CN110489594A - Image vision mask method, device, storage medium and equipment - Google Patents
Image vision mask method, device, storage medium and equipment Download PDFInfo
- Publication number
- CN110489594A CN110489594A CN201810459734.4A CN201810459734A CN110489594A CN 110489594 A CN110489594 A CN 110489594A CN 201810459734 A CN201810459734 A CN 201810459734A CN 110489594 A CN110489594 A CN 110489594A
- Authority
- CN
- China
- Prior art keywords
- vision
- image
- field
- description vectors
- mark
- 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 disclosure provides a kind of image vision mask method, device, storage medium and equipment, retrieves the reduction of image efficiency in the related technology to solve the problems, such as.Disclosed image vision mask method, comprising: extract the vision description vectors information of image to be marked；The corresponding vision mark field of described image is obtained according to the vision description vectors information；Described image is presented according to vision mark field classification.The scheme of the disclosure allows users to conveniently and efficiently retrieve interested visual document, improves recall precision.
Description
Technical field
This disclosure relates to field of computer technology, and in particular, to a kind of image vision mask method, device, storage are situated between
Matter and equipment.
Background technique
Currently, mobile device generally uses shooting time or location information, such as GPS (Global Positioning
System, global positioning system) location information is labeled the obtained video/image of shooting.When user is in mobile device
In when checking video/image, the time or location information that can mark according to file classify/or sort.According to the time pair
In the case that video/image is classified or sorted, user may be selected to press different time granularities, for example, day, the moon or year, right
Image/video carries out classification and checks；In the case where classifying according to position to video/image, user be may be selected according to not
Classification is carried out to image/video with place to check.
But in actual use of the user to mobile device, when browsing to video/image, the retrieval behavior of user is past
Toward being to be driven to lead with content, for example, user wishes to check the video/image etc. of the flower of the cat comprising family or park.But
Video/image can not be carried out effectively polymerization classification, the video/image quantity in mobile device according to content by current mobile device
Be continuously increased in the case where, it will cause the efficiency of its content of interest of user search lower, seriously affect user experience.
Summary of the invention
Purpose of this disclosure is to provide a kind of image vision mask method, device, storage medium and equipment, to solve phase
The problem of image efficiency reduces is retrieved in the technology of pass.
According to the first aspect of the disclosure, a kind of image vision mask method is provided, comprising: extract image to be marked
Vision description vectors information；The corresponding vision mark field of described image is obtained according to the vision description vectors information；It presses
Described image is presented according to vision mark field classification.
Optionally, described that the corresponding vision mark field of described image, packet are obtained according to the vision description vectors information
It includes: the vision description vectors information being sent to server end, wherein be stored with vision in the database of the server end
Description vectors and vision markup information corresponding with vision description vectors；It is sending with the vision to receive the server end
The corresponding vision markup information of description vectors；The vision, which is generated, based on the vision markup information marks field.
Optionally, the method also includes: after getting described image corresponding vision mark field, by the mark
Infuse the corresponding extended field of field write-in described image.
Optionally, the image to be marked includes single-frame static images and/or multi-frame video image, described by the mark
The corresponding extended field of described image is written in field, comprising: for the single-frame static images, vision mark field is write
Enter the image head extended field of the first compressed bit stream, wherein first compressed bit stream is obtained by compressing the single-frame static images
It arrives；For the multi-frame video image, the index of the visual object in the second compressed bit stream and the vision are marked into field
Video sequence head extended field is written, frame head extended field is written into the index of the visual object after coding, wherein described second
Compressed bit stream is obtained by compressing the multi-frame video image.
Optionally, described that described image is presented according to vision mark field classification, comprising: according to the mark of described image
Note field classifies to described image, obtains multiple images classification, and the corresponding visual tag of each image classification is presented,
In, the visual tag is obtained according to the mark field of the image in image classification.
According to the second aspect of the disclosure, a kind of image vision annotation equipment is provided, comprising: extraction module, for mentioning
Take the vision description vectors information of image to be marked；Module is obtained, it is described for being obtained according to the vision description vectors information
The corresponding vision of image marks field；Module is presented, for described image to be presented according to vision mark field classification.
Optionally, the acquisition module, comprising: transmission unit, for the vision description vectors information to be sent to clothes
It is engaged in device end, wherein vision description vectors and corresponding with vision description vectors are stored in the database of the server end
Vision markup information；Receiving unit, the vision corresponding with the vision description vectors sent for receiving the server end
Markup information；Generation unit marks field for generating the vision based on the vision markup information.
Optionally, described device further include: writing module, for getting the corresponding vision mark field of described image
Later, by the corresponding extended field of mark field write-in described image.
Optionally, the image to be marked includes single-frame static images and/or multi-frame video image, write module packet
It includes: the first writing unit, for for the single-frame static images, the first compressed bit stream to be written in vision mark field
Image head extended field, wherein first compressed bit stream is obtained by compressing the single-frame static images；Second writing unit,
For for the multi-frame video image, the index of the visual object in the second compressed bit stream and the vision to be marked field
Video sequence head extended field is written, frame head extended field is written into the index of the visual object after coding, wherein described second
Compressed bit stream is obtained by compressing the multi-frame video image.
Optionally, the presentation module is used for: being classified according to the mark field of described image to described image, is obtained
Multiple images classification, and the corresponding visual tag of each image classification is presented, wherein the visual tag is according in image classification
The mark field of image obtains.
In terms of according to the third of the disclosure, a kind of computer readable storage medium is provided, computer is stored thereon with
Program realizes any one image vision mask method described in the disclosure first aspect when program is executed by processor
Step.
According to the 4th of the disclosure the aspect, a kind of electronic equipment is provided, comprising: memory is stored thereon with calculating
Machine program；And one or more processor realizes disclosure first aspect for executing the program in the memory
Any one described image vision mask method.
Other feature and advantage of the disclosure will the following detailed description will be given in the detailed implementation section.
The scheme of the embodiment of the present disclosure, the vision description vectors information based on image carry out vision to video or image file
Mark, knows the vision main points in image convenient for user, so that user can conveniently and efficiently retrieve interested view
Feel file, improves recall precision.
Detailed description of the invention
Attached drawing is and to constitute part of specification for providing further understanding of the disclosure, with following tool
Body embodiment is used to explain the disclosure together, but does not constitute the limitation to the disclosure.In the accompanying drawings:
Fig. 1 is the flow chart of the image vision mask method of the embodiment of the present disclosure one.
Fig. 2 is the block diagram of the image vision annotation equipment of the embodiment of the present disclosure three.
Fig. 3 is the block diagram of the electronic equipment of the embodiment of the present disclosure four.
Specific embodiment
It is described in detail below in conjunction with specific embodiment of the attached drawing to the disclosure.It should be understood that this place is retouched
The specific embodiment stated is only used for describing and explaining the disclosure, is not limited to the disclosure.
Embodiment one
A kind of image vision mask method is present embodiments provided, Fig. 1 is the flow chart of this method, as shown in Figure 1, the party
Method includes:
Step 101: extracting the vision description vectors information of image to be marked；
Wherein, vision description vectors information includes unique various dimensions digital vectors, which is area image
Information, a kind of abstracted information including pixel gradient amplitude and direction etc. have invariance and uniqueness.
Step 102: the corresponding vision of image being obtained according to vision description vectors information and marks field；
Step 103: image is presented according to vision mark field classification.
In a kind of achievable mode, the step of extracting the vision description vectors information of image to be marked, can be by terminal
Interior visual information abstracting module carries out, exemplary, when terminal carries out image and/or video acquisition, by acquired image
And/or video frame information is sent into visual information abstracting module, and DSP (Digital Signal can be used for example
Processing, Digital Signal Processing), GPU (Graphics Processing Unit, graphics processor abbreviation) or dedicated plus
Fast device is as visual information abstracting module.Visual information abstracting module will be according to Visual Feature Retrieval Process algorithm (such as CNN of definition
(Convolutional Neural Networks, convolutional neural networks, SIFT (Scale-invariant feature
Transform, Scale invariant features transform), ORB (Oriented FAST and Rotated BRIEF) and MPEG
CDVS the vision description vectors information of object in correspondence image and/or video frame) is generated.
In a kind of achievable mode, the corresponding vision of image is obtained according to vision description vectors information and marks field, packet
It includes: vision description vectors information being sent to server end, wherein be stored with vision description vectors in the database of server end
And vision markup information corresponding with vision description vectors；Receive the view corresponding with vision description vectors that server end is sent
Feel markup information；View-based access control model markup information generates vision and marks field.It is exemplary, to obtain visual tag, terminal and service
The information interactive process that device end carries out includes: that the vision description vectors of extraction are sent to server-side by network and mark by terminal
Information inquiry is infused, server end is retrieved in storage vision description vectors and the database of corresponding vision markization information
The corresponding vision of vision description vectors marks and is back to terminal.Terminal generates the view according to the markup information that server-side returns
Feel the mark field of object.
In a kind of achievable mode, the image vision mask method of the disclosure further include: corresponding getting image
After vision marks field, by the corresponding extended field of mark field write-in described image.
In a kind of achievable mode, image to be marked includes single-frame static images and/or multi-frame video image, is based on
This, by the corresponding extended field of mark field write-in image, comprising: the image and/or video of terminal acquisition are compressed, it is raw
At compressed bit stream；For single-frame static images, vision mark field is written to the image head extended field of the first compressed bit stream,
In, the first compressed bit stream is obtained by compression single-frame static images；For multi-frame video image, by the vision in the second compressed bit stream
Video sequence head extended field is written in the index and mark field of object, and frame head is written in the index of the visual object after coding
Extended field, wherein the second compressed bit stream is obtained by compression multi-frame video image.It should be noted that the second compressed bit stream
In visual object the operation that is encoded of index, can be executed before obtaining vision mark field, can also be and obtaining
It obtains vision mark field to execute later, field can also be marked with acquisition vision and be performed simultaneously, the disclosure is to this without limiting.
In the case where only increasing a small amount of additional encoded information, so that the corresponding mark field that image/video file obtains, and by visual object
Video sequence head extended field is written in index and corresponding vision markup information, and the object indexing write-in frame head after coding is extended word
The operation of section can reduce additional bit consumption.
In a kind of achievable mode, the step of image is presented in field classification is marked according to vision, comprising: according to image
Mark field classifies to image, obtains multiple images classification, and the corresponding visual tag of each image classification is presented, wherein
Visual tag is obtained according to the mark field of the image in image classification.It is exemplary, pass through the figure of terminal browsing storage in user
As or when video information, terminal by according to the vision markup information of compressed file head according to set visual tag exhibiting pictures,
User can be according to the corresponding classification of content selection of its concern, and browses the picture under corresponding classification.Belong to different labeled field
File can be classified displaying, and system can automatically generate picture or video according to vision markup information when such as user's Album for glancing over pictures
Classification folder (corresponding mark field such as personage, plant, animal of file etc.).
It include the first classification and the second classification in a kind of achievable mode, in above-mentioned image classification, second is classified as
The corresponding subclassification of an element in first classification, for example, the first classification includes portrait, scene, plant, pet, building, vapour
Vehicle and cuisines, it is therein it is each classification can also continue to include subclassification, for example, under plant classification can also including flower with
And trees etc..In addition, subclassification can also classify according to time and geographical location.
The image vision mask method of the present embodiment, the vision description vectors information based on image is to video or image file
Vision mark is carried out, the vision main points in image are known convenient for user, so that user can conveniently and efficiently retrieve sense
The visual document of interest, improves recall precision.
Embodiment two
A kind of image vision mask method is present embodiments provided, this method mainly includes vision description, vision mark, figure
As compression and four treatment processes of vision sorter:
Vision description processing include:
Image or video frame information are sent into visual information abstracting module when terminal acquires image or video.Visual information mentions
Modulus block believes the vision description vectors that object in correspondence image or video frame is generated according to the Visual Feature Retrieval Process algorithm of definition
Breath.
Vision mark processing include:
The vision description vectors of extraction are sent to server-side by network and inquire corresponding markup information, server end exists
The corresponding vision of vision description vectors is retrieved in visual information data library to mark and be back to terminal.
Terminal generates the mark field of the visual object according to the markup information that server-side returns.
The processing of compression of images includes:
The image or video of acquisition are compressed, compressed bit stream is generated.
For single-frame static images, the image head of the vision mark field write-in compressed bit stream of generation is directly extended into word
Section.For multi-frame video, visual objects all in video index is encoded, visual object is indexed and corresponding vision marks
Video sequence head extended field is written in information, and frame head extended field is written in the object indexing after coding, additional to reduce
Bit consumption.
The processing of vision sorter includes:
In image or video file of the user by terminal browsing storage, terminal will be according to the vision mark of compressed file head
It infuses information and shows file according to set visual tag, user can select the file under corresponding classification according to attentinal contents.
The image vision mask method of the present embodiment, the vision description vectors information based on image or video frame object, base
It inquires corresponding vision in server end in vision description vectors information to mark to terminal, terminal is marked using the vision to video
Or image file carries out vision mark, carries out more complicated operation without terminal again, can conveniently and efficiently to image/
The vision of video frame object marks, and reduces power consumption of terminal, and improves the treatment effeciency of vision mark.
Embodiment three
The present embodiment additionally provides a kind of image vision annotation equipment, device image vision mark used to implement the present disclosure
Injecting method, Fig. 2 are the block diagrams of image vision annotation equipment, as shown in Fig. 2, the device 20 includes following component part:
Extraction module 21, for extracting the vision description vectors information of image to be marked；
Module 22 is obtained, marks field for obtaining the corresponding vision of image according to vision description vectors information；
Module 23 is presented, for image to be presented according to vision mark field classification.
In a kind of achievable mode, obtaining module 21 includes: transmission unit, and the unit is for believing vision description vectors
Breath be sent to server end, wherein be stored in the database of server end vision description vectors and with vision description vectors
Corresponding vision markup information；Receiving unit, the unit are used to receive the corresponding with vision description vectors of server end transmission
Vision markup information；Generation unit, the unit generate vision for view-based access control model markup information and mark field.
In a kind of achievable mode, the image vision annotation equipment of the disclosure further include: writing module, for obtaining
To after the corresponding vision mark field of image, by the corresponding extended field of mark field write-in image.
In a kind of achievable mode, image to be marked includes single-frame static images and/or multi-frame video image, is based on
This, writing module includes: the first writing unit, for for single-frame static images, vision mark field write-in first to be compressed
The image head extended field of code stream, wherein the first compressed bit stream is obtained by compression single-frame static images；Second writing unit is used
In for multi-frame video image, video sequence is written into the index of the visual object in the second compressed bit stream and vision mark field
Frame head extended field is written, wherein the second compressed bit stream is by compressing in the index of visual object after coding by column head extended field
Multi-frame video image obtains.It should be noted that the operation that the index of the visual object in the second compressed bit stream is encoded,
Can obtain vision mark field before execute, can also be obtain vision mark field after execute, can also with obtain
It obtains vision mark field to be performed simultaneously, the disclosure is to this without limiting.
In a kind of achievable mode, module 23 is presented and is used for: classifying according to the mark field of image to image, obtains
Classify to multiple images, and the corresponding visual tag of each image classification is presented, wherein visual tag is according to the figure in image classification
The mark field of picture obtains.It include that the first classification and second are classified in image classification in the achievable mode of another kind, second
The corresponding subclassification of an element being classified as in the first classification.
The image vision annotation equipment of the present embodiment, the vision description vectors information based on image is to video or image file
Vision mark is carried out, the vision main points in image are known convenient for user, so that user can conveniently and efficiently retrieve sense
The visual document of interest, improves recall precision.
Example IV
A kind of electronic equipment is present embodiments provided, which may be provided as a kind of image vision mark dress
It setting, Fig. 3 is the block diagram of the electronic equipment, as shown in figure 3, the electronic equipment 300 may include: processor 301, memory 302,
Multimedia component 303, input/output (I/O) interface 304 and communication component 305.
Wherein, processor 301 is used to control the integrated operation of the electronic equipment 300, to complete above-mentioned image vision mark
All or part of the steps in dispensing device.Memory 302 is for storing various types of data to support in the electronic equipment 300
Operation, these data for example may include the finger of any application or method for operating on the electronic equipment 300
Order and the relevant data of application program, for example, the data of storage may include video, image, vision description vectors information
Extraction algorithm and the mark field of image/video frame etc..Based on this, processor 301 can use the vision in memory and retouch
Vector information is stated to execute above-mentioned steps 101, which can be set by any kind of volatibility or non-volatile memories
Standby or their combination is realized, such as static random access memory (Static Random Access Memory, abbreviation
SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only
Memory, abbreviation EEPROM), Erasable Programmable Read Only Memory EPROM (Erasable Programmable Read-Only
Memory, abbreviation EPROM), programmable read only memory (Programmable Read-Only Memory, abbreviation PROM), only
It reads memory (Read-Only Memory, abbreviation ROM), magnetic memory, flash memory, disk or CD.Above-mentioned electronics is set
Vision description vectors information can be sent to server end by communication component 305 by standby 300, and is received server end and returned
Vision mark field.Wherein, be stored in the database of server end vision description vectors and with vision description vectors pair
The vision markup information answered inquires corresponding vision markup information according to vision description vectors to be executed by server end
Operation.In addition, also can store in the storage 302 of above-mentioned electronic equipment vision description vectors and with vision description vectors pair
The vision markup information answered is inquired so as to be executed by the processor of terminal device 300 according to vision description vectors information
The operation of corresponding vision markup information.Multimedia component can be used to shoot video/photo, which may include
Can image be presented according to vision mark field classification on the screen in screen and audio component, and wherein screen for example can be touching
Screen is touched, when user checks image by touch screen selection, can show the corresponding mark field of the picture on the screen.
Audio component is used for output and/or input audio signal.For example, audio component may include a microphone, microphone is used for
Receive external audio signal.The received audio signal can be further stored in memory 302 or by communication component 304
It sends.Audio component further includes at least one loudspeaker, is used for output audio signal.I/O interface 303 is processor 301 and its
Interface is provided between his interface module, other above-mentioned interface modules can be keyboard, mouse, button etc..These buttons can be
Virtual push button or entity button.Communication component 304 is wired or wireless for carrying out between the electronic equipment 300 and other equipment
Communication.Wireless communication, such as Wi-Fi, bluetooth, near-field communication (Near Field Communication, abbreviation NFC), 2G, 3G
4G or they one or more of combination, therefore the corresponding communication component 304 may include: Wi-Fi module, blue
Tooth module, NFC module.
It should be noted that the function of above-mentioned writing module can also be performed in above-mentioned processor 301, and combine screen real
The function of existing above-mentioned presentation module, due to writing module function and the function of module hereinbefore by the agency of mistake is presented,
Therefore details are not described herein again.
In a kind of achievable mode, electronic equipment 300 can be by one or more application specific integrated circuit
(Application Specific Integrated Circuit, abbreviation ASIC), digital signal processor (Digital
Signal Processor, abbreviation DSP), digital signal processing appts (Digital Signal Processing Device,
Abbreviation DSPD), programmable logic device (Programmable Logic Device, abbreviation PLD), field programmable gate array
(Field Programmable Gate Array, abbreviation FPGA), controller, microcontroller, microprocessor or other electronics member
Part is realized, for executing above-mentioned image vision mask method.
The electronic equipment of the present embodiment can be described locally or through server inquiry and the vision of image/video frame
The corresponding vision of vector information marks field, to be labeled to image/video frame, facilitates user's access.
The present embodiment additionally provides a kind of computer readable storage medium, is stored with computer program in the storage medium,
Any one image vision mask method that the above embodiments of the present application provide is realized when the program is executed by processor.
The preferred embodiment of the disclosure is described in detail in conjunction with attached drawing above, still, the disclosure is not limited to above-mentioned reality
The detail in mode is applied, in the range of the technology design of the disclosure, a variety of letters can be carried out to the technical solution of the disclosure
Monotropic type, these simple variants belong to the protection scope of the disclosure.
It is further to note that specific technical features described in the above specific embodiments, in not lance
In the case where shield, it can be combined in any appropriate way.In order to avoid unnecessary repetition, the disclosure to it is various can
No further explanation will be given for the combination of energy.
In addition, any combination can also be carried out between a variety of different embodiments of the disclosure, as long as it is without prejudice to originally
Disclosed thought equally should be considered as disclosure disclosure of that.
Claims (12)
1. a kind of image vision mask method characterized by comprising
Extract the vision description vectors information of image to be marked；
The corresponding vision mark field of described image is obtained according to the vision description vectors information；
Described image is presented according to vision mark field classification.
2. the method according to claim 1, wherein it is described obtained according to the vision description vectors information it is described
The corresponding vision of image marks field, comprising:
The vision description vectors information is sent to server end, wherein view is stored in the database of the server end
Feel description vectors and vision markup information corresponding with vision description vectors；
Receive the vision markup information corresponding with the vision description vectors that the server end is sent；
The vision, which is generated, based on the vision markup information marks field.
3. the method according to claim 1, wherein the method also includes:
After getting the corresponding vision mark field of described image, by the corresponding expansion of mark field write-in described image
Open up field.
4. according to the method described in claim 3, it is characterized in that, the image to be marked include single-frame static images and/or
Multi-frame video image, it is described by the corresponding extended field of mark field write-in described image, comprising:
For the single-frame static images, vision mark field is written to the image head extended field of the first compressed bit stream,
Wherein, first compressed bit stream is obtained by compressing the single-frame static images；
For the multi-frame video image, the index of the visual object in the second compressed bit stream and the vision are marked into field
Video sequence head extended field is written, frame head extended field is written into the index of the visual object after coding, wherein described second
Compressed bit stream is obtained by compressing the multi-frame video image.
5. the method according to claim 1, which is characterized in that described to mark field according to the vision
Described image is presented in classification, comprising:
Classify according to the mark field of described image to described image, obtains multiple images classification, and each image point is presented
The corresponding visual tag of class, wherein the visual tag is obtained according to the mark field of the image in image classification.
6. a kind of image vision annotation equipment characterized by comprising
Extraction module, for extracting the vision description vectors information of image to be marked；
Module is obtained, marks field for obtaining the corresponding vision of described image according to the vision description vectors information；
Module is presented, for described image to be presented according to vision mark field classification.
7. device according to claim 6, which is characterized in that the acquisition module, comprising:
Transmission unit, for the vision description vectors information to be sent to server end, wherein the data of the server end
Vision description vectors and vision markup information corresponding with vision description vectors are stored in library；
Receiving unit, the vision markup information corresponding with the vision description vectors sent for receiving the server end；
Generation unit marks field for generating the vision based on the vision markup information.
8. device according to claim 6, which is characterized in that described device further include:
Writing module, for after getting the corresponding vision mark field of described image, institute to be written in the mark field
State the corresponding extended field of image.
9. device according to claim 8, which is characterized in that the image to be marked include single-frame static images and/or
Multi-frame video image, the write module are used for:
First writing unit, for for the single-frame static images, the first compressed bit stream to be written in vision mark field
Image head extended field, wherein first compressed bit stream is obtained by compressing the single-frame static images；
Second writing unit, for for the multi-frame video image, by the index of the visual object in the second compressed bit stream with
And video sequence head extended field is written in the vision mark field, by the index write-in frame head extension of the visual object after coding
Field, wherein second compressed bit stream is obtained by compressing the multi-frame video image.
10. according to device described in claim 6 to 9 any one, which is characterized in that the presentation module is used for:
Classify according to the mark field of described image to described image, obtains multiple images classification, and each image point is presented
The corresponding visual tag of class, wherein the visual tag is obtained according to the mark field of the image in image classification.
11. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
The step of claim 1 to 5 any one the method is realized when execution.
12. a kind of electronic equipment characterized by comprising
Memory is stored thereon with computer program；
And one or more processor realizes that claim 1 to 5 is any one for executing the program in the memory
Item the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810459734.4A CN110489594A (en) | 2018-05-14 | 2018-05-14 | Image vision mask method, device, storage medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810459734.4A CN110489594A (en) | 2018-05-14 | 2018-05-14 | Image vision mask method, device, storage medium and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110489594A true CN110489594A (en) | 2019-11-22 |
Family
ID=68545194
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810459734.4A Pending CN110489594A (en) | 2018-05-14 | 2018-05-14 | Image vision mask method, device, storage medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110489594A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103207870A (en) * | 2012-01-17 | 2013-07-17 | 华为技术有限公司 | Method, server, device and system for photo sort management |
| CN104361357A (en) * | 2014-11-07 | 2015-02-18 | 北京途迹科技有限公司 | Photo set classification system and method based on picture content analysis |
| WO2015032670A1 (en) * | 2013-09-06 | 2015-03-12 | Thomson Licensing | Method of classification of images and corresponding device |
| CN105701502A (en) * | 2016-01-06 | 2016-06-22 | 福州大学 | Image automatic marking method based on Monte Carlo data balance |
| US20170083545A1 (en) * | 2015-09-18 | 2017-03-23 | Fujifilm Corporation | Image extraction system, image extraction method, image extraction program, and recording medium storing program |
| CN106933966A (en) * | 2017-02-08 | 2017-07-07 | 捷开通讯(深圳)有限公司 | Photo sort management, device and its mobile terminal |
| CN107766571A (en) * | 2017-11-08 | 2018-03-06 | 北京大学 | The search method and device of a kind of multimedia resource |
| CN107818180A (en) * | 2017-11-27 | 2018-03-20 | 北京小米移动软件有限公司 | Video correlating method, image display method, device and storage medium |
| CN107944503A (en) * | 2017-12-13 | 2018-04-20 | 北京数洋智慧科技有限公司 | A kind of Urban Data acquisition method and system based on image recognition |
-
2018
- 2018-05-14 CN CN201810459734.4A patent/CN110489594A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103207870A (en) * | 2012-01-17 | 2013-07-17 | 华为技术有限公司 | Method, server, device and system for photo sort management |
| WO2015032670A1 (en) * | 2013-09-06 | 2015-03-12 | Thomson Licensing | Method of classification of images and corresponding device |
| CN104361357A (en) * | 2014-11-07 | 2015-02-18 | 北京途迹科技有限公司 | Photo set classification system and method based on picture content analysis |
| US20170083545A1 (en) * | 2015-09-18 | 2017-03-23 | Fujifilm Corporation | Image extraction system, image extraction method, image extraction program, and recording medium storing program |
| CN105701502A (en) * | 2016-01-06 | 2016-06-22 | 福州大学 | Image automatic marking method based on Monte Carlo data balance |
| CN106933966A (en) * | 2017-02-08 | 2017-07-07 | 捷开通讯(深圳)有限公司 | Photo sort management, device and its mobile terminal |
| CN107766571A (en) * | 2017-11-08 | 2018-03-06 | 北京大学 | The search method and device of a kind of multimedia resource |
| CN107818180A (en) * | 2017-11-27 | 2018-03-20 | 北京小米移动软件有限公司 | Video correlating method, image display method, device and storage medium |
| CN107944503A (en) * | 2017-12-13 | 2018-04-20 | 北京数洋智慧科技有限公司 | A kind of Urban Data acquisition method and system based on image recognition |
Non-Patent Citations (1)
| Title |
|---|
| 杜根远: "《空间数据检索及快速处理技术研究》", 31 October 2015 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10846324B2 (en) | Device, method, and user interface for managing and interacting with media content | |
| US11023666B2 (en) | Narrative-based media organizing system for transforming and merging graphical representations of digital media within a work area | |
| US8145256B2 (en) | System, method and mobile unit to sense objects or text and retrieve related information | |
| CN103369049B (en) | Mobile terminal and server exchange method and system thereof | |
| WO2017087568A1 (en) | A digital image capturing device system and method | |
| EP2405349A1 (en) | Apparatus and method for providing augmented reality through generation of a virtual marker | |
| US20130120430A1 (en) | Electronic device and text reading guide method thereof | |
| KR20060026924A (en) | Tagging method and system for digital data | |
| KR101140419B1 (en) | Mobile phone display capturing method | |
| CN101751404A (en) | Classification method of multimedia files | |
| CN106980696A (en) | The sorting technique and device of a kind of photo files | |
| Quack et al. | Object recognition for the internet of things | |
| CN109522405A (en) | File information processing method, electronic equipment and computer-readable deposit medium | |
| CN111371999A (en) | Image management method, device, terminal and storage medium | |
| CN105631461A (en) | Image recognition system and method | |
| WO2024088291A1 (en) | Form filling method and apparatus, electronic device, and medium | |
| CN105743771A (en) | Photo sharing method, photo sharing device and electronic equipment | |
| CN109492170A (en) | Information-pushing method and Related product | |
| CN109710144A (en) | Notes page processing method, computer equipment and the storage medium of notebook | |
| KR101307325B1 (en) | System for dual-searching image using region of interest set | |
| CN112200844A (en) | Method, device, electronic equipment and medium for generating image | |
| US10552515B2 (en) | Information processing terminal and information processing method capable of supplying a user with information useful for selecting link information | |
| CN105183829A (en) | Picture classification method and device | |
| CN108353210B (en) | Processing method and terminal | |
| CN113867875A (en) | Method, device, equipment and storage medium for editing and displaying marked object |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 100085 unit C, building C, lin66, Zhufang Road, Qinghe, Haidian District, Beijing Applicant after: Beijing Xiaomi pinecone Electronic Co., Ltd Address before: 100085 Beijing city Haidian District Qinghe Shun Yip things Park Building 3 unit A Applicant before: BEIJING PINECONE ELECTRONICS Co.,Ltd. |
|
| CB02 | Change of applicant information |