CN107180039A - A kind of text information recognition methods and device based on picture - Google Patents
A kind of text information recognition methods and device based on picture Download PDFInfo
- Publication number
- CN107180039A CN107180039A CN201610133793.3A CN201610133793A CN107180039A CN 107180039 A CN107180039 A CN 107180039A CN 201610133793 A CN201610133793 A CN 201610133793A CN 107180039 A CN107180039 A CN 107180039A
- Authority
- CN
- China
- Prior art keywords
- picture
- text information
- identification
- web interface
- search key
- 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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/957—Browsing optimisation, e.g. caching or content distillation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/48—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Multimedia (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The embodiment of the invention discloses a kind of text information recognition methods based on picture and device, methods described is applied to browser plug-in, including：Receive the search key of user's input；Text information identification is carried out to each picture in web interface, the text information that each picture is included is obtained；The text information that search key is included with each picture is compared, it is determined that the first picture belonging to the text information matched with search key；Show the text information that the first picture is included., can picture is included in ONLINE RECOGNITION web interface text information, simple operation using the embodiment of the present invention.
Description
Technical field
The present invention relates to Internet technical field, more particularly to a kind of text information recognition methods based on picture
And device.
Background technology
At present, for some web developers and publisher, to accelerate Homepage Publishing and avoiding browser-safe
The problems such as property, usually the text information of issue is placed directly in picture.User can not be directly viewable picture institute
Comprising text information, it is necessary to which the picture in webpage is saved in locally, then is parsed by third-party picture
Instrument carries out text information identification to picture, obtains the text information that picture is included, cumbersome, word
The recognition efficiency of information is relatively low.
The content of the invention
Technical problem to be solved of the embodiment of the present invention is that there is provided a kind of text information knowledge based on picture
Other method and device, can picture is included in ONLINE RECOGNITION web interface text information, simple operation.
In order to solve the above-mentioned technical problem, the embodiments of the invention provide a kind of text information knowledge based on picture
Other method, methods described is applied to browser plug-in, including：
Receive the search key of user's input；
Text information identification is carried out to each picture in web interface, obtains what each described picture was included
Text information；
The text information that the search key is included with picture each described is compared, it is determined that and institute
State the first picture belonging to the text information of search key matching；
Show the text information that first picture is included.
Correspondingly, the embodiment of the present invention additionally provides a kind of text information identifying device based on picture, including：
Keyword receiving unit, the search key for receiving user's input；
Text information acquiring unit, for carrying out text information identification to each picture in web interface, is obtained
The text information included to picture each described；
Comparing unit, the text information for the search key and each described picture to be included is carried out
Compare, it is determined that the first picture belonging to the text information matched with the search key；
Word-information display unit, for showing the text information that first picture is included.
Implement the embodiment of the present invention, by receiving the search key that user inputs, to each in web interface
Individual picture carries out text information identification, obtains the text information that each picture is included, by search key with
The text information that each picture is included is compared, it is determined that belonging to the text information matched with search key
The first picture, the text information that is included of the first picture of display can picture institute in ONLINE RECOGNITION web interface
Comprising text information, simple operation.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to implementing
The accompanying drawing used required in example or description of the prior art is briefly described, it should be apparent that, describe below
In accompanying drawing be only some embodiments of the present invention, for those of ordinary skill in the art, do not paying
On the premise of going out creative work, other accompanying drawings can also be obtained according to these accompanying drawings；
Fig. 1 is a kind of structural representation of the terminal provided in the embodiment of the present invention；
Fig. 2 is a kind of structural representation of the terminal provided in another embodiment of the present invention；
Fig. 3 is that a kind of flow of the text information recognition methods based on picture provided in the embodiment of the present invention is shown
It is intended to；
Fig. 4 is that a kind of structure of the text information identifying device based on picture provided in the embodiment of the present invention is shown
It is intended to；
Fig. 5 is a kind of structural representation of the terminal provided in another embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear
Chu, it is fully described by, it is clear that described embodiment is only a part of embodiment of the invention, rather than
Whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not making creation
Property work under the premise of the every other embodiment that is obtained, belong to the scope of protection of the invention.
The above-mentioned text information recognition methods based on picture may operate in tablet personal computer, mobile phone or individual calculus
In the terminals such as machine (Personal Computer, PC), QQ browsers or Google's browser can also be operated in
Etc. in client.
Refer to Fig. 1, Fig. 1 is a kind of structural representation of terminal in the embodiment of the present invention, the terminal can be with
For browser plug-in, the terminal in the embodiment of the present invention can include input module 101, logic control as shown in the figure
Molding block 102, content storage module 103, application programming interface (Application Programming
Interface, API) 104 and output module 105, wherein input module 101 and the He of output module 105
Logic control module 102 is connected, and Logic control module 102 and content storage module 103 are connected, and content is deposited
Module 103 and API104 connections are stored up, wherein：
Input module 101 be used to realizing user and terminal interact and/or information is input in terminal.For example,
Input module 101 can receive the numeral or character information of user's input, be set with producing with user or function
The relevant signal input of control.In the specific embodiment of the invention, input module 101 at least includes touch-control
Panel and/or other human-computer interaction interfaces, such as entity enter key, microphone.
Contact panel, also referred to as touch-screen or touch screen, collect user in touch or close operation thereon
Action.Such as user is on contact panel or close using any suitable objects such as finger, stylus or annex
The operational motion of the position of contact panel, and corresponding attachment means are driven according to formula set in advance.Can
Choosing, contact panel may include both touch detecting apparatus and touch controller.Wherein, touch detection
Device detects the touch operation of user, and the touch operation detected is converted into electric signal, and will be described
Electric signal sends touch controller to；Touch controller receives the electric signal from touch detecting apparatus, and
Contact coordinate is converted into, then gives processor.The touch controller can be sent with reception processing device
Order and execution.Furthermore, it is possible to using resistance-type, condenser type, infrared ray (Infrared) and surface
The polytypes such as sound wave realize contact panel.In the other embodiment of the present invention, the institute of input module 101
The entity enter key of use can include but is not limited to physical keyboard, function key (such as volume control button,
Switch key etc.), trace ball, mouse, the one or more in action bars etc..The input mould of microphone form
Block 101 can collect the voice of user or environment input and convert thereof into electrical signal form, logic control
The executable order of module.
Logic control module 102 is the control centre of terminal, utilizes various interfaces and the whole terminal of connection
Various pieces.
Content storage module 103 can be used for storage software program and data, and content storage module 103 is main
Including program storage area and data storage area, wherein, program storage area can storage program area, at least one
Application program needed for function, such as sound playing program, image player program etc.；Data storage area can
Storage uses created data (such as voice data, phone directory etc.) etc. according to terminal.
Output module 105 includes but is not limited to image output unit and voice output unit.Image output unit
For output character, picture and/or video.Image output unit in the embodiment of the present invention at least includes display
Screen, for example with LCD (Liquid Crystal Display, liquid crystal display), OLED (Organic
Light-Emitting Diode, Organic Light Emitting Diode), Field Emission Display (field emission display,
Abbreviation FED) etc. form come the display screen that configures.Or the image output unit can include reflective display
Device, such as electrophoresis-type (electrophoretic) display, or utilize interference of light modulation tech (Interferometric
Modulation of Light) display.The image output unit can include individual monitor or difference
Multiple displays of size.In the embodiment of the present invention, what above-mentioned input module 101 was used
The display screen that contact panel and output unit 105 are used may be collectively referred to as display.When contact panel detection
To after touch thereon or close gesture operation, Logic control module 102 is sent to determine touch thing
The type of part, subsequent Logic control module 102 is provided accordingly on a display screen according to the type of touch event
Visual output.Although in Fig. 1, input module 101 and output module 105 are as two independent portions
Part realizes input and the output function of terminal, but in some embodiments it is possible to by contact panel with it is aobvious
Display screen is integrated and realizes the input of terminal and output function.For example, the image output unit can show
Show various Graphic User Interfaces (Graphical User Interface, GUI) to be used as virtual controlling component, bag
Include but be not limited to window, scroll bar, icon and scrapbook, so that user is operated by touch control manner.
In a kind of possible implementation, user can input search key by input module 101,
After Logic control module 102 receives and determines the type of event, the identification instruction in the event is sent to
Content memorizer 103, content memorizer 103 determines each picture in web interface according to identification instruction, patrols
Collect control module 102 and call API, and dynamic load and parsing are carried out to each picture by API, to obtain
The text information for taking each picture to be included.Further, Logic control module 102 by search key with
The text information that each picture is included is compared, it is determined that belonging to the text information matched with search key
The first picture, Logic control module 102 by the text information that the first picture is included be sent to content store
Device 103, the text information that content memorizer 103 is included the first picture is shown by output module 105
Show.
In a kind of possible implementation, after web interface of the display of output module 105 comprising picture,
User can patrol by the input pin of input module 101 to needing the identification events of the picture of text information identification
After volume control module 102 receives and determines the type of event, the identification instruction in the event is sent in
Hold memory 103, the picture that text information is recognized the need for content memorizer 103 is carried according to identification instruction
Picture identification information, it is determined that needing the picture that text information is recognized, Logic control module 102 calls API, and
By API to needing the picture that text information is recognized to carry out dynamic load and parsing, word is needed to believe to obtain
The text information that the picture of breath identification is included.
In a kind of possible implementation, after web interface of the display of output module 105 comprising picture,
The event that all pictures in the web interface that currently shows are carried out with text information identification, logic can be generated
After control module 102 receives and determines the type of event, the identification instruction in the event is sent to content
Memory 103, content memorizer 103 instructs the picture identification information of each picture carried according to identification, really
Surely the picture for needing text information to recognize, Logic control module 102 calls API, and by API to needing
The picture of text information identification carries out dynamic load and parsing, to obtain the picture institute for needing text information to recognize
Comprising text information.
Wherein, above-mentioned terminal is included source code is authenticated to be changed, then can by API set into
In terminal, without recognizing that driving carries out text information identification to picture by text information, in order to upgrading or
Person safeguards.Specifically, Logic control module 102 can include background.html files, for indicating
Under html language, background is used to keep background patterns and background color.Content storage module 103
Content script files (content script) can be included, be can be used for by back-stage management page capturing pictures mark
Know the corresponding picture of information.API104 can include text information recognition function, for needing text information
The picture of identification carries out text information identification.
Wherein, picture identification information can be used for the unique mark picture, such as picture name, store path
Or data capacity etc..
It will be appreciated that in the implementation, the function of each functional module of terminal can be according to Fig. 3
Method in embodiment of the method is implemented, can specific corresponding diagram 3 associated description, here is omitted.
Refer to Fig. 2, Fig. 2 is a kind of structural representation of terminal in the embodiment of the present invention, the terminal can be with
For browser plug-in, the terminal in the embodiment of the present invention can include input module 201, logic control as shown in the figure
Molding block 202, content storage module 203, text information identification driving 204 and output module 205, its
Middle input module 201 and output module 205 and Logic control module 202 are connected, Logic control module 202
Connected with content storage module 203, content storage module 203 and text information identification drive 204 and defeated
Go out module 205 to connect, wherein：
In a kind of possible implementation, user can input search key by input module 201,
After Logic control module 202 receives and determines the type of event, the identification instruction in the event is sent to
Content memorizer 203, content memorizer 203 determines each picture in web interface according to identification instruction, defeated
Go out each picture that module 205 determines content memorizer 203 and enter row format to be converted to picture stream, and will
Picture stream is sent to text information identification driving 104, and text information identification driving 204 enters action to each picture
State is loaded and parsed, to obtain the text information that is included of picture for needing text information to recognize, and by word
Information enters row format and is converted to data flow, and data flow is sent into content storage by output module 205
Module 203.Further, the text information that each picture is included is sent to and patrolled by content storage module 203
Collect control module 202, the text information that Logic control module 202 is included search key and each picture
It is compared, it is determined that the first picture belonging to the text information matched with search key, Logic control module
102 text informations for being included the first picture are sent to content memorizer 203, and content memorizer 203 is by
The text information that one picture is included is shown by output module 205.
In a kind of possible implementation, after web interface of the display of output module 205 comprising picture,
User can patrol by the input pin of input module 201 to needing the identification events of the picture of text information identification
After volume control module 202 receives and determines the type of event, the identification instruction in the event is sent in
Hold memory 203, the picture that text information is recognized the need for content memorizer 203 is carried according to identification instruction
Picture identification information, it is determined that needing the picture that text information is recognized, output module 205 is to content memorizer 203
The picture of determination enters row format and is converted to picture stream, and picture stream is sent into text information identification driving 204,
204 pairs of pictures for needing text information to recognize of text information identification driving carry out dynamic load and parsing, to obtain
The text information that is included of picture for needing text information to recognize is taken, and text information is entered into row format and is changed
Content storage module 203 is sent to by output module 205 to data flow, and by data flow.
In a kind of possible implementation, output module 205 is shown after web interface, can be generated pair
All pictures in the web interface currently shown carry out the event of text information identification, Logic control module 202
After receiving and determining the type of event, the identification instruction in the event is sent to content memorizer 203, it is interior
Hold the picture identification information that memory 203 instructs each picture carried according to identification, it is determined that needing word to believe
The picture of identification is ceased, the picture that output module 205 is determined to content memorizer 203 enters row format and is converted to
Picture stream, and picture stream is sent to text information identification driving 204, text information identification 204 pairs of need of driving
The picture for wanting text information to recognize carries out dynamic load and parsing, to obtain the picture for needing text information to recognize
Comprising text information, and text information entered into row format be converted to data flow, and data flow is passed through
Output module 205 is sent to content storage module 203.
Wherein, above-mentioned terminal is included source code is authenticated to be changed, then needs to believe by word
Breath identification driving carries out text information identification to picture, to realize that picture is included in ONLINE RECOGNITION web interface
Text information.Specifically, Logic control module 202 can include background.html files, it is used for
Indicate under html language, background is used to keep background patterns and background color.Content storage module
203 can include content script files (content script), can be used for by back-stage management page crawl figure
Picture corresponding to piece identification information.Text information identification driving 204 is used for the figure to needing text information to recognize
Piece carries out text information identification.
It will be appreciated that in the implementation, the function of each functional module of terminal can be according to Fig. 3
Method in embodiment of the method is implemented, can specific corresponding diagram 3 associated description, here is omitted.
Fig. 3 is referred to, Fig. 3 is a kind of text information recognition methods based on picture in the embodiment of the present invention
Schematic flow sheet, methods described be applied to browser plug-in, as shown in the figure in the embodiment of the present invention based on figure
The text information recognition methods of piece can include：
S301, receives the search key of user's input.
Terminal can receive the search key of user's input.Wherein, keyword is exactly user using search
Word or word inputted during engine, can at utmost summarizing the information content to be searched of user, for example
" k " or " intelligence " etc..In the specific implementation, terminal can draw webpage floating window, so that user's input is searched
Rope keyword, when user needs to retrieve the picture comprising specified word information, can be inputted by webpage floating window
Search key.
S302, carries out text information identification to each picture in web interface, obtains each picture and included
Text information.
Terminal is received after the search key of user's input, can obtain all pictures in web interface,
Text information identification is carried out to each above-mentioned picture, the text information that each picture is included is obtained.Wherein,
Webpage is the basic element for constituting website, is the platform of the various website applications of carrying.On the display screen of terminal
The webpage of display can be web interface, web interface be between people and machine (such as computer) transmit and
The medium of information is exchanged, web interface can include word, picture and/or animation etc..Picture can include text
Word information, and user can not be directly viewable the text information that picture is included in the web interface currently shown.
Wherein, web interface can be the web interface currently shown, and optionally, web interface can include website
Comprising all web interfaces, such as main page, sub-pages etc..
In an alternative embodiment, after terminal obtains the text information that each picture is included, it will can recognize
Obtained text information storage arrives local, when receiving the search key of user's input again so as to terminal,
The text information that each picture is included can be locally directly being obtained, without receiving user's input every time
After search key, text information identification all is carried out to the picture in web interface, the embodiment of the present invention can
Improve resource utilization.
S303, the text information that search key is included with each picture is compared, it is determined that with search
The first picture belonging to the text information of keyword match.
The text information that terminal can be included search key with each picture is compared, it is determined that with searching
The first picture belonging to the text information of rope keyword match.If for example, search key be " intelligence ",
Whether terminal may determine that in the text information that each picture is included includes character " intelligence ", if there is bag
The text information of character " intelligence " is included, the picture belonging to the text information can be confirmed as the first figure by terminal
Piece.
In an alternative embodiment, terminal is compared the text information that search key and each picture are included
Compared with if there is no the text information matched with search key, terminal can be by search key and webpage
Each web page contents in interface are compared, it is determined that the web page contents matched with search key, and show
The web page contents.Wherein, web page contents can include text, animation, audio or video etc., in webpage
Face, building or scenery that picture is included etc. can also be included by holding.
In an alternative embodiment, each picture in terminal-pair web interface carries out text information identification, obtains
After the text information that each picture is included, the word that search key and each picture can be included
Information is compared, it is determined that the first picture belonging to the text information matched with search key, and will search
Keyword is compared with each web page contents in web interface, it is determined that the webpage matched with search key
Content.
S304, the text information that the first picture of display is included.
Terminal determined after the first picture belonging to the text information that is matched with search key, can show the
The text information that one picture is included.For example, terminal can be highlighted the word letter that the first picture is included
Breath.And for example, the text information that terminal can be included the first picture is converted to voice, and then passes through Mike
The voice is put in anemochory.And for example, terminal can create suspended frame, show that the first picture is included in suspended frame
Text information, wherein suspended frame can be located at terminal display screen foremost.
Optionally, can after the first picture belonging to text information that terminal determination is matched with search key
The text information included with the first picture of display and/or the first picture.
In an alternative embodiment, terminal can determine to need text information to know in the web interface currently shown
Other picture, carries out text information identification to picture, obtains the text information that picture is included.Implement
In, terminal can show web interface, and determination needs text information to know in the web interface currently shown
Other picture, if the text information that the picture that above-mentioned determination obtains is included is locally stored, terminal can be with
Directly locally obtaining the text information that the picture is included；If locally not storing the figure that above-mentioned determination is obtained
The text information that piece is included, terminal can carry out text information identification to the picture, obtain the picture and wrapped
The text information contained, and then the text information storage that the picture is included is to locally.
In an alternative embodiment, after terminal shows web interface, it can be determined in the web interface all
Picture comprising text information, and using each above-mentioned picture as the picture for needing text information to recognize, to upper
State each picture and carry out text information identification, obtain the text information that each picture is included.
In an alternative embodiment, terminal can receive the word that user submits to the second picture in web interface
Information identification instruction, the picture that second picture is defined as needing text information to recognize.For example, terminal is shown
, can be with when user needs to check the text information that second picture is included in web interface after web interface
Recognize and instruct for second picture inputting word information, for being instructed according to the identification of literary sub-information by second picture
It is defined as the picture for needing text information to recognize.Wherein, user recognizes for second picture inputting word information
Instruction is specifically as follows：User is by mouse by cursor placement in second picture belonging positions, the webpage clicking right side
Key menu is recognized with inputting word information and instructed.Optionally, user knows for second picture inputting word information
Zhi Ling can also not be：User's long-press second picture recognizes instruction, etc. with inputting word information, specifically not
Limited by the embodiment of the present invention.
In an alternative embodiment, terminal can call default API, and the picture is carried out by default API
Text information is recognized, obtains the text information that the picture is included.The embodiment of the present invention need not install word letter
Breath identification driving, can be easy to upgrade or safeguard.
In an alternative embodiment, terminal can enter row format conversion to picture, obtain picture stream, pass through word
Information identification driving carries out text information identification to picture stream, obtains the text information that the picture is included.
In the embodiment of the present invention, the search key of user's input is received, to each picture in web interface
Text information identification is carried out, the text information that each picture is included is obtained, by search key and each figure
The text information that piece is included is compared, it is determined that first belonging to the text information matched with search key
Picture, the text information that is included of the first picture of display picture can be included in ONLINE RECOGNITION web interface
Text information, simple operation.
Refer to Fig. 4, Fig. 4 is a kind of text information identification dress based on picture provided in the embodiment of the present invention
The text information identifying device based on picture in the structural representation put, the embodiment of the present invention can include flat
The terminals such as plate computer, mobile phone or personal computer, can also including browser etc. client, as shown in the figure this
The text information identifying device based on picture in embodiment can at least include keyword receiving unit 401, text
Word information acquisition unit 402, comparing unit 403 and word-information display unit 404, wherein：
Keyword receiving unit 401, the search key for receiving user's input.
Text information acquiring unit 402, for carrying out text information identification to each picture in web interface,
Obtain the text information that each picture is included.
Comparing unit 403, the text information for search key to be included with each picture is compared,
It is determined that the first picture belonging to the text information matched with search key.
Word-information display unit 404, for showing the text information that the first picture is included.
In an alternative embodiment, the text information identifying device based on picture in the embodiment of the present invention can be with
Including：
Picture determine unit 405, for determining to need what text information was recognized in the web interface currently shown
Picture.
Text information acquiring unit 402, is additionally operable to carry out text information identification to picture, obtains picture and included
Text information.
In an alternative embodiment, picture determine unit 401, specifically for：
Receive user and instruction is recognized to the text information that the second picture in web interface is submitted.
The picture that second picture is defined as needing text information to recognize.
In an alternative embodiment, picture recognition unit 402, specifically for：
Default API is called, and text information identification is carried out to each picture by default API, picture is obtained
Comprising text information.
In an alternative embodiment, picture recognition unit 402, specifically for：
Enter row format conversion to each picture, obtain picture stream.
Recognize that driving carries out text information identification to picture stream by text information, obtain the text that picture is included
Word information.
In the embodiment of the present invention, keyword receiving unit 401 receives the search key of user's input, word
Information acquisition unit 402 carries out text information identification to each picture in web interface, obtains each picture
Comprising text information, the text information that comparing unit 403 is included search key and each picture
It is compared, it is determined that the first picture belonging to the text information matched with search key, word-information display
Unit 404 shows the text information that is included of the first picture, picture can be included in ONLINE RECOGNITION web interface
Text information, simple operation.
Refer to Fig. 5, a kind of structural representation for terminal that Fig. 5 provides for another embodiment of the present invention, this hair
The terminal that bright embodiment is provided can be used for implementing the method that the embodiment of the present invention shown in above-mentioned Fig. 3 is realized,
For convenience of description, the part related to the embodiment of the present invention is illustrate only, particular technique details is not disclosed,
It refer to the embodiment of the present invention shown in Fig. 3.
As shown in figure 5, the terminal includes：At least one processor 501, such as CPU, at least one is defeated
Enter device 503, at least one output device 504, memory 505, at least one communication bus 502.Its
In, communication bus 502 is used to realize the connection communication between these components.Wherein, input unit 503 has
Body can be network interface, for being communicated with external network.Wherein, output device 504 specifically can be with
For display screen, for display image.Wherein, memory 505 may include high-speed RAM memory, also may be used
Non-labile memory, for example, at least one magnetic disk storage, specifically for storage binaryzation can also be included
Image.Memory 505 can optionally be located remotely from the storage dress of aforementioned processor 501 comprising at least one
Put.Processor 501 can be with reference to shown in Fig. 4 the background information identifying device based on image.Memory 505
Middle storage batch processing code, and processor 501 calls the program code stored in memory 505, is used for
Perform following operate：
Input unit 503 receives the search key of user's input.
Processor 501 carries out text information identification to each picture in web interface, obtains each picture institute
Comprising text information.
The text information that search key is included with each picture is compared by processor 501, it is determined that with
The first picture belonging to the text information of search key matching.
Output device 504 shows the text information that the first picture is included.
In an alternative embodiment, processor 501 can also carry out following operation：
Processor 501 determines the picture for needing text information to recognize in the web interface currently shown.
Processor 501 carries out text information identification to picture, obtains the text information that picture is included.
In an alternative embodiment, processor 501 determines to need text information in the web interface currently shown
The picture of identification, is specifically as follows：
Input unit 503 receives user and recognizes instruction to the text information that the second picture in web interface is submitted.
The picture that second picture is defined as needing text information to recognize by processor 501.
In an alternative embodiment, processor 501 carries out text information identification to each picture in web interface,
The text information that each picture is included is obtained, is specifically as follows：
Processor 501 calls default API, and carries out text information identification to each picture by default API,
Obtain the text information that picture is included.
In an alternative embodiment, processor 501 carries out text information identification to each picture in web interface,
The text information that each picture is included is obtained, is specifically as follows：
Processor 501 enters row format conversion to each picture, obtains picture stream.
Processor 501 recognizes that driving carries out text information identification to picture stream by text information, obtains picture
Comprising text information.
Specifically, the terminal introduced in the embodiment of the present invention can combine what Fig. 3 was introduced to implement the present invention
Part or all of flow in embodiment of the method.
One of ordinary skill in the art will appreciate that all or part of flow in above-described embodiment method is realized,
It can be by computer program to instruct the hardware of correlation to complete, described program can be stored in computer
In read/write memory medium, the program is upon execution, it may include such as the flow of the embodiment of above-mentioned each method.
Wherein, described storage medium can for magnetic disc, CD, read-only memory (Read-Only Memory,
) or random access memory (Random Access Memory, RAM) etc. ROM.
Above disclosure is only preferred embodiment of present invention, can not limit the present invention's with this certainly
Interest field, therefore the equivalent variations made according to the claims in the present invention, still belong to the scope that the present invention is covered.
Claims (10)
1. a kind of text information recognition methods based on picture, it is characterised in that methods described is applied to browse
Device plug-in unit, methods described includes：
Receive the search key of user's input；
Text information identification is carried out to each picture in web interface, obtains what each described picture was included
Text information；
The text information that the search key is included with picture each described is compared, it is determined that and institute
State the first picture belonging to the text information of search key matching；
Show the text information that first picture is included.
2. method according to claim 1, it is characterised in that methods described also includes：
The picture for needing text information to recognize is determined in the web interface currently shown；
Text information identification is carried out to the picture, the text information that the picture is included is obtained.
3. method according to claim 2, it is characterised in that described in the web interface currently shown
It is determined that the picture that text information is recognized is needed, including：
Receive user and instruction is recognized to the text information that the second picture in the web interface is submitted；
The picture that the second picture is defined as needing text information to recognize.
4. method according to claim 1, it is characterised in that described each picture in web interface
Text information identification is carried out, the text information that each described picture is included is obtained, including：
Default application programming interface is called, and by the default application programming interface to each institute
State picture and carry out text information identification, obtain the text information that the picture is included.
5. method according to claim 1, it is characterised in that described each picture in web interface
Text information identification is carried out, the text information that each described picture is included is obtained, including：
Enter row format conversion to picture each described, obtain picture stream；
Recognize that driving carries out text information identification to the picture stream by text information, obtain the picture institute
Comprising text information.
6. a kind of text information identifying device based on picture, it is characterised in that including：
Keyword receiving unit, the search key for receiving user's input；
Text information acquiring unit, for carrying out text information identification to each picture in web interface, is obtained
The text information included to picture each described；
Comparing unit, the text information for the search key and each described picture to be included is carried out
Compare, it is determined that the first picture belonging to the text information matched with the search key；
Word-information display unit, for showing the text information that first picture is included.
7. device according to claim 6, it is characterised in that described device also includes：
Picture determine unit, for determining the figure for needing text information to recognize in the web interface currently shown
Piece；
The text information acquiring unit, is additionally operable to carry out text information identification to the picture, obtains described
The text information that picture is included.
8. device according to claim 7, it is characterised in that the picture determine unit, specifically for：
Receive user and instruction is recognized to the text information that the second picture in the web interface is submitted；
The picture that the second picture is defined as needing text information to recognize.
9. method according to claim 6, it is characterised in that the picture recognition unit, specifically for：
Default application programming interface is called, and by the default application programming interface to each institute
State picture and carry out text information identification, obtain the text information that the picture is included.
10. device according to claim 6, it is characterised in that the picture recognition unit, specific to use
In：
Enter row format conversion to picture each described, obtain picture stream；
Recognize that driving carries out text information identification to the picture stream by text information, obtain the picture institute
Comprising text information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610133793.3A CN107180039A (en) | 2016-03-09 | 2016-03-09 | A kind of text information recognition methods and device based on picture |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610133793.3A CN107180039A (en) | 2016-03-09 | 2016-03-09 | A kind of text information recognition methods and device based on picture |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107180039A true CN107180039A (en) | 2017-09-19 |
Family
ID=59829693
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610133793.3A Pending CN107180039A (en) | 2016-03-09 | 2016-03-09 | A kind of text information recognition methods and device based on picture |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107180039A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020238938A1 (en) * | 2019-05-29 | 2020-12-03 | 维沃移动通信有限公司 | Information input method and mobile terminal |
| CN112328149A (en) * | 2020-11-11 | 2021-02-05 | 维沃移动通信有限公司 | Picture format setting method and device and electronic equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1612154A (en) * | 2003-10-29 | 2005-05-04 | 株式会社日立制作所 | File searching and reading method and apparatus |
| CN103064839A (en) * | 2011-10-19 | 2013-04-24 | 北京中文在线数字出版股份有限公司 | Portable document format (Pdf) full-text on-line retrieval method |
| CN103246647A (en) * | 2012-02-01 | 2013-08-14 | 腾讯科技（深圳）有限公司 | Character searching method for browser and mobile terminal |
| CN104484387A (en) * | 2014-12-10 | 2015-04-01 | 北京奇虎科技有限公司 | Method for carrying out searching in browser and browser device |
| CN104536973A (en) * | 2014-12-03 | 2015-04-22 | 北京奇虎科技有限公司 | Picture identification method and browser client |
| CN105224611A (en) * | 2015-09-08 | 2016-01-06 | 安一恒通（北京）科技有限公司 | Based on the operation processing method of browser, device and browser |
-
2016
- 2016-03-09 CN CN201610133793.3A patent/CN107180039A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1612154A (en) * | 2003-10-29 | 2005-05-04 | 株式会社日立制作所 | File searching and reading method and apparatus |
| CN103064839A (en) * | 2011-10-19 | 2013-04-24 | 北京中文在线数字出版股份有限公司 | Portable document format (Pdf) full-text on-line retrieval method |
| CN103246647A (en) * | 2012-02-01 | 2013-08-14 | 腾讯科技（深圳）有限公司 | Character searching method for browser and mobile terminal |
| CN104536973A (en) * | 2014-12-03 | 2015-04-22 | 北京奇虎科技有限公司 | Picture identification method and browser client |
| CN104484387A (en) * | 2014-12-10 | 2015-04-01 | 北京奇虎科技有限公司 | Method for carrying out searching in browser and browser device |
| CN105224611A (en) * | 2015-09-08 | 2016-01-06 | 安一恒通（北京）科技有限公司 | Based on the operation processing method of browser, device and browser |
Non-Patent Citations (1)
| Title |
|---|
| 赵颍梅: "《大学图书馆发展与和谐社会构建》", 31 July 2007, 西南交通大学出版社 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020238938A1 (en) * | 2019-05-29 | 2020-12-03 | 维沃移动通信有限公司 | Information input method and mobile terminal |
| CN112328149A (en) * | 2020-11-11 | 2021-02-05 | 维沃移动通信有限公司 | Picture format setting method and device and electronic equipment |
| CN112328149B (en) * | 2020-11-11 | 2022-03-25 | 维沃移动通信有限公司 | Picture format setting method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9152529B2 (en) | Systems and methods for dynamically altering a user interface based on user interface actions | |
| CN102216893B (en) | Touch screen device, method, and graphical user interface for moving on-screen objects without using cursor | |
| US11262895B2 (en) | Screen capturing method and apparatus | |
| WO2019062910A1 (en) | Copy and pasting method, data processing apparatus, and user device | |
| WO2021047230A1 (en) | Method and apparatus for obtaining screenshot information | |
| WO2016090888A1 (en) | Method, apparatus and device for moving icon, and non-volatile computer storage medium | |
| US10339833B2 (en) | Assistive reading interface | |
| CN107943390B (en) | Character copying method and mobile terminal | |
| EP4057137A1 (en) | Display control method and terminal device | |
| CN111602107B (en) | Display method and terminal during application quitting | |
| CN114895838A (en) | Application program display method and terminal | |
| EP3436969A1 (en) | Ink input for browser navigation | |
| CN110908554B (en) | Long screenshot method and terminal device | |
| WO2019127439A1 (en) | Calculator operation method and terminal | |
| WO2021057301A1 (en) | File control method and electronic device | |
| CN108780400B (en) | Data processing method and electronic equipment | |
| US11243679B2 (en) | Remote data input framework | |
| CN101859177A (en) | Method and device for calling and operating application program on intelligent electronic device | |
| KR20230061519A (en) | Screen capture methods, devices and electronics | |
| CN105631059B (en) | Data processing method, data processing device and data processing system | |
| CN107180039A (en) | A kind of text information recognition methods and device based on picture | |
| CN108418954A (en) | A kind of method for information display and terminal | |
| CN109634508B (en) | User information loading method and device | |
| US11460971B2 (en) | Control method and electronic device | |
| KR20150097250A (en) | Sketch retrieval system using tag information, user equipment, service equipment, service method and computer readable medium having computer program recorded therefor |
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 |