CN107563365A - Electronic installation, picture-text image identification system and method - Google Patents
Electronic installation, picture-text image identification system and method Download PDFInfo
- Publication number
- CN107563365A CN107563365A CN201610519283.XA CN201610519283A CN107563365A CN 107563365 A CN107563365 A CN 107563365A CN 201610519283 A CN201610519283 A CN 201610519283A CN 107563365 A CN107563365 A CN 107563365A
- Authority
- CN
- China
- Prior art keywords
- picture
- text image
- meeting
- module
- calendar
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Facsimiles In General (AREA)
Abstract
The present invention provides a kind of picture-text image identification system, and the system includes：Determining module, for determining the scope to be identified of picture-text image；Module is recognized, for recognizing the scope to be identified to obtain a facsimile file；And sending module, for the facsimile file to be sent to the related personnel related to the picture-text image.The present invention also provides a kind of picture-text image discrimination method, and the electronic installation with the picture-text image identification system and method.The present invention can change into picture-text image facsimile file, and facsimile file is shared with the related personnel related to the picture-text image.
Description
Technical field
The present invention relates to image processing field, more particularly to a kind of picture-text image identification system and method, and apply the figure
The electronic installation of literary image recognition system and method.
Background technology
Generally, we can be by the item instant recording for worrying to omit on many pieces of self-stick notes.During multi-person conference,
Word and scribble that everybody absorbs all the useful ideas often are record on blank.However, these are recorded in self-stick notes, the word on blank with
Scribble but can not be to be organized into editable text, and is shared with related personnel.
The content of the invention
In view of the foregoing, it is necessary to a kind of picture-text image identification system is provided, picture-text image can be changed into picture and text
File, and facsimile file is shared with the related personnel related to the picture-text image.
In view of the foregoing, it is necessary to a kind of picture-text image discrimination method is provided, picture-text image can be changed into picture and text
File, and facsimile file is shared with the related personnel related to the picture-text image.
In view of the foregoing, it is necessary to a kind of electronic installation is provided, picture-text image can be changed into facsimile file, and scheme
Literary sharing files give the related related personnel of the picture-text image.
The picture-text image identification system includes：
Determining module, for determining the scope to be identified of picture-text image；
Module is recognized, for recognizing the scope to be identified to obtain a facsimile file；And
Sending module, for the facsimile file to be sent to the related personnel related to the picture-text image.
Preferably, the system also includes：
Acquisition module, for obtaining the picture-text image；
The acquisition module, it is additionally operable to determine acquisition time and the gain location for obtaining the picture-text image；
Analysis module, for determining that the recognition mode of the picture-text image is certainly according to the acquisition time and gain location
Dynamic model formula or manual mode.
Preferably, the analysis module is additionally operable to：When the acquisition time and the meeting of the corresponding meeting described in calendar
The view time matches, and when the meeting-place of the meeting described in the gain location and the calendar matches, it is determined that
The recognition mode of the picture-text image is automatic mode；And
Mismatched when the acquisition time and the time of meeting of the meeting described in calendar, and/or the acquisition ground
When point and the meeting-place of the meeting described in the calendar mismatch, the recognition mode for determining the picture-text image is hand
Dynamic model formula.
Preferably, the related personnel refers to the personnel for participating in the meeting.
Preferably, the determining module is additionally operable to：
According to the operation of user, the user region for being not required to recognition character specified in the picture-text image is defined as
Picture, and other regions in the picture-text image in addition to the region are defined as the scope to be identified.
Preferably, the step of identification module obtains the facsimile file includes：
Recognize the scope to be identified and obtain picture and word block；
The picture and word block are compared, obtains relative position parameter of each word block relative to the picture
And/or relative size parameter；
Above-mentioned picture is handled according to default picture processing mode, and recognizes each word block to obtain word
Data；
The picture after the processing and lteral data are carried out according to the relative position parameter and/or relative size parameter
Merge so as to obtain the facsimile file.
Preferably, the identification module is additionally operable to:
Analysis lteral data obtains contact details and keyword；
Contact details to be stored are asked the user whether, and the operation for responding user stores the contact details；And
The facsimile file is carried out by classified and stored according to the keyword.
The picture-text image discrimination method includes：
Step is determined, determines the scope to be identified of picture-text image；
Step is recognized, recognizes the scope to be identified to obtain a facsimile file；And
Forwarding step, the facsimile file is sent to the related personnel related to the picture-text image.
Preferably, this method also includes before above-mentioned determination step：
First obtaining step, obtain the picture-text image；
Second acquisition module, it is determined that obtaining acquisition time and the gain location of the picture-text image；And
Analytical procedure, determine that the recognition mode of the picture-text image is automatic mold according to the acquisition time and gain location
Formula or manual mode.
Preferably, in the analytical procedure：
Match when the acquisition time with the time of meeting of the corresponding meeting described in calendar, and the gain location
When matching with the meeting-place of the meeting described in the calendar, the recognition mode for determining the picture-text image is automatic
Pattern；And
Mismatched when the acquisition time and the time of meeting of the meeting described in calendar, and/or the acquisition ground
When point and the meeting-place of the meeting described in the calendar mismatch, the recognition mode for determining the picture-text image is hand
Dynamic model formula.
Preferably, the related personnel refers to the personnel for participating in the meeting.
Preferably, in the determination step：
According to the operation of user, the user region for being not required to recognition character specified in the picture-text image is defined as
Picture, and other regions in the picture-text image in addition to the region are defined as the scope to be identified.
Preferably, the step of acquisition facsimile file includes：
Recognize the scope to be identified and obtain picture and word block；
The picture and word block are compared, obtains relative position parameter of each word block relative to the picture
And/or relative size parameter；
Above-mentioned picture is handled according to default picture processing mode, and recognizes each word block to obtain word
Data；
The picture after the processing and lteral data are carried out according to the relative position parameter and/or relative size parameter
Merge so as to obtain the facsimile file.
Preferably, this method also includes step：
Analysis lteral data obtains contact details and keyword；
Contact details to be stored are asked the user whether, and the operation for responding user stores the contact details；And
The facsimile file is carried out by classified and stored according to the keyword.
The electronic installation includes：
Memory；
At least one processor；
Multiple modules are stored in the memory and by least one computing devices, wherein, the plurality of module
Including：
Determining module, for determining the scope to be identified of picture-text image；
Module is recognized, for recognizing the scope to be identified to obtain a facsimile file；And
Sending module, for the facsimile file to be sent to the related personnel related to the picture-text image.
Preferably, the multiple module also includes：
Acquisition module, for obtaining the picture-text image；
The acquisition module, it is additionally operable to determine acquisition time and the gain location for obtaining the picture-text image；
Analysis module, for determining that the recognition mode of the picture-text image is certainly according to the acquisition time and gain location
Dynamic model formula or manual mode.
Preferably, the analysis module is additionally operable to：
Match when the acquisition time with the time of meeting of the corresponding meeting described in calendar, and the gain location
When matching with the meeting-place of the meeting described in the calendar, the recognition mode for determining the picture-text image is automatic
Pattern；And
Mismatched when the acquisition time and the time of meeting of the meeting described in calendar, and/or the acquisition ground
When point and the meeting-place of the meeting described in the calendar mismatch, the recognition mode for determining the picture-text image is hand
Dynamic model formula.
Preferably, the related personnel refers to the personnel for participating in the meeting.
Preferably, the determining module is additionally operable to：
According to the operation of user, the user region for being not required to recognition character specified in the picture-text image is defined as
Picture, and other regions in the picture-text image in addition to the region are defined as the scope to be identified.
Preferably, the step of identification module obtains the facsimile file includes：
Recognize the scope to be identified and obtain picture and word block；
The picture and word block are compared, obtains relative position parameter of each word block relative to the picture
And/or relative size parameter；
Above-mentioned picture is handled according to default picture processing mode, and recognizes each word block to obtain word
Data；
The picture after the processing and lteral data are carried out according to the relative position parameter and/or relative size parameter
Merge so as to obtain the facsimile file.
Preferably, the identification module is additionally operable to:
Analysis lteral data obtains contact details and keyword；
Contact details to be stored are asked the user whether, and the operation for responding user stores the contact details；And
The facsimile file is carried out by classified and stored according to the keyword.
Compared to prior art, electronic installation provided by the present invention, picture-text image identification system and method will can be schemed
Literary image changes into facsimile file, and facsimile file is shared with the related personnel related to the picture-text image.
Brief description of the drawings
Fig. 1 is the running environment figure of picture-text image identification system preferred embodiment of the present invention.
Fig. 2 is the functional block diagram of picture-text image identification system preferred embodiment of the present invention.
Fig. 3 A-3B illustrate picture-text image.
Fig. 4 is the flow chart of picture-text image discrimination method preferred embodiment of the present invention.Main element symbol description
| Electronic installation | 1 |
| Picture-text image identification system | 10 |
| Acquisition module | 101 |
| Analysis module | 102 |
| Determining module | 103 |
| Recognize module | 104 |
| Sending module | 105 |
| Camera | 11 |
| Communication apparatus | 12 |
| Location equipment | 13 |
| Display screen | 14 |
| Memory | 15 |
| Processor | 16 |
| Calendar | 17 |
| Picture-text image | 2 |
| Region | 21 |
Following embodiment will combine above-mentioned accompanying drawing and further illustrate the present invention.
Embodiment
As shown in fig.1, it is the applied environment figure of picture-text image identification system preferred embodiment of the present invention.In the present embodiment
In, electronic installation 1 is include but not limited to, picture-text image identification system 10, camera 11, communication apparatus 12, location equipment
13rd, display screen 14, memory 15, processor 16.The electronic installation 1 can be mobile phone, tablet personal computer, personal digital assistant,
The equipment such as PC.It should be noted that the present embodiment is only the simple declaration to the structure of the electronic installation 1, at it
In his embodiment, the electronic installation 1 can also include other elements for example, circuit system, sound effect system, battery, operation system
System etc..
In the present embodiment, the picture-text image identification system 10 can be used for recognizing picture-text image, and picture-text image is turned
Related personnel is shared with after chemical conversion facsimile file.
In one embodiment, the picture-text image can refer to include not editable picture and not editable word
Image file.The form of the picture-text image for example can be tif forms, jpg forms.The facsimile file refers to include compiling
The word and the file of editable picture collected.The form of the facsimile file for example can be doc forms, PPT forms.Need
Bright, editable picture can refer to that for example adjustment can be zoomed in and out to the size of picture, and color of picture etc. can be belonged to
Property is changed.Not editable picture can also contain not editable word in itself.
In other embodiments, the picture-text image may also mean that including editable picture and not editable
The image file of word.The facsimile file can also refer to the file including editable word and not editable picture.
In the present embodiment, the camera 11 can be built in the electronic installation 1 or be external in the electronic installation
1。
In the present embodiment, the communication module 12 can be the electronic installation 1 by cable network or wireless network with
External equipment (not shown) establishes communication connection.The cable network can be any types of traditional wire communication, such as
Internet, LAN.The wireless network can be any types of conventional wireless communication, such as radio, Wireless Fidelity
(Wireless Fidelity, WIFI), honeycomb, satellite, broadcast etc..Wireless communication technique can include, but not limited to the whole world
GSM (Global System for Mobile Communications, GSM), GPRS
(General Packet Radio Service, GPRS), CDMA (Code Division Multiple Access,
CDMA), WCDMA (W-CDMA), CDMA2000, IMT single carrier (IMT Single Carrier), enhanced data
Speed GSM evolution (Enhanced Data Rates for GSM Evolution, EDGE), Long Term Evolution (Long-
Term Evolution, LTE), senior long term evolution technology, time-division Long Term Evolution (Time-Division LTE, TD-
LTE), high performance radio LAN (High Performance Radio Local Area Network, HiperLAN),
High performance radio wide area network (High Performance Radio Wide Area Network, HiperWAN), local are more
Appoint sending service (Local Multipoint Distribution Service, LMDS), full micro-wave access global inter communication
(Worldwide Interoperability for Microwave Access, WiMAX), ZigBee protocol (ZigBee), indigo plant
Tooth, orthogonal frequency division multiplexi (Flash Orthogonal Frequency-Division Multiplexing, Flash-
OFDM), Large Copacity space-division multiple access (High Capacity Spatial Division Multiple Access, HC-
SDMA), Universal Mobile Telecommunications System (Universal Mobile Telecommunications System, UMTS), general
Mobile communication system time division duplex (UMTS Time-Division Duplexing, UMTS-TDD), evolved high-speed packet connect
Enter (Evolved High Speed Packet Access, HSPA+), TD SDMA (Time Division
Synchronous Code Division Multiple Access, TD-SCDMA), evolution data optimization (Evolution-
Data Optimized, EV-DO), DECT (Digital Enhanced Cordless
Telecommunications, DECT) and other.
The location equipment 13 can be used for detecting the position that the electronic installation 1 is presently in, and the location equipment 13 can
Think full balls Ding Wei Xi System (Global Positioning System, referred to as：GPS), auxiliary global satellite positioning system
(Assisted Global Positioning System, referred to as：AGPS), Beidou satellite navigation system (BeiDou
Navigation Satellite System, BDS), or GLONASS satellite navigation system (GLOBAL NAVIGATION
SATELLITE SYSTEM, GLONASS).
The common screen of the display screen 14 or the touch-screen with touch-input function, such as can support multiple spot to touch
The contact panel (Multi-touch panel) of control, such as resistive touch screen or capacitive touch screen.
In the present embodiment, the memory 15 can be used for the Various types of data for storing the electronic installation 1, such as the storage
Device 15 can be used for the program code for storing the picture-text image identification system 10.
In the present embodiment, the memory 15 can be also used for storing calendar 17.The calendar 17 can record all kinds of things
Part, such as recordable meeting relevent information.In one embodiment, when the meeting relevent information includes, but not limited to meeting
Between, meeting-place, communication modes (such as addresses of items of mail or the phone number of people with a part in a conference person's list and each personnel participating in the meeting
Deng).
In the present embodiment, described picture-text image identification system 10 can be divided into one or more modules, described
One or more modules are stored in the memory 15, and are performed by one or more processors (such as processor 16), with
Realize function provided by the present invention.As shown in fig.2, in the present embodiment, the picture-text image identification system 10 can be split
Into acquisition module 101, analysis module 102, determining module 103, identification module 104 and sending module 105.Mould alleged by the present invention
Block is the program segment that can complete a specific function, is particularly suited for describing the execution of software in the electronic apparatus 1 than program
Journey, the detailed functions on each module will be described specifically below.
The acquisition module 101 is used to obtain picture-text image.
In one embodiment, the picture-text image can refer to include not editable picture and not editable word
Image file.The form of the picture-text image for example can be tif forms, jpg forms.In other embodiments, the picture and text
Image may also mean that the image file including editable picture and not editable word.
In one embodiment, the acquisition module 101 can pass through the communication module 12 and receive external equipment (in figure
It is not shown) the transmitted picture-text image to come, so as to obtain picture-text image.
In other embodiments, the acquisition module 101 can also obtain institute by controlling the camera 11 to shoot
State picture-text image.
For example, in a multi-person conference, word and painting that each personnel participating in the meeting writes on blank are record on a blank
Crow, then the acquisition module 101 camera 11 can be controlled to be directed at blank shooting to obtain picture-text image.
For example, refering to shown in Fig. 3 A, the acquisition module 101 gets a picture-text image 2.
The acquisition module 101 is additionally operable to determine acquisition time and the gain location for obtaining the picture-text image.
In one embodiment, when the picture-text image is obtained from external equipment, the acquisition time can be
Refer to the time that the acquisition module 101 receives the complete picture-text image.When the picture-text image is the acquisition module
When the 101 controls shooting of camera 11 obtains, the acquisition time can refer to that the camera 11 shoots the picture and text shadow
The shooting time of picture.
In one embodiment, the acquisition module 101 can determine to obtain institute by calling the location equipment 13
State the gain location of picture-text image.
In one embodiment, the location equipment 13 can be that full balls Ding Wei Xi System (Global Positioning
System, referred to as：GPS), auxiliary global satellite positioning system (Assisted Global Positioning System, letter
Claim：AGPS), Beidou satellite navigation system (BeiDou Navigation Satellite System, BDS), or GLONASS
Satellite navigation system (GLOBAL NAVIGATION SATELLITE SYSTEM, GLONASS).
The analysis module 102 is used for the identification mould that the picture-text image is determined according to the acquisition time and gain location
Formula is automatic mode or manual mode.
In the present embodiment, when the acquisition time and the time of meeting phase of the corresponding meeting described in calendar 17
Match somebody with somebody, and when the meeting-place of the meeting described in the gain location and the calendar 17 matches, the analysis module
The recognition mode of the 102 determination picture-text images is automatic mode.
Mismatched when the acquisition time and the time of meeting of the meeting described in calendar 17, and/or the acquisition
When place and the meeting-place of the meeting described in the calendar 17 mismatch, the recognition mode of the picture-text image is determined
For manual mode.
It should be noted that described obtain what the time matched with the time of meeting of the corresponding meeting described in calendar 17
Situation, set period (example of the acquisition time within the time of meeting or after the time of meeting can be referred to
Such as 10 minutes) in.
For example, it is assumed that the time of meeting is 2016/6/14,9:00am~11:Am, if the acquisition time is 2016/6/14,
10:00am, i.e., within the time of meeting, the time of meeting for obtaining time and the corresponding meeting described in calendar 17
Match.Equally, if the acquisition time is 11:05am, then it is described obtain 10 minutes after the time of meeting time it
Interior, the acquisition time matches with the time of meeting of the corresponding meeting described in calendar 17.
In one embodiment, when the recognition mode of the picture-text image is automatic mode, the determining module 103 is controlled
The electronic installation 1 is made automatically into recognition mode.When the recognition mode of the picture-text image is manual mode, the determination
Module 103 enters identification module according to the operation of user.For example, the determining module 103 can be in the electronic installation 1
A dialog box is shown on display screen 14 to ask the user whether to recognize the picture-text image, and when user's selection will recognize institute
When stating picture-text image, the electronic installation 1 is controlled to enter the recognition mode of the picture-text image.
The determining module 103 is additionally operable to determine the scope to be identified of picture-text image.
In one embodiment, the determining module 103 can be specified in the picture-text image not according to the operation of user
The region of recognition character is needed, and the region that this is not required to recognition character is defined as picture.The determining module 103 is by the picture and text
Other regions in image outside the region are as the scope to be identified.
For example, refering to shown in Fig. 3 B, the determining module 103 determines that the region 21 that user outlines in picture-text image 2 is figure
Piece, it is not required to recognize the word in the picture.The determining module 103 is by other in the picture-text image 2 in addition to region 21
Region is defined as the scope to be identified.
The identification module 104 is used to recognize the scope to be identified to obtain a facsimile file.
In one embodiment, the facsimile file refers to the file for including editable word and editable picture.
The form of the facsimile file for example can be doc forms, PPT forms.It should be noted that editable picture can refer to example
Can such as adjustment be zoomed in and out to the size of picture.
In other embodiments, the facsimile file can also refer to including editable word and not editable picture
File.
In one embodiment, the identification module 104 can be remembered using Chinese patent notification number CN100511267C
The method of load obtains the facsimile file, and specific steps include：
(1) recognize the scope to be identified and obtain picture and word block；
(2) picture and word block are compared, obtain each word block relative to the relative position parameter of picture and/
Or relative size parameter；
(3) above-mentioned picture is handled according to default picture processing mode, and recognizes each word block to obtain
Lteral data；
(4) according to the relative position parameter and/or relative size parameter by the picture and lteral data after the processing
Merge so as to obtain the facsimile file.
It should be noted that being not required to the region of recognition character in the picture-text image when user specifies, and this is not required to
It is described according to pre- when the region of recognition character is as picture (for convenience of description, hereinafter referred to as " picture specified by user ")
If picture processing mode the step of handling picture also include handling the picture specified by user.In addition,
Also include merging the picture specified by user when picture after the processing and lteral data are merged.
It should be noted that the lteral data is editable word.The identification module 104 can utilize such as light
Character recognition technology is learned to recognize the word in the scope to be identified.In one embodiment, the identification module 104 is also right
The lteral data of above-mentioned acquisition is analyzed to obtain contact details and keyword.
In one embodiment, the contact details include, but not limited to telephone number, addresses of items of mail.
The identification module 104 also asks the user whether contact details to be stored, and the operation for responding user contacts this
Information is stored into the memory 15.
The facsimile file is carried out classified and stored by the identification module 104 always according to the keyword.
The sending module 105 is used to for the facsimile file to be sent to the related personnel related to the picture-text image.
In one embodiment, the related personnel related to picture-text image can refer to people with a part in a conference person.Example
Such as, when the picture-text image be based on people with a part in a conference person the word that is write on blank and scribble it is captured obtain when
Wait, the sending module 105 can get people with a part in a conference person's list and corresponding communication side from the calendar 17
Formula, the facsimile file is sent to each personnel participating in the meeting according to the communication modes recorded.
As shown in fig.4, it is the method flow diagram of picture-text image discrimination method preferred embodiment of the present invention.According to different
Demand, the execution sequence of the step in flow chart shown in Fig. 4 can change, and some steps can be omitted.
Step S301, the acquisition module 101 obtain picture-text image.
In one embodiment, the picture-text image can refer to include not editable picture and not editable word
Image file.The form of the picture-text image for example can be tif forms, jpg forms.In other embodiments, the picture and text
Image may also mean that the image file including editable picture and not editable word.
In one embodiment, the acquisition module 101 can pass through the communication module 12 and receive external equipment (in figure
It is not shown) the transmitted picture-text image to come, so as to obtain picture-text image.
In other embodiments, the acquisition module 101 can also obtain institute by controlling the camera 11 to shoot
State picture-text image.
For example, in a multi-person conference, word and painting that each personnel participating in the meeting writes on blank are record on a blank
Crow, then the acquisition module 101 camera 11 can be controlled to be directed at blank shooting to obtain picture-text image.
For example, refering to shown in Fig. 3 A, the acquisition module 101 gets a picture-text image 2.
Step S302, the acquisition module 101 determine to obtain acquisition time and the gain location of the picture-text image.
In one embodiment, when the picture-text image is obtained from external equipment, the acquisition time can be
Refer to the time that the acquisition module 101 receives the complete picture-text image.When the picture-text image is the acquisition module
When the 101 controls shooting of camera 11 obtains, the acquisition time can refer to that the camera 11 shoots the picture and text shadow
The shooting time of picture.
In one embodiment, the acquisition module 101 can determine to obtain institute by calling the location equipment 13
State the gain location of picture-text image.
In one embodiment, the location equipment 13 can be that full balls Ding Wei Xi System (Global Positioning
System, referred to as：GPS), auxiliary global satellite positioning system (Assisted Global Positioning System, letter
Claim：AGPS), Beidou satellite navigation system (BeiDou Navigation Satellite System, BDS), or GLONASS
Satellite navigation system (GLOBAL NAVIGATION SATELLITE SYSTEM, GLONASS).
Step S303, the analysis module 102 determine the picture-text image according to the acquisition time and gain location
Recognition mode is automatic mode or manual mode.When it is determined that the recognition mode of the picture-text image is automatic mode, perform
Step S3031.When it is determined that the recognition mode of the picture-text image is manual mode, step S3032 is performed.
In the present embodiment, when the acquisition time and the time of meeting phase of the corresponding meeting described in calendar 17
Match somebody with somebody, and when the meeting-place of the meeting described in the gain location and the calendar 17 matches, the analysis module
The recognition mode of the 102 determination picture-text images is automatic mode.
Mismatched when the acquisition time and the time of meeting of the meeting described in calendar 17, and/or the acquisition
When place and the meeting-place of the meeting described in the calendar 17 mismatch, the recognition mode of the picture-text image is determined
For manual mode.
It should be noted that described obtain what the time matched with the time of meeting of the corresponding meeting described in calendar 17
Situation, set period (example of the acquisition time within the time of meeting or after the time of meeting can be referred to
Such as 10 minutes) in.
For example, it is assumed that the time of meeting is 2016/6/14,9:00am~11:Am, if the acquisition time is 2016/6/14,
10:00am, i.e., within the time of meeting, the time of meeting for obtaining time and the corresponding meeting described in calendar 17
Match.Equally, if the acquisition time is 11:05am, then it is described obtain 10 minutes after the time of meeting time it
Interior, the acquisition time matches with the time of meeting of the corresponding meeting described in calendar 17.
Step S3031, when the recognition mode of the picture-text image is automatic mode, the determining module 103 controls institute
Electronic installation 1 is stated automatically into recognition mode.Step S304 is performed after execution of step S3031.
Step S3032, when the recognition mode of the picture-text image is manual mode, the determining module 103 according to
The operation at family recognizes module to enter.For example, the determining module 103 can be in aobvious on the display screen 14 of the electronic installation 1
Show a dialog box to ask the user whether to recognize the picture-text image, and when user's selection will recognize the picture-text image
When, control the electronic installation 1 to enter the recognition mode of the picture-text image.Step S304 is performed after execution of step S3032.
Step S304, the determining module 103 determine the scope to be identified of picture-text image.
In one embodiment, the determining module 103 can be specified in the picture-text image not according to the operation of user
The region of recognition character is needed, and the region that this is not required to recognition character is defined as picture.The determining module 103 is by the picture and text
Other regions in image outside the region are as the scope to be identified.
For example, refering to shown in Fig. 3 B, the determining module 103 determines that the region 21 that user outlines in picture-text image 2 is figure
Piece, it is not required to recognize the word in the picture.The determining module 103 is by other in the picture-text image 2 in addition to region 21
Region is defined as the scope to be identified.
Step S305, the identification module 104 recognize the scope to be identified to obtain a facsimile file.
In one embodiment, the facsimile file refers to the file for including editable word and editable picture.
The form of the facsimile file for example can be doc forms, PPT forms.It should be noted that editable picture can refer to example
Can such as adjustment be zoomed in and out to the size of picture.
In other embodiments, the facsimile file can also refer to including editable word and not editable picture
File.
In one embodiment, the identification module 104 can be remembered using Chinese patent notification number CN100511267C
The method of load obtains the facsimile file, and specific steps include：
(1) recognize the scope to be identified and obtain picture and word block；
(2) picture and word block are compared, obtain each word block relative to the relative position parameter of picture and/
Or relative size parameter；
(3) above-mentioned picture is handled according to default picture processing mode, and recognizes each word block to obtain
Lteral data；
(4) according to the relative position parameter and/or relative size parameter by the picture and lteral data after the processing
Merge so as to obtain the facsimile file.
It should be noted that when user is in step S304, specifies the region for being not required to recognition character and be not required to distinguish by this
It is described according to default when the region of knowledge word is considered as picture (for convenience of description, hereinafter referred to as " picture specified by user ")
Picture processing mode the step of handling picture also include handling the picture specified by user.In addition, inciting somebody to action
The step of picture and lteral data after the processing merge also includes merging in the picture specified by user.
It should be noted that the lteral data is editable word.The identification module 104 can utilize such as light
Character recognition technology is learned to recognize the word in the scope to be identified.In one embodiment, the identification module 104 is also right
The lteral data of above-mentioned acquisition is analyzed to obtain contact details and keyword.
In one embodiment, the contact details include, but not limited to telephone number, addresses of items of mail.
The identification module 104 also asks the user whether contact details to be stored, and the operation for responding user contacts this
Information is stored into the memory 15.
The facsimile file is carried out classified and stored by the identification module 104 always according to the keyword.
The facsimile file is sent to the correlation related to the picture-text image by step S306, the sending module 105
Personnel.
In one embodiment, the related personnel related to picture-text image can refer to people with a part in a conference person.Example
Such as, when the picture-text image be based on people with a part in a conference person the word that is write on blank and scribble it is captured obtain when
Wait, the sending module 105 can get people with a part in a conference person's list and corresponding communication side from the calendar 17
Formula, the facsimile file is sent to each personnel participating in the meeting according to the communication modes recorded.
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention and it is unrestricted, although reference
The present invention is described in detail for above preferred embodiment, it will be understood by those within the art that, can be to this hair
Bright technical scheme is modified or equivalent substitution should not all depart from the spirit and scope of technical solution of the present invention.
Claims (21)
1. a kind of picture-text image identification system, it is characterised in that the system includes：
Determining module, for determining the scope to be identified of picture-text image；
Module is recognized, for recognizing the scope to be identified to obtain a facsimile file；And
Sending module, for the facsimile file to be sent to the related personnel related to the picture-text image.
2. picture-text image identification system as claimed in claim 1, it is characterised in that the system also includes：
Acquisition module, for obtaining the picture-text image；
The acquisition module, it is additionally operable to determine acquisition time and the gain location for obtaining the picture-text image；
Analysis module, for determining that the recognition mode of the picture-text image is automatic mold according to the acquisition time and gain location
Formula or manual mode.
3. picture-text image identification system as claimed in claim 2, it is characterised in that the analysis module is additionally operable to：When described
The acquisition time matches with the time of meeting of the corresponding meeting described in calendar, and the gain location and the calendar institute
When the meeting-place for the meeting recorded matches, the recognition mode for determining the picture-text image is automatic mode；And
Mismatched when the time of meeting of the meeting described in acquisition time and the calendar, and/or the gain location with
When the meeting-place of the meeting described in the calendar mismatches, the recognition mode for determining the picture-text image is manual mould
Formula.
4. picture-text image identification system as claimed in claim 3, it is characterised in that the related personnel refers to participate in the meeting
The personnel of view.
5. picture-text image identification system as claimed in claim 1, it is characterised in that the determining module is additionally operable to：
According to the operation of user, the user region for being not required to recognition character specified in the picture-text image is defined as figure
Piece, and other regions in the picture-text image in addition to the region are defined as the scope to be identified.
6. picture-text image identification system as claimed in claim 5, it is characterised in that the identification module obtains the picture and text text
The step of part, includes：
Recognize the scope to be identified and obtain picture and word block；
Compare the picture and word block, obtain each word block relative to the relative position parameter of the picture and/or
Relative size parameter；
Above-mentioned picture is handled according to default picture processing mode, and recognizes each word block to obtain word number
According to；
The picture after the processing and lteral data are merged according to the relative position parameter and/or relative size parameter
So as to obtain the facsimile file.
7. picture-text image identification system as claimed in claim 1, it is characterised in that the identification module is additionally operable to:
Analysis lteral data obtains contact details and keyword；
Contact details to be stored are asked the user whether, and the operation for responding user stores the contact details；And
The facsimile file is carried out by classified and stored according to the keyword.
8. a kind of picture-text image discrimination method, it is characterised in that this method includes：
Step is determined, determines the scope to be identified of picture-text image；
Step is recognized, recognizes the scope to be identified to obtain a facsimile file；And
Forwarding step, the facsimile file is sent to the related personnel related to the picture-text image.
9. picture-text image discrimination method as claimed in claim 8, it is characterised in that this method is gone back before above-mentioned determination step
Including：
First obtaining step, obtain the picture-text image；
Second acquisition module, it is determined that obtaining acquisition time and the gain location of the picture-text image；And
Analytical procedure, according to it is described acquisition the time and gain location determine the recognition mode of the picture-text image be automatic mode also
It is manual mode.
10. picture-text image discrimination method as claimed in claim 9, it is characterised in that in the analytical procedure：
Match when the acquisition time with the time of meeting of the corresponding meeting described in calendar, and the gain location and institute
When stating the meeting-place of the meeting described in calendar and matching, the recognition mode for determining the picture-text image is automatic mold
Formula；And
Mismatched when the time of meeting of the meeting described in acquisition time and the calendar, and/or the gain location with
When the meeting-place of the meeting described in the calendar mismatches, the recognition mode for determining the picture-text image is manual mould
Formula.
11. picture-text image discrimination method as claimed in claim 10, it is characterised in that the related personnel refers to described in participation
The personnel of meeting.
12. picture-text image discrimination method as claimed in claim 8, it is characterised in that in the determination step：
According to the operation of user, the user region for being not required to recognition character specified in the picture-text image is defined as figure
Piece, and other regions in the picture-text image in addition to the region are defined as the scope to be identified.
13. picture-text image discrimination method as claimed in claim 12, it is characterised in that the step for obtaining the facsimile file
Suddenly include：
Recognize the scope to be identified and obtain picture and word block；
Compare the picture and word block, obtain each word block relative to the relative position parameter of the picture and/or
Relative size parameter；
Above-mentioned picture is handled according to default picture processing mode, and recognizes each word block to obtain word number
According to；
The picture after the processing and lteral data are merged according to the relative position parameter and/or relative size parameter
So as to obtain the facsimile file.
14. picture-text image discrimination method as claimed in claim 8, it is characterised in that this method also includes step：
Analysis lteral data obtains contact details and keyword；
Contact details to be stored are asked the user whether, and the operation for responding user stores the contact details；And
The facsimile file is carried out by classified and stored according to the keyword.
15. a kind of electronic installation, it is characterised in that the device includes：
Memory；
At least one processor；
Multiple modules are stored in the memory and by least one computing devices, wherein, the plurality of module includes：
Determining module, for determining the scope to be identified of picture-text image；
Module is recognized, for recognizing the scope to be identified to obtain a facsimile file；And
Sending module, for the facsimile file to be sent to the related personnel related to the picture-text image.
16. electronic installation as claimed in claim 15, it is characterised in that the multiple module also includes：
Acquisition module, for obtaining the picture-text image；
The acquisition module, it is additionally operable to determine acquisition time and the gain location for obtaining the picture-text image；
Analysis module, for determining that the recognition mode of the picture-text image is automatic mold according to the acquisition time and gain location
Formula or manual mode.
17. electronic installation as claimed in claim 16, it is characterised in that the analysis module is additionally operable to：
Match when the acquisition time with the time of meeting of the corresponding meeting described in calendar, and the gain location and institute
When stating the meeting-place of the meeting described in calendar and matching, the recognition mode for determining the picture-text image is automatic mold
Formula；And
Mismatched when the time of meeting of the meeting described in acquisition time and the calendar, and/or the gain location with
When the meeting-place of the meeting described in the calendar mismatches, the recognition mode for determining the picture-text image is manual mould
Formula.
18. electronic installation as claimed in claim 17, it is characterised in that the related personnel refers to the people for participating in the meeting
Member.
19. electronic installation as claimed in claim 15, it is characterised in that the determining module is additionally operable to：
According to the operation of user, the user region for being not required to recognition character specified in the picture-text image is defined as figure
Piece, and other regions in the picture-text image in addition to the region are defined as the scope to be identified.
20. electronic installation as claimed in claim 19, it is characterised in that the identification module obtains the step of the facsimile file
Suddenly include：
Recognize the scope to be identified and obtain picture and word block；
Compare the picture and word block, obtain each word block relative to the relative position parameter of the picture and/or
Relative size parameter；
Above-mentioned picture is handled according to default picture processing mode, and recognizes each word block to obtain word number
According to；
The picture after the processing and lteral data are merged according to the relative position parameter and/or relative size parameter
So as to obtain the facsimile file.
21. electronic installation as claimed in claim 15, it is characterised in that the identification module is additionally operable to:
Analysis lteral data obtains contact details and keyword；
Contact details to be stored are asked the user whether, and the operation for responding user stores the contact details；And
The facsimile file is carried out by classified and stored according to the keyword.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610519283.XA CN107563365A (en) | 2016-07-01 | 2016-07-01 | Electronic installation, picture-text image identification system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610519283.XA CN107563365A (en) | 2016-07-01 | 2016-07-01 | Electronic installation, picture-text image identification system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107563365A true CN107563365A (en) | 2018-01-09 |
Family
ID=60970092
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610519283.XA Pending CN107563365A (en) | 2016-07-01 | 2016-07-01 | Electronic installation, picture-text image identification system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107563365A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1581786A (en) * | 2003-08-05 | 2005-02-16 | 英业达股份有限公司 | Digital conference data integration-transmission system and method thereof |
| US20100241432A1 (en) * | 2009-03-17 | 2010-09-23 | Avaya Inc. | Providing descriptions of visually presented information to video teleconference participants who are not video-enabled |
| CN104572716A (en) * | 2013-10-18 | 2015-04-29 | 英业达科技有限公司 | System and method for playing video files |
| CN104967749A (en) * | 2015-07-29 | 2015-10-07 | 努比亚技术有限公司 | Device and method for processing picture and text information |
| CN105205644A (en) * | 2014-06-10 | 2015-12-30 | 中兴通讯股份有限公司 | Recording method and apparatus, and terminal |
-
2016
- 2016-07-01 CN CN201610519283.XA patent/CN107563365A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1581786A (en) * | 2003-08-05 | 2005-02-16 | 英业达股份有限公司 | Digital conference data integration-transmission system and method thereof |
| US20100241432A1 (en) * | 2009-03-17 | 2010-09-23 | Avaya Inc. | Providing descriptions of visually presented information to video teleconference participants who are not video-enabled |
| CN104572716A (en) * | 2013-10-18 | 2015-04-29 | 英业达科技有限公司 | System and method for playing video files |
| CN105205644A (en) * | 2014-06-10 | 2015-12-30 | 中兴通讯股份有限公司 | Recording method and apparatus, and terminal |
| CN104967749A (en) * | 2015-07-29 | 2015-10-07 | 努比亚技术有限公司 | Device and method for processing picture and text information |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11032709B2 (en) | Host a conference call | |
| US20160232402A1 (en) | Methods and devices for querying and obtaining user identification | |
| US9443155B2 (en) | Systems and methods for real human face recognition | |
| CN110471858B (en) | Application program testing method, device and storage medium | |
| WO2015090137A1 (en) | A voice message search method, device, and system | |
| US11138422B2 (en) | Posture detection method, apparatus and device, and storage medium | |
| CN106302996B (en) | Message display method and device | |
| WO2015039601A1 (en) | Methods, devices, terminal device and systems for pattern recognition | |
| CN107465997A (en) | Bluetooth connecting method, device, terminal and computer-readable recording medium | |
| US20210295273A1 (en) | Terminal and non-transitory computer readable storage medium | |
| US20170017783A1 (en) | Biometric Authentication Matching Using Grip Detection | |
| WO2019132564A1 (en) | Method and system for classifying time-series data | |
| CN107765853A (en) | Using method for closing, device, storage medium and electronic equipment | |
| CN112099704A (en) | Information display method and device, electronic equipment and readable storage medium | |
| US9202033B2 (en) | Techniques for skin tone activation | |
| CN112287234A (en) | Information retrieval method, device and storage medium | |
| CN109165651A (en) | A kind of identification code recognition methods, terminal and computer readable storage medium | |
| US20150062005A1 (en) | Method and system for providing user interaction when capturing content in an electronic device | |
| US20150006669A1 (en) | Systems and methods for directing information flow | |
| CN109828844A (en) | Processing method, mobile terminal and the storage medium of application program | |
| WO2021073434A1 (en) | Object behavior recognition method and apparatus, and terminal device | |
| CN112734661A (en) | Image processing method and device | |
| CN113342170A (en) | Gesture control method, device, terminal and storage medium | |
| CN108776600A (en) | Application program pretrigger method, mobile terminal and computer readable storage medium | |
| EP3164816A1 (en) | Method of providing relevant information and electronic device adapted to the same |
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: 20180109 |