CN107861684A - Write recognition methods, device, storage medium and computer equipment - Google Patents
Write recognition methods, device, storage medium and computer equipment Download PDFInfo
- Publication number
- CN107861684A CN107861684A CN201711184637.0A CN201711184637A CN107861684A CN 107861684 A CN107861684 A CN 107861684A CN 201711184637 A CN201711184637 A CN 201711184637A CN 107861684 A CN107861684 A CN 107861684A
- Authority
- CN
- China
- Prior art keywords
- recognition result
- identification
- recognition
- writing
- candidate
- 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
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0487—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser
- G06F3/0488—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures
- G06F3/04883—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures for inputting data by handwriting, e.g. gesture or text
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/02—Input arrangements using manually operated switches, e.g. using keyboards or dials
- G06F3/023—Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
- G06F3/0233—Character input methods
- G06F3/0236—Character input methods using selection techniques to select from displayed items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/02—Input arrangements using manually operated switches, e.g. using keyboards or dials
- G06F3/023—Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
- G06F3/0233—Character input methods
- G06F3/0237—Character input methods using prediction or retrieval techniques
-
- 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
- G06V30/24—Character recognition characterised by the processing or recognition method
- G06V30/242—Division of the character sequences into groups prior to recognition; Selection of dictionaries
- G06V30/244—Division of the character sequences into groups prior to recognition; Selection of dictionaries using graphical properties, e.g. alphabet type or font
- G06V30/2455—Discrimination between machine-print, hand-print and cursive writing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Character Discrimination (AREA)
Abstract
The present invention relates to writing recognition methods, device, storage medium and computer equipment, applied to technical field of touch control.Methods described includes:Detect when acting on the written information on touch-screen/contact panel, identify the written handwriting of current written information respectively by multiple preset identification models;Recognition result of each identification model to the written handwriting is obtained, as candidate's recognition result;A preferred recognition result is selected from multiple candidate's recognition results, output displaying is carried out to preferred recognition result.The present invention solves the problems, such as to realize that writing recognition efficiency is low under existing way, simplifies user and operate, without advance manual switching identification model, it is possible to increase write the efficiency of identification.
Description
Technical field
The present invention relates to technical field of touch control, is set more particularly to writing recognition methods, device, storage medium and computer
It is standby.
Background technology
With the fast development of terminal device, current most of terminal devices all support user's touch operation, touch operation
Also it has been gradually replacing traditional button operation custom.
In the terminal device for supporting touch operation, in addition to supporting touch to choose, to touch the operations such as slip, generally also prop up
The touch writing identification of user is held, both can be the handwriting recognition of user or the book by instruments such as mouse, lettering pens
Identification is write, facilitates user to input information.Recognizable written handwriting includes word and figure, in addition, in some terminal devices,
The also recognizable music score write, flow chart etc..
A variety of different types of identification models are pre-set in existing terminal device, it is a variety of different types of to support
Writing identification, however, checking that terminal device is current, it is necessary to be set by system when user's using terminal equipment carries out writing input
In which kind of identification model, and artificial (or manual) switching identification model could effectively identify use to the desired identification model of user
The written handwriting at family, writing is caused to identify less efficient.
The content of the invention
Based on this, it is necessary to for realizing the problem of writing recognition efficiency is relatively low under existing way, there is provided one kind writing is known
Other method, apparatus, storage medium and computer equipment.
Scheme provided in an embodiment of the present invention includes:
One kind writing recognition methods, including:
Detect when acting on the written information on touch-screen/contact panel, pass through multiple preset identification models and distinguish
Identify the written handwriting corresponding to the written information;
Recognition result of each identification model to the written handwriting is obtained, as candidate's recognition result;
A preferred recognition result is selected from multiple candidate's recognition results, output exhibition is carried out to preferred recognition result
Show.
In one embodiment, after carrying out output displaying to preferred recognition result, in addition to:
When detecting the trigger action instruction to the preferably recognition result, other candidates of this written handwriting are identified
As a result output displaying is carried out.
In one embodiment, when detecting the trigger action instruction to the preferably recognition result, to this lettering pen
After other candidate's recognition results of mark carry out output displaying, in addition to:
When detecting the trigger action instruction to the preferably recognition result, other candidates of this written handwriting are identified
As a result output displaying is carried out;Or
Instruction is chosen to any candidate's recognition result if not received in setting time, the preferably recognition result is made
For the final recognition result of this writing identification.
In one embodiment, receive and instruction is chosen to any candidate's recognition result in other candidate's recognition results, will be by
After final recognition result of the candidate's recognition result chosen as this writing identification, in addition to:
Obtain to the control information of preferred recognition result, correction entries corresponding to generation, by the correction entries preserve to
Default experience storehouse;Every correction entries includes:Corresponding to current written handwriting, the written handwriting preferably recognition result with
And final recognition result.
In one embodiment, it is described a preferred recognition result is selected from multiple candidate's recognition results after, also wrap
Include:
It whether there is correction entries corresponding with the preferably recognition result in inquiry experience storehouse, if in the presence of according to described
Correction entries is corrected to preferred recognition result;
It is described to carry out output displaying to preferred recognition result, including:Output exhibition is carried out to the preferred recognition result after correction
Show.
In one embodiment, preferred recognition result is corrected according to the correction entries, including:
If correction entries corresponding with the preferably recognition result there are more than two in the experience storehouse, the wherein time is obtained
A newest correction entries, preferred recognition result is corrected according to this correction entries.
In one embodiment, current written handwriting is identified respectively by multiple identification models, including:Calculate current writing
The matching degree of each known person's handwriting, the identification mould is determined according to the matching degree in person's handwriting person's handwriting storehouse corresponding with identification model
Recognition result of the type to current written handwriting;Wherein, each identification model corresponds to a person's handwriting storehouse, the person's handwriting storehouse Zhong Bao respectively
Include multiple known person's handwritings;
A preferred recognition result is selected from multiple candidate's recognition results, including:From multiple candidate's recognition results
One candidate's recognition result of matching degree highest is selected, as preferred recognition result.
In one embodiment, it is described to call preset identification model, identify current book respectively by multiple identification models
Person's handwriting is write, including:
Predefined first priority of each identification model is obtained, calls and knows according to the order of the first priority from high to low
Other model, current written handwriting is identified by each identification model respectively;
And/or
The second priority of each identification model is determined according to history identification record, according to the second priority from high to low
Order calls identification model, identifies current written handwriting respectively by each identification model.
In one embodiment, the second priority of each identification model is determined according to history identification record, including:
It is determined that identification model corresponding to the preferred recognition result of last writing identification, true by the priority of the identification model
It is set to limit priority, preferentially to call the identification model.
In one embodiment, recognition result of each identification model to the written handwriting is obtained, identifies and ties as candidate
Fruit, including:
It is default to judge whether identification model is more than or equal to the matching degree corresponding to the recognition result of current written handwriting
The first matching degree, if so, obtain identification model recognition result as candidate's recognition result, otherwise, abandon the identification mould
The recognition result of type.
In one embodiment, preset identification mould is called according to the order of the priority of the first priority/second from high to low
Type, identify current written handwriting respectively by each identification model, in addition to:
Detect whether the identification model currently called is more than to the matching degree corresponding to the recognition result of current written handwriting
Or the second matching degree equal to setting, if so, stopping calling remaining identification model.
One kind writing identification device, including:
Calling module, when acting on written information on the touchscreen for detecting, pass through multiple preset identification models
The written handwriting corresponding to the written information is identified respectively;
Collection module, for obtaining recognition result of each identification model to the written handwriting, identify and tie as candidate
Fruit;
And module is chosen, for selecting a preferred recognition result from multiple candidate's recognition results, know to preferred
Other result carries out output displaying.
A kind of computer-readable recording medium, is stored thereon with computer program, and the program is realized when being executed by processor
The step of any of the above-described methods described.
A kind of computer equipment, including memory, processor and storage can be run on a memory and on a processor
Computer program, the step of realizing any of the above-described methods described during the computing device described program.
Implement above-described embodiment to have the advantages that:Detecting the writing that acts on touch-screen/contact panel
During information, the written handwriting of current written information is identified respectively by multiple preset identification models;Obtain each identification model
To the recognition result of the written handwriting, multiple candidate's recognition results are obtained;Further chosen from multiple candidate's recognition results
Go out a preferred recognition result, and output displaying is carried out to preferred recognition result;Thus user is without advance clear and definite terminal device
Current recognition mode, without selected manually in advance or switching identification model, simplify user's operation, it is possible to increase writing
Recognition efficiency.
In addition, in one embodiment of the invention, moreover it is possible to the correction entries according to user to recognition result, to filtering out
Preferred recognition result a kind of timely alignment mechanism is provided so that final recognition result more meets the truth of user writing.
Certainly, any embodiment for implementing the present invention it is not absolutely required to reach all of above beneficial effect simultaneously.
Brief description of the drawings
Fig. 1 is the applied environment figure that recognition methods is write in one embodiment;
Fig. 2 is the indicative flowchart of the writing recognition methods of an embodiment;
Fig. 3 is the effect diagram of the writing recognition methods of an embodiment;
Fig. 4 is the schematic diagram of the character recognition algorithm of an embodiment;
Fig. 5 is the schematic diagram of the character recognition algorithm of another embodiment;
Fig. 6 is the identification container of an embodiment and the indicative flowchart for identifying plug-in unit;
Fig. 7 is the schematic diagram of the writing identification device of an embodiment.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
The term " comprising " and " having " of the embodiment of the present invention and their any deformations, it is intended that cover non-exclusive
Comprising.Such as contain series of steps or the process, method, system, product or equipment of (module) unit are not limited to
The step of listing or unit, but alternatively also including the step of not listing or unit, or alternatively also include for these
The intrinsic other steps of process, method, product or equipment or unit.
Referenced herein " multiple " refer to two or more."and/or", the association for describing affiliated partner are closed
System, expression may have three kinds of relations, for example, A and/or B, can be represented:Individualism A, while A and B be present, individualism
These three situations of B.It is a kind of relation of "or" that character "/", which typicallys represent forward-backward correlation object,.
It is the similar object of difference that term " first second the 3rd " involved by the embodiment of the present invention, which is only, is not represented
For the particular sorted of object, it is possible to understand that ground, " first second the 3rd " can exchange specific suitable in the case of permission
Sequence or precedence.It should be appreciated that the object that " first second the 3rd " is distinguished can exchange in the appropriate case, so that here
The embodiments of the invention of description can be implemented with the order in addition to those for illustrating or describing herein.
Referenced herein " embodiment " is it is meant that the special characteristic, structure or the characteristic that describe can wrap in conjunction with the embodiments
It is contained at least one embodiment of the application.Each position in the description occur the phrase might not each mean it is identical
Embodiment, nor the independent or alternative embodiment with other embodiments mutual exclusion.Those skilled in the art explicitly and
Implicitly understand, embodiment described herein can be combined with other embodiments.
In order to facilitate understanding, the noun being related in the embodiment of the present invention is explained below.
Written handwriting:By order and point set information structure, the point set can be touch point point set or mouse point
Point set etc..
Container:It is the object for storing and organizing other objects.
Plug-in unit:It is the program that a kind of application programming interfaces for following certain specification are write out.
Fig. 1 is the applied environment figure that recognition methods is write in one embodiment;As shown in figure 1, its working environment is related to end
End equipment, the terminal device support writing identification function, and including but not limited to handwriting recognition, mouse track drafting is identified, touched
Touch pen writing identification.Such as identification user's handwriting, or identification user by mouse draw person's handwriting, the handwriting/
Mouse, which draws person's handwriting, includes the text informations such as Chinese character, English alphabet, numeral, or the graphical information such as triangle, rectangle, circle, this
Outside, it also can be music score, flow chart etc..
The cut-away view of terminal device in one embodiment is as shown in Figure 1.The terminal device includes total by system
Input equipment, output equipment, processor, storage medium and the internal memory of line connection.
Wherein, the input equipment may include touch-screen/Trackpad and other input equipments.Touch-screen/Trackpad, can
Collecting touch operation of the user on or near it, (for example user is existed using any suitable object or annex such as finger, stylus
Operation on touch-screen/Trackpad or near touch-screen/Trackpad), and connected accordingly according to formula set in advance driving
Connection device.Optionally, touch-screen/Trackpad may include both touch detecting apparatus and touch controller.Wherein, inspection is touched
The touch orientation of device detection user is surveyed, and detects the signal that touch operation is brought, transmits a signal to touch controller;Touch
Controller receives touch information from touch detecting apparatus, and is converted into contact coordinate, then gives processor, and can receive
Order that processor is sent simultaneously is performed.It is furthermore, it is possible to more using resistance-type, condenser type, infrared ray and surface acoustic wave etc.
Type, which is realized, touches touch-screen/Trackpad.Except touch-screen/Trackpad, input equipment can also include other input equipments.Tool
Body, other input equipments can include but is not limited to physical keyboard, function key (such as volume control button, switch key
Deng), trace ball, mouse, the one or more in action bars etc..
Display device can be used for display by the information of user's input or be supplied to the information of user.Display device may include to show
Display screen, further, touch-screen can cover display screen, after touch-screen detects the touch operation on or near it, transmission
To processor to determine the type of touch event, it is followed by subsequent processing device and is provided on a display screen accordingly according to the type of touch event
Visual output.In some embodiments it is possible to touch-screen and display screen are integrated and realize input and the output work of terminal device
Energy.
Specifically, touch-screen/Trackpad of terminal device is used to receive written handwriting.The storage medium storage of terminal device
There are operating system and a kind of writing identification device, the writing identification device is used to realize a kind of writing recognition methods.Terminal device
Processor be used for provide calculate and control ability, support the operation of whole terminal device.Saved as in terminal device non-volatile
Property storage medium in the operation of writing identification device environment is provided, computer-readable instruction can be stored in the internal memory, the meter
When calculation machine readable instruction is executed by processor, a kind of writing recognition methods of computing device may be such that.The touch-screen of terminal device
Also exportable writing recognition result information.
The terminal device includes but is not limited to smart mobile phone, tablet personal computer, vehicle-mounted computer, wearable intelligent equipment etc..
With reference to Fig. 1 and the above-mentioned explanation to application environment, writing recognition methods embodiment is illustrated below.
Although the step in various embodiments of the present invention is arranged with label, it is not used to limit the priority time of step
Sequence, based on the order of step or the execution of certain step need other steps unless expressly stated, the otherwise phase of step
Order is adjustable.
Fig. 2 is the indicative flowchart of the writing recognition methods of an embodiment;As shown in Fig. 2 the writing in the present embodiment
Recognition methods includes step:
S11, detect when acting on the written information on touch-screen/contact panel, pass through multiple preset identification models
The written handwriting corresponding to the written information is identified respectively.
The written information refers to that user carries out written handwriting information by touch-screen/Trackpad.The written handwriting
By including order and point set information structure, including touch point, mouse point etc..
The identification model refers to that corresponding knowledge can be obtained based on matching algorithm to written handwriting progress signature analysis
The program module of other result.For different identification models, the recognizer of use may be different, therefore different identification models pair
May be different in the recognition accuracy of same written handwriting.
In an alternative embodiment, identification model can only identify written handwriting corresponding with its type, such as Text region
Model can only identify the text handwriting of writing, for the music score person's handwriting then None- identified, or be identified as the symbol of mistake of writing.
In another alternative embodiment, no matter written handwriting why type, each identification model is recognizable, but the standard of recognition result
Exactness can be variant;For example, currently write for music score, be identified by music score identification model, the matching degree of recognition result
Up to 90%;It is identified by Text region model, the matching degree of recognition result is 30%;Carried out by figure identification model
Identification, the matching degree of recognition result is 50%.
In one embodiment, the step of above-mentioned writing recognition methods also includes pre-setting multiple different identification models.
It should be understood that the preset situation of identification model can be not limited to the above-mentioned situation enumerated depending on actual conditions.
S12, recognition result of each identification model to the written handwriting is obtained, as candidate's recognition result.
The recognizer that different identification models uses may be different, such as carry out written handwriting knowledge based on matching principle
Not.Matching principle therein is specific for example, written handwriting is compared with the stroke of existing known word, calculates both
Matching degree, word known to matching degree highest is chosen as recognition result;Such as the stroke of all known words is determined
Justice is multiple directions, and the stroke writing of known word then is resolved into a character string, when people writes one on the touchscreen
During symbol, it is also resolved into the character string of multiple directions, finally comparing the distances of two character strings can just judge and different
The matching degree of symbol.Or for example, the characteristic value of extraction written handwriting to be identified, calculate this feature value with it is existing known several
The matching degree of the characteristic value of what figure, selected characteristic value matching degree highest known geometry is as recognition result.
In an alternative embodiment, the match cognization algorithm that character is identified identification model includes:In advance will be all
The stroke writing of character defines 8 directions, and each direction is represented with different numerical value, and as shown in Figure 4 is then by known standard
The stroke of character can resolve into a character string, such as known standard character B stroke can decompose to obtain a character string
“2601234012234”.Then as user written character B on the touchscreen, the character of user writing is also resolved into 8 sides
To character string " 22661223440123, finally compare the distance of two character strings, it may be determined that go out the symbol and of user writing
The matching degree (degree of approximation) of symbol is known, reference can be made to shown in Fig. 4.
In another alternative embodiment, the match cognization algorithm that character is identified identification model includes:In advance by word
Symbol is divided into many fritters, as shown in Fig. 5 (a), character 8 is changed and is divided into 4*5=20 fritter, and each fritter is by many pictures
What element was formed, in other words, each fritter is made up of many pixels, for example 100*100=10000 pixel is formed.System
Count the pixel of how many black each fritter Nei, such as the first row:1st fritter, totally 0 black picture element, is designated as 0;2nd
Fritter, totally 28 black picture elements, are designated as 28;3rd fritter, totally 10 black picture elements, are designated as 10;4th fritter, totally 0 it is black
Color pixel, it is designated as 0.By that analogy, the numeral of each fritter of every a line is obtained, as the characteristic value of corresponding fritter, finally
Obtain shown in numerical value such as Fig. 5 (b) of each fritter of character 8, thus obtaining an array corresponding to a character 8, in this, as
The feature array of character 8.For the character of user writing, the feature array of the character of user writing is similarly obtained, compares two
The distance of feature array, it may be determined that go out the character of user writing and the matching degree (degree of approximation) of known character.
It is appreciated that the recognizer that each identification model uses includes but is not limited to the example above.
By calling multiple identification models that current written handwriting is identified, multiple different identification knots are can obtain
Fruit.
S13, a preferred recognition result is selected from multiple candidate's recognition results, preferred recognition result is exported
Displaying.
As described above, different identification models may be different to the recognition result of same written handwriting, and what is got is multiple
There is also difference for candidate's recognition result.Difference based on recognition result in the degree of accuracy (or matching degree), can be from multiple candidates
A preferred recognition result, the recognition result selected as Automatic sieve are selected in recognition result.
The writing recognition methods of above-described embodiment, when detecting written information, by calling multiple identification models to distinguish
Current written handwriting is identified, obtains multiple candidate's recognition results;Further one is selected from multiple candidate's recognition results
It is preferred that recognition result, and output displaying is carried out to preferred recognition result.User currently enables without advance clear and definite terminal device
Identification model, without selected manually in advance or switching identification model, and written handwriting can be effectively identified, improve book
Write recognition efficiency.
In one embodiment, after above-mentioned steps S13, in addition to:Detect the triggering to the preferably recognition result
During operational order, output displaying is carried out to other candidate's recognition results of this written handwriting.To show each identification to user
Specific recognition result of the model to this written handwriting.
Further, in one embodiment, receive and any candidate's recognition result in other candidate's recognition results is chosen
Instruction, the final recognition result using selected candidate's recognition result as this writing identification.As shown in figure 3, it ought select automatically
When the recognition result taken is shown, this end of identification is not represented, but enters preselected state, now user can point
Recognition result is hit, ejects the recognition result obtained by other identification models.User can select a kind of recognition result to substitute ought
The preceding recognition result chosen automatically.
Alternatively, if exceeding certain time, or user directly carries out handwriting recognition next time, then it is assumed that user gives tacit consent to
Automatically the recognition result chosen, this identification is terminated.As shown in figure 3, A is handwriting, B is the recognition result chosen automatically, C
It is the candidate's recognition result deployed after user clicks on B.By above-described embodiment, because user can be carried out to automatic identification result
Correction, therefore further increase recognition accuracy.
Further, in one embodiment, receive to other candidate's recognition results in any candidate's recognition result choosing
Middle instruction, after selected candidate's recognition result is write into the final recognition result of identification as this, it may also include:Obtain
To the control information of preferred recognition result, correction entries corresponding to generation, the correction entries is preserved to default experience storehouse;
Every correction entries includes:Current written handwriting, the preferred recognition result of the written handwriting and final recognition result.I.e.
The control information of recognition result of the user to choosing automatically is recorded, rule of thumb the correction entries information of storehouse record can be with
The convenient accuracy for assessing writing identification.
Further, in another embodiment, after the experience storehouse described in structure above-described embodiment, can also be based on described
Experience storehouse carries out automatic correction process to the recognition result chosen automatically.I.e. in step s 13 from multiple candidate's recognition results
After selecting a preferred recognition result, first inquire about in experience storehouse and whether there is correction corresponding with the preferably recognition result
Record, if in the presence of being corrected according to the correction entries to preferred recognition result.Accordingly, it is described to preferred recognition result
Output displaying is carried out to refer to:Output displaying is carried out to the preferred recognition result after correction.
For example, with reference to shown in figure 3, recognition result A is initially selected in identification process, whether inquiry experience includes in storehouse
Recognition result A correction entries, if inquiring more correction entrieies for being replaced by other recognition results B of recognition result A, lead
It is dynamic that this recognition result is replaced with into B.Thus, can based on the correction empirical value of user, realize to preferred recognition result from
Dynamic correction, improve identification accuracy.
Alternatively, in the correction empirical value based on user, the automatic timing to preferred recognition result, concrete mode are realized
May also include for:If correction entries corresponding with the preferably recognition result there are more than two in the experience storehouse, obtain wherein
A time newest correction entries, is corrected according to this correction entries to preferred recognition result.
In an alternative embodiment, in above-mentioned steps S11, current written handwriting is identified respectively by multiple identification models
Specific identification method may include:Calculate of each known person's handwriting in current written handwriting person's handwriting storehouse corresponding with identification model
With degree, recognition result of the identification model to current written handwriting is determined according to the matching degree.Wherein, each identification model
A person's handwriting storehouse is corresponded to respectively, and the person's handwriting storehouse includes multiple known person's handwritings.Such as Text region model is for literal pool, text
It is 3500 or so that commonly used word is included in character library, because the Chinese character utilization rate beyond commonly used word is very low, when written handwriting exceeds
During the scope of literal pool, directly it is judged to mismatching.
Thus, the recognition result of each identification model output has a corresponding matching degree.Alternatively, above-mentioned steps
A preferred recognition result is selected in S13 from multiple candidate's recognition results, concrete mode may include:Identified from multiple candidates
As a result one candidate's recognition result of matching degree highest is selected in, as preferred recognition result.
Further, in one embodiment, the specific implementation of the step S11 may include:Obtain each identification mould
Predefined first priority of type, identification model is called according to the order of the first priority from high to low, passes through each identification mould
Type identifies current written handwriting respectively.The priority level (i.e. the first priority) of each identification model is pre-set, is pressed
Call each identification model that current written handwriting is identified successively according to priority level.For example, pre-set Text region
Model is TP top priority, and flow chart identification model is lowest priority, then preferential to call during active user's handwriting input
Hand-written person's handwriting is identified Text region model, and hand-written person's handwriting is identified last call flow chart identification model.
In another embodiment, in the step S11, preset identification model is called, is distinguished by multiple identification models
Identifying the specific implementation of current written handwriting can also be:The second of each identification model is determined according to history identification record
Priority, identification model is called according to the order of the second priority from high to low, is identified respectively currently by each identification model
Written handwriting.I.e. multiple identification models are dynamically adapted priority orders.
Alternatively, the logic of multiple identification model dynamic adjustment priority orders can be:Moved according to identification types before
State adjusts priority orders, for example, last recognition result user selection is word, is then arranged to Text region model most
High priority.
Further, in one embodiment, can also be according to written handwriting size dynamic adjustment priority orders etc..Such as:
There is larger gap (size gap, which reaches, to impose a condition) in the size of this written handwriting, then sentence with the size of last time written handwriting
This disconnected writing identification is different from last time writing identification types, by the low one-level of the priority of the identification model in limit priority
Processing.For example, last recognition result user selection is word, then Text region model is arranged to highest by system automatically
Priority, however this user writing for figure, and the size of figure is more than twice of writing words size, then can determine that
What user currently write is not literal type, and the priority of Text region model is reduced into coagulation automatically.Alternatively, for
The priority for originally coming the identification model after Text region model also sequentially degrades.
Further, in one embodiment, recognition result of each identification model to the written handwriting is obtained, as time
Recognition result is selected, including:Judge identification model whether the matching degree corresponding to the recognition result of current written handwriting is more than or
Equal to default first matching degree (such as 80%), if so, the recognition result of acquisition identification model is as candidate's recognition result, it is no
Then, the recognition result of the identification model is ignored.When there is a fairly large number of identification model, by the present embodiment, first to each knowledge
The recognition result of other model is screened, and it is poor to ignore wherein recognition effect, be advantageous to improve in candidate's step choose it is preferred
The efficiency and accuracy of recognition result.
In one embodiment, preset identification mould is called according to the order of the priority of the first priority/second from high to low
Type, identify that current written handwriting can be further adjusted to respectively by each identification model:Detect the identification mould currently called
Type to the matching degree corresponding to the recognition result of current written handwriting whether be more than or equal to setting the second matching degree (such as
95%), if so, stopping calling remaining identification model.
When the recognizer of identification module has carried the matching degree of recognition result, according to sequentially successively in identification process
Call identification model, if recognition result meets certain matching degree (such as 95%), directly return this and before this
The recognition result of the identification module of identification is performed, otherwise calls next identification model.If the in addition, recognizer of identification module
Minimum matching limit (such as 50%) is simply set, when the matching degree that written handwriting is calculated for it is more than the minimum matching
During limit, just think to identify successfully, recognition result corresponding to output, otherwise it is assumed that recognition failures;In this case, identify successfully
When matching degree corresponding to recognition result be recognizer results of calculation, matching degree corresponding to recognition result during recognition failures
It is then 0.
When there is a fairly large number of identification model, by the present embodiment, when having detected that recognition result meets sets requirement
When, other follow-up identification models will no longer carry out the identification of this written handwriting, due to equal without all preset identification models
This writing identification is carried out, is advantageous to save system resource, improves writing recognition efficiency.
In an alternative embodiment, the identification model is identification plug-in unit;The identification plug-in unit meets condition:Input writing
Person's handwriting, export the recognition result of the written handwriting.Accordingly, the specific implementation of the step S11 may include:Call and know
Identification plug-in unit in other container, current written handwriting is identified respectively by multiple identification plug-in units;The identification container adds in advance
It is loaded with multiple different identification plug-in units.
With reference to shown in figure 6, identification container defines unified interface, and identification plug-in unit supports input writing person's handwriting, output identification
As a result.Written handwriting is by comprising order and point set information structure, including touch point, mouse point etc., recognition result are then one herein
The unified identification object of kind, including character, figure etc.;Different types of recognition result then has different presentation modes.It is all full
The identification plug-in unit of this interface of foot can be added in the identification container, for example, output is also regarded as one as former state by person's handwriting
The special identification plug-in unit of kind, it can be loaded into the identification container.For the calling of the identification plug-in unit in identification container, it is usually
Called according to its sequence in container is identified.Identify container in identification plug-in unit, can according to the first priority ranking of setting,
During identification is write, identify that the identification plug-in unit in container can also adjust its order according to the second precedence information dynamic.
Alternatively, the identification plug-in unit includes:Text region plug-in unit, figure identification plug-in unit, music score identification plug-in unit, flow chart identification plug-in unit
In it is two or more.
In another embodiment, the writing recognition methods also includes:The identification plug-in unit in identifying container is being called, is being passed through
Before multiple identification plug-in units identify current written handwriting respectively, the priority of each identification plug-in unit in identification container is set, and
Activate each identification plug-in unit.In each writing identification process, without interim activation identification plug-in unit, be advantageous to save the time,
Further improve recognition efficiency.
It should be noted that for foregoing each method embodiment, in order to which simplicity describes, it is all expressed as a series of
Combination of actions, but those skilled in the art should know, the present invention is not limited by described sequence of movement, because according to
According to the present invention, some steps can use other orders or carry out simultaneously.In addition, can also any group be carried out to above-described embodiment
Close, obtain other embodiments.
Based on the writing recognition methods identical thought in above-described embodiment, the present invention also provide writing identification device,
The device can be used for performing above-mentioned writing recognition methods.For convenience of description, the structural representation of identification device embodiment is write
In, the part related to the embodiment of the present invention is illustrate only, it will be understood by those skilled in the art that schematic structure is not formed
Restriction to device, it can include than illustrating more or less parts, either combine some parts or different part cloth
Put.
Fig. 7 is the schematic diagram of the writing identification device of one embodiment of the invention;As shown in fig. 7, the present embodiment
Writing identification device includes:
Calling module 510, when acting on the written information on touch-screen/contact panel for detecting, by multiple pre-
The identification model put identifies the written handwriting corresponding to the written information respectively;
Collection module 520, for obtaining recognition result of each identification model to the written handwriting, identified as candidate
As a result;
And module 530 is chosen, for selecting a preferred recognition result from multiple candidate's recognition results, to excellent
Recognition result is selected to carry out output displaying.
The writing identification device of above-described embodiment, touch-screen/contact panel is acted on detecting by calling module 510
On written information when, call multiple identification models to identify current written handwriting respectively, obtained by collection module 520 each
Identification model obtains multiple candidate's recognition results to the recognition result of the written handwriting;Further choosing module 530 can be from more
A preferred recognition result is selected in individual candidate's recognition result, and output displaying is carried out to preferred recognition result.User need not
The identification model that advance clear and definite terminal device currently enables, just can be real without selected manually in advance or switching identification model
Now to realizing effective identification of person's handwriting, writing recognition efficiency is improved.
In one embodiment, the writing identification device also includes expansion module.The expansion module, for detecting pair
During the trigger action instruction of the preferably recognition result, output exhibition is carried out to other candidate's recognition results of this written handwriting
Show.
Further, in one embodiment, the writing identification device also includes result determining module.The result determines
Module, instruction is chosen to any candidate's recognition result in other candidate's recognition results for receiving, candidate's knowledge that will be selected
Final recognition result of the other result as this writing identification;Or if for not received to any candidate in setting time
Recognition result chooses instruction, the final recognition result using the preferably recognition result as this writing identification.
Further, in one embodiment, the writing identification device also includes logging modle.The logging modle, use
In obtaining the control information to preferred recognition result, correction entries corresponding to generation, the correction entries is preserved to default
Experience storehouse;Every correction entries includes:Current written handwriting, preferably recognition result and final recognition result.
Further, in one embodiment, the writing identification device also includes automatic correction module.The automatic correction
Module, for after choosing module 530 and a preferred recognition result is selected from multiple candidate's recognition results, inquiring about experience
It whether there is correction entries corresponding with the preferably recognition result in storehouse, if in the presence of according to the correction entries to preferred knowledge
Other result is corrected.
Accordingly, the selection module 530 is specifically used for carrying out output displaying to the preferred recognition result after correction.
In one embodiment, the automatic correction module, if being additionally operable to inquire in the experience storehouse and the preferred knowledge
Correction entries corresponding to other result has more than two, then obtains a wherein time newest correction entries, is corrected according to this
Record is corrected to preferred recognition result.
In one embodiment, above-mentioned each identification model identifies that the mode of current written handwriting includes:Calculate current book
The matching degree of each known person's handwriting in person's handwriting person's handwriting storehouse corresponding with identification model is write, the identification is determined according to the matching degree
Recognition result of the model to current written handwriting;Wherein, each identification model corresponds to a person's handwriting storehouse respectively, in the person's handwriting storehouse
Including multiple known person's handwritings.
Based on this, in one embodiment, the selection module 530 is specifically used for selecting from multiple candidate's recognition results
With degree one candidate's recognition result of highest, as preferred recognition result.
In one embodiment, the calling module 510, it is preferential specifically for obtaining each identification model predefined first
Level, identification model is called according to the order of the first priority from high to low, identifies current book respectively by each identification model
Write person's handwriting.
In another embodiment, the calling module 510, it may also be used for each identification mould is determined according to history identification record
Second priority of type, identification model is called according to the order of the second priority from high to low, is distinguished by each identification model
Identify current written handwriting.Alternatively, the mode of the second priority of each identification model is determined according to history identification record
It may include:It is determined that identification model corresponding to the preferred recognition result of last writing identification, true by the priority of the identification model
It is set to limit priority, preferentially to call the identification model.
In one embodiment, the collection module 520, specifically for judging identification of the identification model to current written handwriting
Whether as a result corresponding matching degree is more than or equal to default first matching degree, if so, obtaining the recognition result of identification model
As candidate's recognition result, otherwise, ignore the recognition result of the identification model.
In one embodiment, the calling module 510, be additionally operable to according to the priority of the first priority/second from height to
Low order calls preset identification model, during identifying current written handwriting respectively by each identification model, detection
Whether the identification model currently called is more than or equal to setting to the matching degree corresponding to the recognition result of current written handwriting
Second matching degree, if so, stopping calling remaining identification model.
In one embodiment, identification model described above can be identification plug-in unit;The identification plug-in unit meets condition:Input book
Person's handwriting is write, exports the recognition result of the written handwriting.The calling module 510 is particularly used in, and is called in identification container
Plug-in unit is identified, current written handwriting is identified respectively by multiple identification plug-in units;It is described identification container be pre-loaded with it is multiple not
Same identification plug-in unit.Alternatively, the identification plug-in unit includes:Text region plug-in unit, figure identification plug-in unit, music score identification plug-in unit,
It is two or more in flow chart identification plug-in unit.
In one embodiment, above-mentioned writing identification device also includes:Setup module, each knowledge in container is identified for setting
The priority of other plug-in unit, and activate each identification plug-in unit.
It should be noted that writing identification device and the writing recognition methods of the present invention are based on same design, know in writing
In the embodiment of other device, the content such as information exchange, implementation procedure between each module, with a pair of above method embodiment 1
Should, the technical characteristic and its advantage illustrated in the embodiment of above-mentioned writing recognition methods is applied to writing identification device
In embodiment, hereby give notice that.
In addition, in the embodiment of the writing identification device of above-mentioned example, the logical partitioning of each program module is only citing
Illustrate, can be as needed in practical application, such as examined for the facility of the realization of the configuration requirement or software of corresponding hardware
Consider, above-mentioned function distribution completed by different program module, will the internal structure of the writing identification device be divided into not
Same program module, to complete all or part of function described above.
It will appreciated by the skilled person that realizing all or part of flow in above-described embodiment method, being can
To instruct the hardware of correlation to complete by computer program, described program can be stored in a computer-readable storage and be situated between
In matter, as independent production marketing or use.Described program upon execution, can perform embodiment each as described above method it is complete
Portion or part steps.Wherein, described storage medium can be magnetic disc, CD, read-only memory (Read-Only
Memory, ROM) or random access memory (Random Access Memory, RAM) etc..
Accordingly, a kind of storage medium is also provided in one embodiment, is stored thereon with computer program, wherein, the journey
Any one writing recognition methods in each embodiment as described above is realized when sequence is executed by processor.
Above computer storage medium, by the computer program of its storage, user is realized without advance clear and definite terminal
The identification model that equipment currently enables, without selected manually in advance or switching identification model, written handwriting is realized automatically
Effectively identification, it is possible to increase writing recognition efficiency.
In addition, the storage medium is also settable with a kind of computer equipment, place is also included in the computer equipment
Manage device, during program in storage medium described in the computing device, can realize the method for the various embodiments described above whole or
Part steps.
Accordingly, a kind of computer equipment is also provided in one embodiment, and the computer equipment includes memory, processor
And storage is on a memory and the computer program that can run on a processor, wherein, realize during computing device described program
Any one writing recognition methods in each embodiment as described above.
Above computer equipment, by the computer program run on the processor, user is realized without bright in advance
The identification model that true terminal device currently enables, without advance manual switching identification model, realizes having for written handwriting automatically
Effect identification, it is possible to increase writing recognition efficiency.
In the above-described embodiments, the description to each embodiment all emphasizes particularly on different fields, and does not have the portion being described in detail in some embodiment
Point, it may refer to the associated description of other embodiments.
Embodiment described above only expresses the several embodiments of the present invention, it is impossible to is interpreted as to the scope of the claims of the present invention
Limitation.It should be pointed out that for the person of ordinary skill of the art, without departing from the inventive concept of the premise,
Various modifications and improvements can be made, these belong to protection scope of the present invention.Therefore, the protection domain of patent of the present invention
It should be determined by the appended claims.
Claims (14)
1. one kind writing recognition methods, it is characterised in that including:
When detecting the written information of effect on the touchscreen, the written information is identified respectively by multiple preset identification models
Corresponding written handwriting;
Recognition result of each identification model to the written handwriting is obtained, as candidate's recognition result;
A preferred recognition result is selected from multiple candidate's recognition results, output displaying is carried out to preferred recognition result.
2. writing recognition methods according to claim 1, it is characterised in that carry out exporting displaying to preferred recognition result
Afterwards, in addition to:
When detecting the trigger action instruction to the preferably recognition result, to other candidate's recognition results of this written handwriting
Carry out output displaying.
3. writing recognition methods according to claim 2, it is characterised in that detecting to the preferably recognition result
When trigger action instructs, after carrying out output displaying to other candidate's recognition results of this written handwriting, in addition to:
Instruction is chosen to any candidate's recognition result in other candidate's recognition results if receiving, candidate's identification that will be selected is tied
Final recognition result of the fruit as this writing identification;Or
Instruction is chosen to any candidate's recognition result if not received in setting time, regard the preferably recognition result as this
The final recognition result of secondary writing identification.
4. writing recognition methods according to claim 3, it is characterised in that receive to any in other candidate's recognition results
Candidate's recognition result chooses instruction, using selected candidate's recognition result as this writing identification final recognition result it
Afterwards, in addition to:
The control information to preferred recognition result is obtained, correction entries corresponding to generation, the correction entries is preserved to default
Experience storehouse;Wherein, correction entries includes:Current written handwriting, the preferred recognition result corresponding with writing notes
And final recognition result.
5. writing recognition methods according to claim 4, it is characterised in that described to be chosen from multiple candidate's recognition results
Go out after a preferred recognition result, in addition to:
It whether there is correction entries corresponding with the preferably recognition result in inquiry experience storehouse, if in the presence of according to the correction
Record is corrected to preferred recognition result;
It is described to carry out output displaying to preferred recognition result, including:Output displaying is carried out to the preferred recognition result after correction.
6. writing recognition methods according to claim 5, it is characterised in that according to the correction entries to preferred identification knot
Fruit is corrected, including:
If correction entries corresponding with the preferably recognition result there are more than two in the experience storehouse, it is newest to obtain the wherein time
A correction entries, preferred recognition result is corrected according to this correction entries.
7. writing recognition methods according to any one of claims 1 to 6, it is characterised in that
Current written handwriting is identified respectively by multiple preset identification models, including:Calculate current written handwriting and identification
The matching degree of each known person's handwriting, determines the identification model to current book according to the matching degree in person's handwriting storehouse corresponding to model
Write the recognition result of person's handwriting;Wherein, each identification model corresponds to a person's handwriting storehouse respectively, and the person's handwriting storehouse includes multiple known
Person's handwriting;
A preferred recognition result is selected from multiple candidate's recognition results, including:Selected from multiple candidate's recognition results
One candidate's recognition result of matching degree highest, as preferred recognition result.
8. writing recognition methods according to claim 7, it is characterised in that known respectively by multiple preset identification models
Not current written handwriting, including:
Predefined first priority of each identification model is obtained, is called according to the order of the first priority from high to low preset
Identification model, identify current written handwriting respectively by each identification model;
And/or
The second priority of each identification model is determined according to history identification record, according to the order of the second priority from high to low
Preset identification model is called, identifies current written handwriting respectively by each identification model.
9. writing recognition methods according to claim 8, it is characterised in that each identification is determined according to history identification record
Second priority of model, including:
It is determined that identification model corresponding to the preferred recognition result of last writing identification, the priority of the identification model is defined as
Limit priority, preferentially to call the identification model.
10. writing recognition methods according to claim 8, it is characterised in that obtain each identification model to the writing
The recognition result of person's handwriting, as candidate's recognition result, including:
Judge whether identification model is more than or equal to default the to the matching degree corresponding to the recognition result of current written handwriting
One matching degree, if so, otherwise the recognition result for obtaining identification model, abandons the identification model as candidate's recognition result
Recognition result.
11. writing recognition methods according to claim 8, it is characterised in that according to the priority of the first priority/second from
High to Low order calls preset identification model, identifies current written handwriting respectively by each identification model, in addition to:
Detect whether the identification model currently called is more than or waits to the matching degree corresponding to the recognition result of current written handwriting
In the second matching degree of setting, if so, stopping calling remaining identification model.
12. one kind writing identification device, it is characterised in that including:
Calling module, when acting on the written information on touch-screen/contact panel for detecting, pass through multiple preset identifications
Model identifies the written handwriting corresponding to the written information respectively;
Collection module, for obtaining recognition result of each identification model to the written handwriting, as candidate's recognition result;
And module is chosen, for selecting a preferred recognition result from multiple candidate's recognition results, to preferred identification knot
Fruit carries out output displaying.
13. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that the program is by processor
The step of claim 1 to 11 any methods described is realized during execution.
14. a kind of computer equipment, including memory, processor and storage are on a memory and the meter that can run on a processor
Calculation machine program, it is characterised in that the step of any methods described of claim 1 to 11 is realized during the computing device described program
Suddenly.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711184637.0A CN107861684A (en) | 2017-11-23 | 2017-11-23 | Write recognition methods, device, storage medium and computer equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711184637.0A CN107861684A (en) | 2017-11-23 | 2017-11-23 | Write recognition methods, device, storage medium and computer equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107861684A true CN107861684A (en) | 2018-03-30 |
Family
ID=61703511
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711184637.0A Pending CN107861684A (en) | 2017-11-23 | 2017-11-23 | Write recognition methods, device, storage medium and computer equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107861684A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108875748A (en) * | 2018-06-27 | 2018-11-23 | 上海连尚网络科技有限公司 | Generation method, equipment and the computer-readable medium of wireless access points information |
CN110379234A (en) * | 2019-07-23 | 2019-10-25 | 广东小天才科技有限公司 | A kind of study coach method and device |
CN110658934A (en) * | 2019-09-25 | 2020-01-07 | 福建工大云技术有限公司 | Method and device for changing touch identification information based on movement of stylus |
CN111062401A (en) * | 2019-09-27 | 2020-04-24 | 商汤国际私人有限公司 | Stacked object identification method and device, electronic device and storage medium |
CN112052713A (en) * | 2020-04-15 | 2020-12-08 | 上海摩象网络科技有限公司 | Video processing method and device and handheld camera |
CN112703479A (en) * | 2018-11-30 | 2021-04-23 | 深圳市柔宇科技股份有限公司 | Writing device control method and writing device |
CN115937861A (en) * | 2022-11-30 | 2023-04-07 | 广州市保伦电子有限公司 | Multi-person synchronous writing recognition method and system based on touch screen |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0632403A2 (en) * | 1993-06-30 | 1995-01-04 | Microsoft Corporation | Handwritten symbol recognizer |
CN101149804A (en) * | 2006-09-19 | 2008-03-26 | 北京三星通信技术研究有限公司 | Self-adaptive hand-written discrimination system and method |
CN104573683A (en) * | 2013-10-21 | 2015-04-29 | 富士通株式会社 | Character string recognizing method and device |
CN104933084A (en) * | 2015-05-04 | 2015-09-23 | 上海智臻网络科技有限公司 | Method, apparatus and device for acquiring answer information |
CN105247540A (en) * | 2013-06-09 | 2016-01-13 | 苹果公司 | Managing real-time handwriting recognition |
-
2017
- 2017-11-23 CN CN201711184637.0A patent/CN107861684A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0632403A2 (en) * | 1993-06-30 | 1995-01-04 | Microsoft Corporation | Handwritten symbol recognizer |
CN101149804A (en) * | 2006-09-19 | 2008-03-26 | 北京三星通信技术研究有限公司 | Self-adaptive hand-written discrimination system and method |
CN105247540A (en) * | 2013-06-09 | 2016-01-13 | 苹果公司 | Managing real-time handwriting recognition |
CN104573683A (en) * | 2013-10-21 | 2015-04-29 | 富士通株式会社 | Character string recognizing method and device |
CN104933084A (en) * | 2015-05-04 | 2015-09-23 | 上海智臻网络科技有限公司 | Method, apparatus and device for acquiring answer information |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108875748A (en) * | 2018-06-27 | 2018-11-23 | 上海连尚网络科技有限公司 | Generation method, equipment and the computer-readable medium of wireless access points information |
CN112703479A (en) * | 2018-11-30 | 2021-04-23 | 深圳市柔宇科技股份有限公司 | Writing device control method and writing device |
CN110379234A (en) * | 2019-07-23 | 2019-10-25 | 广东小天才科技有限公司 | A kind of study coach method and device |
CN110658934A (en) * | 2019-09-25 | 2020-01-07 | 福建工大云技术有限公司 | Method and device for changing touch identification information based on movement of stylus |
CN111062401A (en) * | 2019-09-27 | 2020-04-24 | 商汤国际私人有限公司 | Stacked object identification method and device, electronic device and storage medium |
CN112052713A (en) * | 2020-04-15 | 2020-12-08 | 上海摩象网络科技有限公司 | Video processing method and device and handheld camera |
WO2021208256A1 (en) * | 2020-04-15 | 2021-10-21 | 上海摩象网络科技有限公司 | Video processing method and apparatus, and handheld camera |
CN112052713B (en) * | 2020-04-15 | 2022-01-11 | 上海摩象网络科技有限公司 | Video processing method and device and handheld camera |
CN115937861A (en) * | 2022-11-30 | 2023-04-07 | 广州市保伦电子有限公司 | Multi-person synchronous writing recognition method and system based on touch screen |
CN115937861B (en) * | 2022-11-30 | 2023-09-08 | 广东保伦电子股份有限公司 | Multi-user synchronous writing identification method and system based on touch screen |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107861684A (en) | Write recognition methods, device, storage medium and computer equipment | |
US10409418B2 (en) | Electronic device operating according to pressure state of touch input and method thereof | |
CN101464741B (en) | Touch panel and its use method and notebook computer with the same | |
US8363949B2 (en) | Character recognition for overlapping textual user input | |
JP3471920B2 (en) | Method for determining a computationally significant response and method for operating a processor control system | |
US7932895B2 (en) | Control of an electronic device using a gesture as an input | |
CN103294257B (en) | The apparatus and method for being used to guide handwriting input for handwriting recognition | |
CN107194331A (en) | A kind of fingerprint identification method and mobile terminal | |
EP2650766A1 (en) | Multi-character continuous handwriting input method | |
CN106527888B (en) | The method and device of the screen sliding lookup page | |
JPH07182446A (en) | Operating method of machine | |
US20100231597A1 (en) | Calculator and computer-readable medium | |
CN103218160A (en) | Man-machine interaction method and terminal | |
US9588678B2 (en) | Method of operating electronic handwriting and electronic device for supporting the same | |
CN107798228A (en) | A kind of face identification method and mobile terminal | |
KR101927064B1 (en) | Apparus and method for generating summary data about e-book | |
CN105630397A (en) | Method and terminal equipment for opening popup boxes | |
US20120151340A1 (en) | Global settings for the enablement of culture-based gestures | |
CN104199608B (en) | The method of quick open record and touch terminal on touching terminal | |
CN104102704A (en) | System control displaying method and system control displaying device | |
CN107368205A (en) | A kind of hand-written inputting method and mobile terminal | |
US20110316887A1 (en) | Electronic device with a touch screen and touch operation control method utilized thereby | |
CN107368249A (en) | A kind of touch control operation recognition methods, device and mobile terminal | |
CN106951258A (en) | The operating method and mobile terminal of a kind of mobile terminal | |
CN110442266A (en) | Object identification method, device, electronic equipment and storage medium |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180330 |