CN110245572A - Region content identification method, device, computer equipment and storage medium - Google Patents
Region content identification method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110245572A CN110245572A CN201910419206.0A CN201910419206A CN110245572A CN 110245572 A CN110245572 A CN 110245572A CN 201910419206 A CN201910419206 A CN 201910419206A CN 110245572 A CN110245572 A CN 110245572A
- Authority
- CN
- China
- Prior art keywords
- picture
- identification
- region
- selection
- instruction
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Information Transfer Between Computers (AREA)
Abstract
This application involves development field, in particular to a kind of region content identification method, device, computer equipment and storage medium.The described method includes: receiving acquisition instructions, and the picture to be processed of identification target is obtained according to acquisition instructions；Show picture to be processed；The regional choice instruction of input is received, and at least two identification regions are selected on picture to be processed according to regional choice instruction；A splicing picture is obtained according at least two identification regions of selection；Splicing picture is sent to server, and receives the target text of server transmission obtained to splicing picture progress content recognition.Specific aim identification can be carried out according to the region where text to be identified in picture using this method, improve recognition result accuracy.
Description
Technical field
This application involves multizone contents recognizing technology field, more particularly to a kind of region content identification method, device,
Computer equipment and storage medium.
Background technique
With the development of data technique, more and more information all pass through network processes and interaction, thus for papery material
The technology that material is converted to electronic format also emerges one after another.
Traditionally, terminal is usually that the picture of paper material is carried out to full figure intelligence for the identification of content in paper material
Identification, however material more complicated for background, such as poster, billboard etc., in content identification process, computer can not be sentenced
Break region of the word content to be identified in picture, may miss and the non-legible region in picture is included in identification range, cause
Recognition result inaccuracy.
Summary of the invention
Based on this, it is necessary to which in view of the above technical problems, providing one kind can be according to where text to be identified in picture
Region carries out specific aim identification, the multizone content identification method for improving recognition result accuracy, device, computer equipment and deposits
Storage media.
A kind of region content identification method, which comprises
Acquisition instructions are received, and obtain the picture to be processed of identification target according to acquisition instructions；
Show the picture to be processed；
Receive the regional choice instruction of input, and according to regional choice instruction select on the picture to be processed to
Few two identification regions；
A splicing picture is obtained according at least two identification regions of selection；
The splicing picture is sent to server, and receive that the server sends in splicing picture progress
Hold the target text that identification obtains.
The regional choice instruction for receiving input in one of the embodiments, and instructed according to regional choice in institute
It states and selects at least two identification regions on picture to be processed, comprising:
The regional choice instruction for receiving input, according to the selection of the display difference of the picture to be processed and the regional choice
Instruct corresponding identification region；
Show the identification region of selection；
Continue the regional choice instruction for receiving input, until instruction is completed in the selection for receiving input.
In one of the embodiments, after the identification region for showing selection, further includes:
Receive the region adjustment instruction of input；
The identification region is adjusted according to the region adjustment instruction.
It is described in one of the embodiments, to select at least two on the picture to be processed according to regional choice instruction
After identification region, further includes:
Record the selecting sequence of at least two identification region；
At least two identification regions according to selection obtain a splicing picture, comprising:
Obtain background picture；
At least two identification region of selection is arranged on the background picture according to the selecting sequence, is generated
One splicing picture.
What the reception server was sent in one of the embodiments, carries out content recognition to the splicing picture
After obtained target text, further includes:
Show the target text；
The false command of input is received, and the false command is sent to server；
Receive the correction content corresponding with the false command that the server returns.
A kind of multizone content identification apparatus, described device include:
Picture collection module for receiving acquisition instructions, and obtains the picture to be processed for identifying target according to acquisition instructions；
Picture display module, for showing the picture to be processed；
Region selection module, regional choice instruction for receiving input, and instructed described according to regional choice wait locate
At least two identification regions are selected on reason picture；
Picture obtains module, obtains a splicing picture at least two identification regions according to selection；
Text obtains module, for the splicing picture to be sent to server, and receives pair that the server is sent
The splicing picture carries out the target text that content recognition obtains.
The region selection module includes: in one of the embodiments,
First selecting unit, regional choice instruction for receiving input, according to the display difference of the picture to be processed
Select identification region corresponding with regional choice instruction；
Region display unit, for showing the identification region of selection；
Continue selecting unit, for continuing the regional choice instruction for receiving input, until receiving the selection of input
Complete instruction.
The region selection module in one of the embodiments, further include:
Adjustment instruction receiving unit, region adjustment instruction for receiving input；
Zone adjusting unit, for adjusting the identification region according to the region adjustment instruction.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
The step of device realizes any of the above-described the method when executing the computer program.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
The step of method described in any of the above embodiments is realized when row.
Above-mentioned zone content identification method, device, computer equipment and storage medium, terminal is according to user demand, acquisition
The picture to be processed of the identification target for the paper material for needing to identify, and shown that user is at end in the display interface of terminal
Input area selection instruction is held, at least two identification regions are selected in the picture to be processed of display, and according to the identification of selection
Region obtains the splicing picture comprising all regions that need to be identified in this picture to be processed, and splicing picture is sent to service
Device is identified by content of the server to splicing picture, obtains editable e-text, i.e. target text.Pass through user
At least two identification regions are manually selected, server is identified only in the content recognition to picture to be identified and is wrapped in splicing picture
The part contained can be avoided non-legible region and be misrepresented into identification range, cause identification to malfunction, to improve the standard of recognition result
True property.
Detailed description of the invention
Fig. 1 is the application scenario diagram of region content identification method in one embodiment；
Fig. 2 is the flow diagram of region content identification method in one embodiment；
Fig. 3 is the flow diagram of step S206 step in one embodiment；
Fig. 4 is the structural block diagram of multizone content identification apparatus in one embodiment；
Fig. 5 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Region content identification method provided by the present application, can be applied in application environment as shown in Figure 1.Wherein, eventually
End 102 is communicated with server 104 by network by network.When terminal 102 receives acquisition instructions, that is, obtain papery material
The picture to be processed of the identification target of material, and identification region is selected in picture to be processed according to the input of user at the terminal,
Then the identification region of selection is spliced to obtain splicing picture, splicing picture is sent to server 104 and carries out content knowledge
Not, when server 104 identifies the content in splicing picture, then obtained target text is back to terminal 102.Wherein, eventually
End 102 can be, but not limited to be various personal computers, laptop, smart phone, tablet computer and portable wearable
Equipment, server 104 can be realized with the server cluster of the either multiple server compositions of independent server.
In one embodiment, as shown in Fig. 2, providing a kind of region content identification method, it is applied to Fig. 1 in this way
In terminal 102 for be illustrated, comprising the following steps:
S202 receives acquisition instructions, and the picture to be processed of identification target is obtained according to acquisition instructions.
Wherein, acquisition instructions are the instructions for starting terminal acquisition picture, can be user and pass through starting at the terminal
The instruction of program or corresponding key-press input.
Picture to be processed is terminal by scanning device to the papery for needing to identify wherein word content, background complexity
The identification target of material or the material of other forms shot poster of the picture perhaps scanned for example to roadside or
The picture that billboard is shot, poster or billboard at this time are identification target.
Specifically, after terminal gets acquisition instructions, by built-in or external capture apparatus, such as taking the photograph for mobile phone or computer
As head or the scanner of computer external etc., target to be captured is placed in shooting area, obtains the picture of shooting area,
Picture i.e. to be processed.
S204 shows picture to be processed.
Specifically, after terminal acquires picture to be processed, it will be shown on the display interface of terminal, for user to this figure
Piece is edited.
S206 receives the regional choice instruction of input, and is selected at least on picture to be processed according to regional choice instruction
Two identification regions.
Wherein, regional choice instruction be it is that user inputs at the terminal, for selecting in picture to be processed need to know
The instruction in the region of other content, such as user can pass through touch screen or key entry area domain selection instruction in mobile phone terminal.
Specifically, input area selection instruction, the regional choice instruction that terminal is inputted according to user exist user at the terminal
Select at least two regions for needing to identify in this picture to be processed as identification region on display interface.For example, user is in hand
By input equipments such as touch screen or mouses on the screen of machine or computer, rectangle is used in the picture to be processed shown on the screen
Or other shapes mark out at least two identification regions comprising content to be identified.
S208 obtains a splicing picture according at least two identification regions of selection.
Splicing picture be terminal by selectively identification region splice etc. processing obtains one for identification its
The picture of middle content, for example, user has selected the identification region of three rectangles in the picture to be processed of the display interface of terminal,
The identification region of these three rectangles is spliced into a picture by terminal, i.e. splicing picture.When user only selects in picture to be processed
When selecting an identification region, following behaviour can be continued to execute using this identification region as the splicing picture of content to be identified
Make step.
S210, will splicing picture be sent to server, and receive server transmission to splicing picture carry out content recognition
Obtained target text.
Specifically, after the completion of terminal splices picture, obtained splicing picture is sent to server and carries out next step
The target text that identification obtains is sent to terminal after the completion of device identification to be serviced, completed this time to picture by content recognition operation
On multiple regions the operation that is identified of content.
Optionally, server identifies that server can to the word segment in splicing picture by contents recognizing technology
It is converted into the form of editable text (or character), is obtained so that picture will be spliced by terminal built-in or external content recognition equipment
To target text.Wherein, content recognition equipment is the equipment for converting editable target text for the text in picture,
It can refer to OCR identification equipment etc.；OCR (Optical Character Recognition, optical character identification) equipment refers to inspection
The character on picture is looked into, its shape is determined by the mode for detecting dark, bright, shape is then translated into meter with character identifying method
The equipment of the process of calculation machine text.
Above-mentioned zone content identification method, the identification mesh for the paper material that terminal needs to identify according to user demand, acquisition
Target picture to be processed, and shown in the display interface of terminal, user is in terminal input area domain selection instruction, in display
At least two identification regions are selected in picture to be processed, and are obtained one according to the identification region of selection and included this picture to be processed
In all regions that need to be identified splicing picture, will splicing picture be sent to server, by server to splicing picture content
It is identified, obtains editable e-text, i.e. target text.At least two identification regions are manually selected by user, are made
In the content recognition to picture to be identified, only the part for including in picture is spliced in identification to server, can be avoided non-legible region
Identification range is entered by misrepresentation, causes identification to malfunction, to improve the accuracy of recognition result.
In one embodiment, the regional choice that the step S206 in above-mentioned zone content identification method receives input refers to
It enables, and at least two identification regions is selected on picture to be processed according to regional choice instruction, may include:
S302 receives the regional choice instruction of input, selects to refer to regional choice according to the display difference of picture to be processed
Enable corresponding identification region.
Wherein, the display difference of picture to be processed refers to the difference of the background colour of picture to be processed, such as color difference,
Or the difference in the display content of picture to be processed, such as the typesetting difference of text.
Specifically, it is automatic according to click of the user in screen after the regional choice that terminal receives user's input instructs
Judge that user wants the identification region obtained.For example, background colour is usually picture region and official documents and correspondence for a poster picture
Region, terminal can distinguish the official documents and correspondence region in this poster according to the display situation in this poster picture, using official documents and correspondence region as
Identification region.Or the character area for there is multiple and different typesettings in a picture can be certainly when the user clicks when a region
The dynamic character area for matching corresponding typesetting.
S304 shows the identification region of selection.
Specifically, when the regional choice instruction that terminal is inputted according to user automatically identifies a corresponding identification region
Afterwards, this selected identification region can be shown on the screen with the frame of rectangle or other shapes or the modes such as highlighted, supply
User checks whether this identification region is its region for wanting selection.
S306 continues to the regional choice instruction of input, until instruction is completed in the selection for receiving input.
Specifically, user can continue input area selection instruction, by the picture to be processed of input equipment on the screen
It is selected, terminal continues to match corresponding identification region automatically for user, until user selects this all picture to be processed
In identification region, user terminal input selection complete instruction, complete the region selection step of this picture to be processed.
In above-described embodiment, it is that user's intelligent Matching is corresponding out that the regional choice that terminal can be inputted by user, which instructs,
Identification region improves operability of the user in regional choice.
It in one embodiment, can also include: to receive input after above-mentioned steps S304 shows the identification region of selection
Region adjustment instruction；Identification region is adjusted according to region adjustment instruction.
Wherein, region adjustment instruction is the instruction for adjusting this identification region, and it is right on a terminal screen to can be user
The instruction that the boundary of identification region is adjusted.
Specifically, in above-mentioned steps S304, terminal is after display interface shows the identification region of selection, if user sends out
When this existing identification region is not the identification region oneself wanted, adjustment instruction can be inputted to terminal again, this identification region is carried out
Adjustment.For example, the identification region that terminal generates is rectangular area, user makes to identify interior by the length and width of dragging rectangle
Hold within this rectangle.
It in above-described embodiment, is corrected by the identification region that region adjustment instruction judges terminal intelligent, guarantees to know
The accuracy in other region.
In one embodiment, being instructed in above-mentioned steps S206 according to regional choice selects at least on picture to be processed
It can also include: the selecting sequence for recording at least two identification regions after two identification regions；Then in above-mentioned step S208
At least two identification regions according to selection obtain a splicing picture, may include: acquisition background picture；Extremely by selection
Few two identification regions arrange on background picture according to selecting sequence, generate a splicing picture.
Wherein, background picture is to generate the background layer of splicing picture for placing identification region.Can for Transparent color or its
His color.
Specifically, user can according to needed in picture to be processed identification content successive or importance sequence it is suitable to carry out
Sequence selection, and the identification region of selection is spliced on a unified background layer according to the selecting sequence of user, make spliced map
Piece background colour having the same obtains a splicing picture.
Optionally, after server gets the splicing picture of terminal transmission, also according to multiple identification regions in splicing picture
Put in order to be identified to word content therein, the typographical sequences of obtained target text also with multiple identification regions
Put in order and be consistent.
In above-described embodiment, picture splicing and identification are carried out by the selecting sequence of user, so that finally obtained spelling
The typographical sequences of map interlinking piece and final target text can select the sequence consensus of identification region with user.
In one embodiment, what the reception server in above-mentioned steps S210 was sent carries out content recognition to splicing picture
It can also include: displaying target text after obtained target text；The false command of input is received, and false command is sent out
It send to server；Receive the correction content corresponding with false command that server returns.
Wherein, false command is when the content in the target text that user's discovery server content identifies has identification
When mistake, to the instruction of terminal input.It can be the instruction re-recognized, be also possible to in the part in target text
Appearance is labeled, the instruction etc. only again identified that this partial content.
Specifically, after terminal receives target text, this target text is displayed on the display interface, if user has found clothes
It when the content recognition inaccuracy of business device, is then instructed to terminal input error, this false command is sent to server by end, so that clothes
Be engaged in device according to this false command in destination document full content or partial content carry out error correction.
Optionally, technical staff can be in server end one intelligent correction model of training, i.e., using a large amount of texts as sample
This, the model that can automatically identify the wrong content in document obtained by machine learning and big data training is automatic right
The target text that server obtains splicing picture recognition carries out error correction.
In above-described embodiment, the recognition result of server is collected in the false command that server can be fed back according to terminal, for
The part of identification error carries out misarrangement.
It should be understood that although each step in the flow chart of Fig. 2-3 is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 2-3
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively
It carries out, but can be at least part of the sub-step or stage of other steps or other steps in turn or alternately
It executes.
In one embodiment, as shown in figure 4, providing a kind of multizone content identification apparatus, comprising: picture collection mould
Block 100, picture display module 200, region selection module 300, picture splicing module 400 and text obtain module 500, in which:
Picture collection module 100 for receiving acquisition instructions, and obtains the figure to be processed for identifying target according to acquisition instructions
Piece；
Picture display module 200, for showing picture to be processed；
Region selection module 300, regional choice instruction for receiving input, and instructed according to regional choice to be processed
At least two identification regions are selected on picture；
Picture splicing module 400 obtains a splicing picture at least two identification regions according to selection；
Text obtain module 500, be sent to server for that will splice picture, and receive server send to spliced map
Piece carries out the target text that content recognition obtains.
In one embodiment, above-mentioned zone selecting module 300 may include:
First selecting unit, regional choice instruction for receiving input, selects according to the display difference of picture to be processed
Identification region corresponding with regional choice instruction.
Region display unit, for showing the identification region of selection.
Continue selecting unit, for continuing to the regional choice instruction of input, until the selection for receiving input is completed
Instruction.
In one embodiment, above-mentioned zone selecting module 300 can also include:
Adjustment instruction receiving unit, region adjustment instruction for receiving input.
Zone adjusting unit, for adjusting identification region according to region adjustment instruction.
In one embodiment, above-mentioned multizone content identification apparatus can also include:
Selecting sequence logging modle, for recording the selecting sequence of at least two identification regions.
Then above-mentioned picture splicing module 400 may include:
Background acquiring unit, for obtaining background picture.
Picture concatenation unit, at least two identification regions for that will select are arranged in background picture according to selecting sequence
On, generate a splicing picture.
In one embodiment, above-mentioned multizone content identification apparatus can also include:
Text display module is used for displaying target text.
False command sending module, false command for receiving input, and false command is sent to server.
Correction module, for receiving the correction content corresponding with false command of server return.
Specific restriction about multizone content identification apparatus may refer to above for region content identification method
It limits, details are not described herein.Modules in above-mentioned multizone content identification apparatus can be fully or partially through software, hardware
And combinations thereof realize.Above-mentioned each module can be embedded in the form of hardware or independently of in the processor in computer equipment,
It can be stored in a software form in the memory in computer equipment, execute the above modules pair in order to which processor calls
The operation answered.
In one embodiment, a kind of computer equipment is provided, which can be terminal, internal structure
Figure can be as shown in Figure 5.The computer equipment includes processor, the memory, network interface, display connected by system bus
Screen and input unit.Wherein, the processor of the computer equipment is for providing calculating and control ability.The computer equipment is deposited
Reservoir includes non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system and computer journey
Sequence.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The network interface of machine equipment is used to communicate with external terminal by network connection.When the computer program is executed by processor with
Realize a kind of region content identification method.The display screen of the computer equipment can be liquid crystal display or electric ink is shown
Screen, the input unit of the computer equipment can be the touch layer covered on display screen, be also possible on computer equipment shell
Key, trace ball or the Trackpad of setting can also be external keyboard, Trackpad or mouse etc..
It will be understood by those skilled in the art that structure shown in Fig. 5, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, which is stored with
Computer program, which performs the steps of reception acquisition instructions when executing computer program, and is obtained according to acquisition instructions
Take the picture to be processed of identification target；Show picture to be processed；The regional choice instruction of input is received, and is referred to according to regional choice
Order selects at least two identification regions on picture to be processed；A spliced map is obtained according at least two identification regions of selection
Piece；Splicing picture is sent to server, and receives the target of server transmission obtained to splicing picture progress content recognition
Text.
In one embodiment, processor executes the regional choice instruction for the reception input realized when computer program, and
At least two identification regions are selected on picture to be processed according to regional choice instruction, comprising: the regional choice for receiving input refers to
It enables, identification region corresponding with regional choice instruction is selected according to the display difference of picture to be processed；Show the cog region of selection
Domain；The regional choice instruction of input is continued to, until instruction is completed in the selection for receiving input.
In one embodiment, after that realizes when processor execution computer program shows the identification region of selection, also
It include: the region adjustment instruction for receiving input；Identification region is adjusted according to region adjustment instruction.
In one embodiment, that realizes when processor execution computer program instructs according to regional choice in figure to be processed
On piece selects after at least two identification regions, further includes: the selecting sequence of at least two identification regions of record；Processor executes
At least two identification regions according to selection realized when computer program obtain a splicing picture, comprising: obtain Background
Piece；At least two identification regions of selection are arranged on background picture according to selecting sequence, generate a splicing picture.
In one embodiment, processor execute computer program when realize receive server send to splicing picture
After the target text that progress content recognition obtains, further includes: displaying target text；The false command of input is received, and will be wrong
Accidentally instruction is sent to server；Receive the correction content corresponding with false command that server returns.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of reception acquisition instructions when being executed by processor, and according to acquisition instructions obtain identification target to
Handle picture；Show picture to be processed；The regional choice instruction of input is received, and is instructed according to regional choice in picture to be processed
At least two identification regions of upper selection；A splicing picture is obtained according at least two identification regions of selection；Picture will be spliced
It is sent to server, and receives the target text of server transmission obtained to splicing picture progress content recognition.
In one embodiment, the regional choice instruction for the reception input realized when computer program is executed by processor,
And at least two identification regions are selected on picture to be processed according to regional choice instruction, comprising: receive the regional choice of input
Instruction selects identification region corresponding with regional choice instruction according to the display difference of picture to be processed；Show the identification of selection
Region；The regional choice instruction of input is continued to, until instruction is completed in the selection for receiving input.
In one embodiment, after that realizes when computer program is executed by processor shows the identification region of selection,
Further include: receive the region adjustment instruction of input；Identification region is adjusted according to region adjustment instruction.
In one embodiment, that realizes when computer program is executed by processor instructs according to regional choice to be processed
After selecting at least two identification regions on picture, further includes: the selecting sequence of at least two identification regions of record；Computer journey
At least two identification regions according to selection realized when sequence is executed by processor obtain a splicing picture, comprising: obtain back
Scape picture；At least two identification regions of selection are arranged on background picture according to selecting sequence, generate a splicing picture.
In one embodiment, realized when computer program is executed by processor receive server send to spliced map
Piece carries out after the target text that content recognition obtains, further includes: displaying target text；The false command of input is received, and will
False command is sent to server；Receive the correction content corresponding with false command that server returns.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of region content identification method, which comprises
Acquisition instructions are received, and obtain the picture to be processed of identification target according to acquisition instructions；
Show the picture to be processed；
The regional choice instruction of input is received, and selects at least two on the picture to be processed according to regional choice instruction
A identification region；
A splicing picture is obtained according at least two identification regions of selection；
The splicing picture is sent to server, and receive that the server sends to splicing picture progress content knowledge
The target text not obtained.
2. the method according to claim 1, wherein the regional choice for receiving input instructs, and according to area
Domain selection instruction selects at least two identification regions on the picture to be processed, comprising:
The regional choice instruction for receiving input is instructed according to the selection of the display difference of the picture to be processed with the regional choice
Corresponding identification region；
Show the identification region of selection；
Continue the regional choice instruction for receiving input, until instruction is completed in the selection for receiving input.
3. according to the method described in claim 2, it is characterized in that, also being wrapped after the identification region for showing selection
It includes:
Receive the region adjustment instruction of input；
The identification region is adjusted according to the region adjustment instruction.
4. the method according to claim 1, wherein described instruct according to regional choice in the picture to be processed
After at least two identification regions of upper selection, further includes:
Record the selecting sequence of at least two identification region；
At least two identification regions according to selection obtain a splicing picture, comprising:
Obtain background picture；
At least two identification region of selection is arranged on the background picture according to the selecting sequence, generates one
Splice picture.
5. the method according to claim 1, which is characterized in that described to receive what the server was sent
After the target text obtained to the splicing picture progress content recognition, further includes:
Show the target text；
The false command of input is received, and the false command is sent to server；
Receive the correction content corresponding with the false command that the server returns.
6. a kind of multizone content identification apparatus, which is characterized in that described device includes:
Picture collection module for receiving acquisition instructions, and obtains the picture to be processed for identifying target according to acquisition instructions；
Picture display module, for showing the picture to be processed；
Region selection module, regional choice instruction for receiving input, and instructed according to regional choice in the figure to be processed
On piece selects at least two identification regions；
Picture obtains module, obtains a splicing picture at least two identification regions according to selection；
Text obtains module, for the splicing picture to be sent to server, and receive server transmission to described
Splicing picture carries out the target text that content recognition obtains.
7. device according to claim 6, which is characterized in that the region selection module includes:
First selecting unit, regional choice instruction for receiving input, selects according to the display difference of the picture to be processed
Identification region corresponding with regional choice instruction；
Region display unit, for showing the identification region of selection；
Continue selecting unit, for continuing the regional choice instruction for receiving input, until the selection for receiving input is completed
Instruction.
8. device according to claim 7, which is characterized in that the region selection module further include:
Adjustment instruction receiving unit, region adjustment instruction for receiving input；
Zone adjusting unit, for adjusting the identification region according to the region adjustment instruction.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 5 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 5 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910419206.0A CN110245572A (en) | 2019-05-20 | 2019-05-20 | Region content identification method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910419206.0A CN110245572A (en) | 2019-05-20 | 2019-05-20 | Region content identification method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110245572A true CN110245572A (en) | 2019-09-17 |
Family
ID=67884501
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910419206.0A Pending CN110245572A (en) | 2019-05-20 | 2019-05-20 | Region content identification method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110245572A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112580625A (en) * | 2020-12-11 | 2021-03-30 | 海信视像科技股份有限公司 | Display device and image content identification method |
| US11997341B2 (en) | 2020-07-14 | 2024-05-28 | Hisense Visual Technology Co., Ltd. | Display apparatus and method for person recognition and presentation |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101667251A (en) * | 2008-09-05 | 2010-03-10 | 三星电子株式会社 | OCR recognition method and device with auxiliary positioning function |
| CN107358227A (en) * | 2017-06-29 | 2017-11-17 | 努比亚技术有限公司 | A kind of mark recognition method, mobile terminal and computer-readable recording medium |
| CN108470041A (en) * | 2018-02-12 | 2018-08-31 | 维沃移动通信有限公司 | A kind of information search method and mobile terminal |
| CN108874283A (en) * | 2018-05-29 | 2018-11-23 | 努比亚技术有限公司 | Image identification method, mobile terminal and computer readable storage medium |
| US20180365536A1 (en) * | 2017-06-19 | 2018-12-20 | Adobe Systems Incorporated | Identification of fonts in an application |
| CN109117848A (en) * | 2018-09-07 | 2019-01-01 | 泰康保险集团股份有限公司 | A kind of line of text character identifying method, device, medium and electronic equipment |
-
2019
- 2019-05-20 CN CN201910419206.0A patent/CN110245572A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101667251A (en) * | 2008-09-05 | 2010-03-10 | 三星电子株式会社 | OCR recognition method and device with auxiliary positioning function |
| US20180365536A1 (en) * | 2017-06-19 | 2018-12-20 | Adobe Systems Incorporated | Identification of fonts in an application |
| CN107358227A (en) * | 2017-06-29 | 2017-11-17 | 努比亚技术有限公司 | A kind of mark recognition method, mobile terminal and computer-readable recording medium |
| CN108470041A (en) * | 2018-02-12 | 2018-08-31 | 维沃移动通信有限公司 | A kind of information search method and mobile terminal |
| CN108874283A (en) * | 2018-05-29 | 2018-11-23 | 努比亚技术有限公司 | Image identification method, mobile terminal and computer readable storage medium |
| CN109117848A (en) * | 2018-09-07 | 2019-01-01 | 泰康保险集团股份有限公司 | A kind of line of text character identifying method, device, medium and electronic equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11997341B2 (en) | 2020-07-14 | 2024-05-28 | Hisense Visual Technology Co., Ltd. | Display apparatus and method for person recognition and presentation |
| CN112580625A (en) * | 2020-12-11 | 2021-03-30 | 海信视像科技股份有限公司 | Display device and image content identification method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110442822B (en) | Method, device, equipment and storage medium for displaying small program content | |
| JP4829920B2 (en) | Form automatic embedding method and apparatus, graphical user interface apparatus | |
| US20170220858A1 (en) | Optical recognition of tables | |
| CN109947967A (en) | Image-recognizing method, device, storage medium and computer equipment | |
| US8897594B2 (en) | Image reader, mobile terminal apparatus, and non-transitory computer readable medium | |
| US11243670B2 (en) | Information processing system, information processing apparatus, information processing method and non-transitory computer readable medium | |
| CN110462613A (en) | Automatically generate document | |
| US9135234B1 (en) | Collaborative generation of digital content with interactive reports | |
| CN111324352A (en) | Code generation method of application page and related equipment | |
| CN105809162B (en) | Method and device for acquiring WIFI hotspot and picture associated information | |
| CN109710144A (en) | Notes page processing method, computer equipment and the storage medium of notebook | |
| CN114490395A (en) | Test processing method, device, equipment and medium | |
| CN111223155A (en) | Image data processing method, image data processing device, computer equipment and storage medium | |
| CN110245570A (en) | Scan text segmentation method, device, computer equipment and storage medium | |
| CN110245572A (en) | Region content identification method, device, computer equipment and storage medium | |
| CN115174506B (en) | Session information processing method, apparatus, readable storage medium and computer device | |
| CN112306601A (en) | Application interaction method and device, electronic equipment and storage medium | |
| CN110097040B (en) | Image processing apparatus and storage medium | |
| US10275528B2 (en) | Information processing for distributed display of search result | |
| CN113919287B (en) | Entity relationship labeling method and device combining RPA and AI and electronic equipment | |
| US20210073458A1 (en) | Comic data display system, method, and program | |
| CN113835598A (en) | Information acquisition method and device and electronic equipment | |
| CN108664945A (en) | Image text and form-pronunciation-meaning characteristic recognition method and device | |
| CN114679546A (en) | Display method and device, electronic equipment and readable storage medium | |
| CN113849415A (en) | Control testing method and device, storage medium and electronic equipment |
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 |