out information, so that mobile terminal sends unknown things image and remote server to mobile terminal feedback information to remote server.
In sum, the disclosed image identification search system based on content of the embodiment of the present invention, including mobile terminal 1 and server 2, the server 2 of image and selected search option and high in the clouds that above-mentioned mobile terminal 1 is responsible for shooting, collecting the unknown things is responsible for carrying out feature extraction and search matching primitives, jointly coordinate cooperation, achieve the function of image identification search based on content, characteristics of image property value in conjunction with unknown things picture, more precisely search required unknown separate feature, and ensure that convenience and the accuracy searching for more specifically unknown things in the case of knowing unknown things outward appearance.
In each method embodiment of the present invention; the sequence number of described each step can not be used for limiting the sequencing of each step; for those of ordinary skill in the art, on the premise of not paying creative work, the priority of each step is changed also within protection scope of the present invention.
The module of foregoing description or the specific works process of unit, be referred to the corresponding process in preceding method embodiment, do not repeat them here.
It should be noted that in above-mentioned terminal and server example, included modules and unit are to carry out dividing according to function logic, but are not limited to above-mentioned division, as long as being capable of corresponding function；It addition, the specific name of each module and unit is also only to facilitate mutually distinguish, it is not limited to protection scope of the present invention.
In several embodiments provided herein, it should be understood that disclosed equipment and method, can realize by another way.Such as, terminal embodiment described above is only schematically, such as, described module or the division of unit, be only a kind of logic function to divide, actual can have when realizing other dividing mode, the most multiple unit or assembly can in conjunction with or be desirably integrated into another system, or some features can ignore, or do not perform.Another point, shown or discussed coupling each other or direct-coupling or communication connection can be the INDIRECT COUPLING by some interfaces, module or unit or communication connection, can be electrical, machinery or other form.
Additionally, each functional module or unit in each embodiment of the present invention can be integrated in a processing module or unit, can also be modules or unit is individually physically present, it is also possible to two or more modules or unit are integrated in a module or unit.
Above-described embodiment is the present invention preferably embodiment; but embodiments of the present invention are also not restricted to the described embodiments; the change made under other any spirit without departing from the present invention and principle, modify, substitute, combine, simplify; all should be the substitute mode of equivalence, within being included in protection scope of the present invention.
Claims (14)
1. an image identification search method based on content, is applied to mobile terminal, it is characterised in that described image identification search method includes:
The image of the unknown things of shooting；
The image of described unknown things is sent the server to high in the clouds；
Receive the Query Result information of described server push and show.
A kind of image identification search method based on content the most according to claim 1, it is characterised in that after the image of described shooting the unknown things, also include:
The target area that several information contents selected are abundant on the image of described unknown things.
A kind of image identification search method based on content the most according to claim 1, it is characterised in that after the image of described shooting the unknown things, also include:
Select the class categories of unknown things.
4. an image identification search method based on content, is applied to server, it is characterised in that described image identification search method includes:
Receive the unknown things image that mobile terminal sends；
Described unknown things image is carried out tagsort, extracts image feature value；
Scan in the image index relation table of unknown things according to described image feature value；
The unknown things image searched and unknown separate feature are pushed to mobile terminal.
A kind of image identification search method based on content the most according to claim 4, it is characterised in that
Receive the unknown things image that mobile terminal sends；
The target area of described unknown things image is carried out tagsort, extracts the multiple spot eigenvalue of image；
Multiple spot eigenvalue according to described image scans in the image index relation table of unknown things；
The unknown things image searched and unknown separate feature are pushed to mobile terminal.
A kind of image identification search method based on content the most according to claim 1, it is characterized in that, the target area of the described unknown things image to uploading carries out tagsort, before extracting the multiple spot eigenvalue of image, also including the image index relation table setting up described unknown things, it is specific as follows:
Obtain unknown things picture and unknown separate feature from each big search database website, be stored in cloud server visual signature data base；
Obtain the image feature value of unknown things picture in visual signature data base；
Image feature value is according to unknown things classification of things classification in search database website, the sub-category index relative table setting up unknown things picture in visual signature data base, and stores on the server.
7. according to arbitrary described a kind of based on content the image identification search method of claim 4 to 6, it is characterised in that
Described image feature value includes color characteristic, brightness and textural characteristics.
8. the mobile terminal of an image identification search based on content, it is characterised in that described mobile terminal includes following modules:
Taking module, for shooting the image of unknown things；
First sending module, for sending the server to high in the clouds by the image of described unknown things；
First receiver module, for receiving the Query Result information of described server push and showing.
The mobile terminal of a kind of image identification search based on content the most according to claim 8, it is characterised in that described mobile terminal also includes:
First option mod, the target area that several information contents selected are abundant on the image in described unknown things.
The mobile terminal of a kind of image identification search based on content the most according to claim 8, it is characterised in that described mobile terminal also includes:
Second option mod, for selecting the class categories of unknown things.
The server of 11. 1 kinds of image identification search based on content, it is characterised in that described server includes following modules:
Second receiver module, for receiving the unknown things image that mobile terminal sends；
Characteristic extracting module, for described unknown things image is carried out tagsort, extracts image feature value；
Image search module, for scanning in the image index relation table of unknown things according to described image feature value；
Second sending module, for being pushed to mobile terminal by the unknown things image searched and unknown separate feature.
The server of 12. a kind of image identification search based on content according to claim 11, it is characterised in that
Described characteristic extracting module carries out tagsort to the target area of described unknown things image, extracts the multiple spot eigenvalue of image；
Described image search module scans in the image index relation table of unknown things according to the multiple spot eigenvalue of described image.
The server of 13. a kind of image identification search based on content according to claim 11, it is characterised in that
Described server also includes image index relation table module, and for setting up the image index relation table of described unknown things, this module includes:
Acquisition of information and memory element, for obtaining unknown things picture and unknown separate feature from each big search database website, be stored in cloud server visual signature data base；
Image feature value acquiring unit, for obtaining the image feature value of unknown things picture in visual signature data base；
Index relative table forms unit, for image feature value according to unknown things classification of things classification in search database website, the sub-category index relative table setting up unknown things picture in visual signature data base, and stores on the server.
The system of 14. 1 kinds of image identification search based on content, it is characterised in that including:
Mobile terminal, for shooting the image of unknown things, by the image transmission of unknown for shooting things to the server in high in the clouds after selecting the class categories of the abundant target area of several information contents or unknown things, finally receive the Query Result information of server push and show；
Server, for receiving the unknown things image of mobile terminal transmission and carrying out tagsort extraction image feature value, then scan in the image index relation table of unknown things according to described image feature value, finally the unknown things image searched and unknown separate feature are pushed to mobile terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610153430.6A CN105824928A (en) | 2016-03-17 | 2016-03-17 | Mobile terminal, server, content-based image recognition searching method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610153430.6A CN105824928A (en) | 2016-03-17 | 2016-03-17 | Mobile terminal, server, content-based image recognition searching method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105824928A true CN105824928A (en) | 2016-08-03 |
Family
ID=56524611
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610153430.6A Pending CN105824928A (en) | 2016-03-17 | 2016-03-17 | Mobile terminal, server, content-based image recognition searching method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105824928A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106649485A (en) * | 2016-09-30 | 2017-05-10 | 广东欧珀移动通信有限公司 | Method for pushing information and mobile terminal |
| CN106777316A (en) * | 2017-01-03 | 2017-05-31 | 深圳皮皮哥网络科技有限公司 | A kind of network leather lines image search method and system |
| CN106933968A (en) * | 2017-02-09 | 2017-07-07 | 北京理工大学 | A kind of related information acquisition methods, terminal, server and system |
| CN106940807A (en) * | 2017-04-19 | 2017-07-11 | 深圳市元征科技股份有限公司 | A kind of processing method and processing device based on mirror device of looking in the distance |
| CN107016368A (en) * | 2017-04-07 | 2017-08-04 | 郑州悉知信息科技股份有限公司 | The information acquisition method and server of a kind of object |
| CN107145823A (en) * | 2017-03-29 | 2017-09-08 | 深圳市元征科技股份有限公司 | A kind of image-recognizing method, pattern recognition device and server |
| CN107948391A (en) * | 2016-10-12 | 2018-04-20 | 吴展兴 | Action electronic device and server |
| CN108280420A (en) * | 2018-01-19 | 2018-07-13 | 百度在线网络技术（北京）有限公司 | System, method and apparatus for handling image |
| CN108900629A (en) * | 2018-07-25 | 2018-11-27 | 西安艾润物联网技术服务有限责任公司 | A kind of service push method and device |
| CN110020185A (en) * | 2017-12-29 | 2019-07-16 | 国民技术股份有限公司 | Intelligent search method, terminal and server |
| CN110445980A (en) * | 2019-07-04 | 2019-11-12 | 深圳市大拿科技有限公司 | A kind of mobile phone remote image capture method and system |
| CN110751086A (en) * | 2019-10-17 | 2020-02-04 | 北京字节跳动网络技术有限公司 | Target searching method, device, equipment and storage medium based on video |
| CN111476328A (en) * | 2020-04-13 | 2020-07-31 | 黎志瀛 | Image recognition feature code associated target system |
| CN111988481A (en) * | 2019-05-22 | 2020-11-24 | 北京三好互动教育科技有限公司 | Image shooting device, image processing system and image processing method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1885291A (en) * | 2005-06-20 | 2006-12-27 | 三星电子株式会社 | Method and system for providing photographed image-related information to user, and mobile terminal therefor |
| CN101000623A (en) * | 2007-01-08 | 2007-07-18 | 深圳市宜搜科技发展有限公司 | Method for image identification search by mobile phone photographing and device using the method |
| CN101216841A (en) * | 2008-01-14 | 2008-07-09 | 南京搜拍信息技术有限公司 | Interactive type image search system and method |
| CN103577840A (en) * | 2013-10-30 | 2014-02-12 | 汕头大学 | Item identification method |
| CN104765891A (en) * | 2015-05-06 | 2015-07-08 | 苏州搜客信息技术有限公司 | Searching shopping method based on pictures |
-
2016
- 2016-03-17 CN CN201610153430.6A patent/CN105824928A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1885291A (en) * | 2005-06-20 | 2006-12-27 | 三星电子株式会社 | Method and system for providing photographed image-related information to user, and mobile terminal therefor |
| CN101000623A (en) * | 2007-01-08 | 2007-07-18 | 深圳市宜搜科技发展有限公司 | Method for image identification search by mobile phone photographing and device using the method |
| CN101216841A (en) * | 2008-01-14 | 2008-07-09 | 南京搜拍信息技术有限公司 | Interactive type image search system and method |
| CN103577840A (en) * | 2013-10-30 | 2014-02-12 | 汕头大学 | Item identification method |
| CN104765891A (en) * | 2015-05-06 | 2015-07-08 | 苏州搜客信息技术有限公司 | Searching shopping method based on pictures |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106649485A (en) * | 2016-09-30 | 2017-05-10 | 广东欧珀移动通信有限公司 | Method for pushing information and mobile terminal |
| CN107948391A (en) * | 2016-10-12 | 2018-04-20 | 吴展兴 | Action electronic device and server |
| CN106777316A (en) * | 2017-01-03 | 2017-05-31 | 深圳皮皮哥网络科技有限公司 | A kind of network leather lines image search method and system |
| CN106933968A (en) * | 2017-02-09 | 2017-07-07 | 北京理工大学 | A kind of related information acquisition methods, terminal, server and system |
| CN107145823A (en) * | 2017-03-29 | 2017-09-08 | 深圳市元征科技股份有限公司 | A kind of image-recognizing method, pattern recognition device and server |
| CN107016368A (en) * | 2017-04-07 | 2017-08-04 | 郑州悉知信息科技股份有限公司 | The information acquisition method and server of a kind of object |
| CN106940807A (en) * | 2017-04-19 | 2017-07-11 | 深圳市元征科技股份有限公司 | A kind of processing method and processing device based on mirror device of looking in the distance |
| CN110020185A (en) * | 2017-12-29 | 2019-07-16 | 国民技术股份有限公司 | Intelligent search method, terminal and server |
| CN108280420A (en) * | 2018-01-19 | 2018-07-13 | 百度在线网络技术（北京）有限公司 | System, method and apparatus for handling image |
| CN108900629A (en) * | 2018-07-25 | 2018-11-27 | 西安艾润物联网技术服务有限责任公司 | A kind of service push method and device |
| CN108900629B (en) * | 2018-07-25 | 2021-11-30 | 西安艾润物联网技术服务有限责任公司 | Service pushing method and device |
| CN111988481A (en) * | 2019-05-22 | 2020-11-24 | 北京三好互动教育科技有限公司 | Image shooting device, image processing system and image processing method |
| CN110445980A (en) * | 2019-07-04 | 2019-11-12 | 深圳市大拿科技有限公司 | A kind of mobile phone remote image capture method and system |
| CN110751086A (en) * | 2019-10-17 | 2020-02-04 | 北京字节跳动网络技术有限公司 | Target searching method, device, equipment and storage medium based on video |
| CN111476328A (en) * | 2020-04-13 | 2020-07-31 | 黎志瀛 | Image recognition feature code associated target system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105824928A (en) | Mobile terminal, server, content-based image recognition searching method and system | |
| US11886489B2 (en) | System and method of identifying visual objects | |
| US7872669B2 (en) | Photo-based mobile deixis system and related techniques | |
| CN100578508C (en) | Interactive type image search system and method | |
| CN102017661B (en) | Data access based on content of image recorded by a mobile device | |
| CN102147815B (en) | Method and system for searching images | |
| CN104765891A (en) | Searching shopping method based on pictures | |
| US20140254942A1 (en) | Systems and methods for obtaining information based on an image | |
| CN105631051A (en) | Character recognition based mobile augmented reality reading method and reading system thereof | |
| CN103353875B (en) | Media interaction method based on visual search and system | |
| CN102317929A (en) | Method and system for image matching | |
| CN103778261A (en) | Self-guided tour method based on mobile cloud computing image recognition | |
| CN102855298A (en) | Image retrieval method and system | |
| TWI651673B (en) | Seraching method for product photograph and searching system for product photograph | |
| CN102214222A (en) | Presorting and interacting system and method for acquiring scene information through mobile phone | |
| CN103428537A (en) | Video processing method and video processing device | |
| CN103106252A (en) | Method for using handheld device to position plane area | |
| CN104392007A (en) | Streetscape retrieval and identification method of intelligent mobile terminal | |
| CN103514447A (en) | Face recognition system based on smart phone | |
| CN110309810A (en) | A kind of pedestrian's recognition methods again based on batch center similarity | |
| CN107679128B (en) | Information display method and device, electronic equipment and storage medium | |
| CN106250396B (en) | Automatic image label generation system and method | |
| CN103530377A (en) | Scene information searching method based on binary feature codes | |
| He et al. | Garment image retrieval on the web with ubiquitous camera-phone | |
| EP2849093A1 (en) | Method of displaying data associated with an image of an object, and corresponding device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160803 |
|
| RJ01 | Rejection of invention patent application after publication |