CN106657663A - Method and device for extracting information in image of mobile terminal - Google Patents
Method and device for extracting information in image of mobile terminal Download PDFInfo
- Publication number
- CN106657663A CN106657663A CN201710004918.7A CN201710004918A CN106657663A CN 106657663 A CN106657663 A CN 106657663A CN 201710004918 A CN201710004918 A CN 201710004918A CN 106657663 A CN106657663 A CN 106657663A
- Authority
- CN
- China
- Prior art keywords
- image
- module
- mobile terminal
- information
- character
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72403—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality
- H04M1/7243—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality with interactive means for internal management of messages
- H04M1/72439—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality with interactive means for internal management of messages for image or video messaging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Human Computer Interaction (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Character Input (AREA)
Abstract
The invention discloses a method for extracting information in an image of a mobile terminal and mainly solves a technical problem of incapability of carrying out conversion effectively and accurately in the existing technology. The technical scheme adopted in the invention comprises the following steps of (1) enabling settings; (2) selecting a target image B which needs conversion by a user; (3) converting the target image B to obtain an image E, wherein the number of lines of the image E is the number of lines of the target image B; (4) carrying out extraction operation on the image E to obtain a character string Mz; and (5) popping up the character string Mz in the step (4) to display and edit through a popup box in order to solve the technical problem well. The method and the device are applied to electronic equipment with image processing.
Description
Technical field
The present invention relates to image conversion art, is related specifically to the method and dress of information in a kind of extraction mobile terminal image
Put.
Background technology
With the development and the popularization of intelligent terminal of internet, the exchange between people becomes increasingly dependent on instant chat software,
Such as wechat, QQ etc., this also gradually instead of traditional note and MMS.Instant messenger brings very just to me
While chance is linked up in victory, also some inconveniences can be brought to us.For example, when some information are sent to other side, intelligence
There is the function of screenshotss in terminal, we can easily use this function by some important information, such as telephone number
Other side is sent in the form of screenshotss.But after other side receives the picture of our transmissions, need memory phone number above
Code, whether the verification being then back to remember successfully, subsequently into dialing interface, is one by one being input to the number information in memory
In dial.Because the time memory that people are of short duration, the number information for being likely to result in the input in dial are wrong, need sometimes
To check whether that input is correct picture is opened.Therefore, such case just influences whether the experience of user.
In prior art, need whether memory telephone number above, the verification being then back to are remembered successfully, subsequently into
Dialing interface, is one by one being input to the number information in memory in dial.Presence is likely to result in and is input in dial
Number information it is wrong and have influence on the technical problem of the experience of user.Therefore it provides one kind can pass through Digital Image Processing
Technology completes to navigate to information of interest and is converted into character from picture, and to play frame in the form of present to user, facilitate user
Duplication operation method, it is just necessary.
The content of the invention
The technical problem to be solved in the present invention is exist to be likely to result in the number being input in dial in prior art
Information is wrong and has influence on the technical problem of the experience of user.The present invention provides one kind and need not carry out figure by memory-verification mode
The method of piece information conversion, methods described only needs to complete the positioning action of information of interest in picture, it is possible to by number
Word image processing techniques completes to navigate to information of interest and is converted into character from picture, and to play frame in the form of present to use
Family, user friendly subsequent operation.
To solve above-mentioned technical problem, the technical solution used in the present invention is as follows：
A kind of method for extracting information in mobile terminal image, including：
(1) open and arrange；
(2) switch target image B needed for user selectes, including：During the position that length is intercepted on demand, point out to confirm what is intercepted
Original position (x0,y0), point out the final position (x for confirming to intercept1,y1), intercept from original image width M, height N
Target image B；
(3) the target image B is converted, obtains image E, image E line numbers are the line number of target image B；
(4) extraction operation is carried out to described image E, obtains character string Mz, character string Mz be the numeral in target image B and
Word message；
(5) by character string Mz described in step (4) to play frame ejection, to show editor.
In such scheme, further, setting is opened described in the step (1) to be included opening, referring to by arranging menu
Line identification is opened, speech recognition is opened.
Further, the speech recognition is opened to be included in fingerprint recognition and completes specific action.
Further, the specific action is double-click fingerprint identification module.
Further, the step (3) includes：
A. target image B is carried out into gray scale conversion, obtains image C；
B. binarization operation is carried out to image C, obtains image D；
C. opening operation operation is carried out to image D, obtains image E.
Further, the pixel value of described image C is 0～255.
Further, operation is extracted in the step (4) includes：
A () extracts the information line number in target image B：Region of the white pixel value density more than 30% in image E is extracted,
White pixel value density, more than the line number that the number in 30% region is in image E, is the line number in target image B；
B () extracts numeral and Word message in target image B；
C () matches the character M：Character M is matched with ATL, matching threshold is 0.97, obtain matching character
Mi, wherein i=0,1,2......n；
D () repeat step b and step c, from left to right arrangement matching character Mi, obtains character string Mz；
Further, the step (b) includes：
The level integration of described image E is calculated, projected image F is obtained, n crest is contained in projected image F, image E has n
OK；
Split n row images respectively, obtain segmentation figure as Fi, segmentation picture traverse is M；
According to segmentation figure as the upright projection image G of Fi splits described image E, character M is obtained, character M width is w, its
Middle i=0,1,2......n.
Further, the step (5) frame of being hit by a bullet includes：
Viewing area, to show testing result, acquiescence is shown as numeral；
Switching push button, to switch the details for checking testing result；
Cancellation, reproduction button, to replicate to the character string.
Further, methods described is used for the electronic equipment with image procossing.
The present invention also provides the extraction element of a kind of method of information in extraction mobile terminal image, the extraction element bag
Include the opening module being sequentially connected, image interception module, image processing module, calculation process module and display editor module；
The opening module is used to open setting, including menu opening module, and fingerprint recognition opening module and voice are opened
Module；
The menu opening module is applied to menu and opens setting；
The fingerprint recognition opening module is suitable for use with fingerprint and opens setting；
The voice opening module is suitable for use with voice and opens setting；
The display editor module includes display module, mode switch module and editor module, display module and editor's mould
Block is converted to the text results that the method for word draws for showing and editing the image that can receive；
The mode switch module is used for switching and shows digital information and details.
The patent utilization image procossing of the invention can automatically extract the character information contained in picture, comprising numeral and text
Word, facilitates user to extract the information of interest contained in picture, and when user is by information interested, such as number information is copied to
In pasting boards, then can facilitate user that number information is adhered directly onto in dialing interface in dialing interface, then eliminate use
Number information is remembered to the tedious steps being input into one by one in family.This patent is related to method can be transplanted to all of android systems
In system, the application as system level is used.Image procossing splits user using level with the method for upright projection in this patent
Character information in the area-of-interest of positioning, the method amount of calculation is little, speed is high, the degree of accuracy is high, and will not in calculating process
Take more memory information.
Present invention has the advantages that,
Effect one, improves image procossing and is converted to the intelligent of alphanumeric information；
Effect two, methods described has versatility；
Effect three, methods described has high efficiency.
Description of the drawings
With reference to the accompanying drawings and examples the present invention is further described.
Fig. 1 is apparatus of the present invention block diagram；
Fig. 2 is flow chart of the present invention；
Fig. 3 is width M, the schematic diagram of the target image B of height N of intercepting in original image of the present invention；
Fig. 4 is the schematic diagram of segmentation figure picture of the present invention；
Fig. 5 is the schematic diagram that the present invention plays frame.
Specific embodiment
In order that the objects, technical solutions and advantages of the present invention become more apparent, with reference to embodiments, to the present invention
It is further elaborated.It should be appreciated that specific embodiment described herein is not used to only to explain the present invention
Limit the present invention.
Fig. 2 is schematic flow sheet of the present invention, the clear detailed flow process for describing the method for the invention.
Embodiment 1：
Such as Fig. 1, this enforcements disclose it is a kind of can reception image be converted to word method device, described device includes
The opening module being sequentially connected, image interception module, image processing module, calculation process module and display editor module；It is described
Opening module is used to open setting, including menu opening module, fingerprint recognition opening module and voice opening module；The menu
Opening module is applied to menu and opens setting；The fingerprint recognition opening module is suitable for use with fingerprint and opens setting；Institute's predicate
Sound opening module is suitable for use with voice and opens setting；It is described display editor module include display module, mode switch module and
Editor module, display module and editor module are used to showing and edit described can be obtained the method for receiving image and being converted to word
The text results for going out；The mode switch module is used for switching and shows digital information and details.
A kind of foundation can will receive the method that image is converted to word, and such as Fig. 2, methods described step includes：
(1) opened with setting menu and arranged；
(2) with the head of a household by switch target image B, such as Fig. 3 needed for selecting, whether detection interface display is picture, such as Fig. 2 institutes
State, during the position that length is intercepted on demand, point out the original position (x0, y0) for confirming to intercept, point out the final position for confirming to intercept
(x1, y1), intercepts width M, a target image B of height N, such as Fig. 3 from original image；
(3) target image B is carried out into gray scale conversion, obtains image C, the pixel value of image C is 0～255；Image C is entered
Row binarization operation, obtains image D；Opening operation operation is carried out to image D, image E is obtained, image E line numbers are target image B's
Line number；
(4) extraction operation is carried out to described image E, obtains character string Mz, character string Mz be the numeral in target image B and
Word message；
A () extracts the information line number in target image B：Region of the white pixel value density more than 30% in image E is extracted,
White pixel value density, more than the line number that the number in 30% region is in image E, is the line number in target image B；
B () extracts numeral and Word message in target image B, calculate the level integration of described image E, obtains perspective view
As F, n crest is contained in projected image F, image E there are n rows；
Such as Fig. 4, n row images are split respectively, obtain segmentation figure as Fi, segmentation picture traverse is M；
According to segmentation figure as the upright projection image G of Fi splits described image E, character M is obtained, as described in Figure 3, character M
Width is w, wherein i=0,1,2......n；
C () matches the character M：Character M is matched with ATL, it is 0.97 to reach matching threshold, is matched
Character Mi, wherein i=0,1,2......n；
D () repeat step b and step c, from left to right arrangement matching character Mi, obtains character string Mz；
(5) as shown in figure 5, playing frame pop-up display character string Mz, numerical monitor is defaulted as, switching push button checks testing result
Details, with cancel, reproduction button duplication stickup is carried out to the character string.
Further, methods described is used for the electronic equipment with image procossing.
Embodiment 2
The present embodiment further illustrates the difference of opening ways in the technology of embodiment 1：Step (1) is：
(1) opened with voice recognition mode and arranged.
Embodiment 3
The present embodiment further illustrates the difference of opening ways in the technology of embodiment 1：Step (1) is：
(1) in fingerprint recognition open place, double-click, fingerprint recognition open place is opened and arranged.
Although being described to illustrative specific embodiment of the invention above, in order to the technology of the art
Personnel are it will be appreciated that the present invention, but the present invention is not limited only to the scope of specific embodiment, the common skill to the art
For art personnel, as long as long as various change is in the spirit and scope of the invention of appended claim restriction and determination, one
Cut using the innovation and creation of present inventive concept in the row of protection.
Claims (10)
1. it is a kind of extract mobile terminal image in information method, it is characterised in that：Methods described includes：
(1) open and arrange；
(2) switch target image B needed for user selectes, including：During the position that length is intercepted on demand, the starting for confirming to intercept is pointed out
Position (x0,y0), point out the final position (x for confirming to intercept1,y1), width M, a target of height N are intercepted from original image
Image B；
(3) the target image B is converted, obtains image E, image E line numbers are the line number of target image B；
(4) extraction operation is carried out to described image E, obtains character string Mz, character string Mz is numeral and word in target image B
Information；
(5) by character string Mz described in step (4) playing frame pop-up display editor.
It is 2. according to claim 1 can will to receive the method that image is converted to word, it is characterised in that：The step
(1) setting is opened described in includes that menu unlatching, fingerprint recognition are opened, speech recognition is opened by arranging.
3. it is according to claim 2 extract mobile terminal image in information method, it is characterised in that：The speech recognition
Unlatching is included in fingerprint recognition and completes specific action.
4. it is according to claim 2 extract mobile terminal image in information method, it is characterised in that：It is described specific dynamic
As double-click fingerprint identification module.
5. it is according to claim 1 extract mobile terminal image in information method, it is characterised in that：The step (3)
Including：
A. target image B is carried out into gray scale conversion, obtains image C；
B. binarization operation is carried out to image C, obtains image D；
C. opening operation operation is carried out to image D, obtains image E.
6. it is according to claim 1 extract mobile terminal image in information method, it is characterised in that：Described image C
Pixel value is 0～255.
7. it is according to claim 1 extract mobile terminal image in information method, it is characterised in that：The step (4)
Middle extraction operation includes：
A () extracts the information line number in target image B：Extract region of the white pixel value density more than 30% in image E, white
Pixel value density, more than the line number that the number in 30% region is in image E, is the line number in target image B；
B () extracts numeral and Word message in target image B；
C () matches the character M：Character M is matched with ATL, matching threshold is 0.97, obtain matching character Mi, its
Middle i=0,1,2......n；
D () repeat step b and step c, from left to right arrangement matching character Mi, obtains character string Mz.
8. it is according to claim 7 extract mobile terminal image in information method, it is characterised in that：The step (b)
Including：
The level integration of described image E is calculated, projected image F is obtained, n crest is contained in projected image F, image E there are n rows；
Split n row images respectively, obtain segmentation figure as Fi, segmentation picture traverse is M；
According to segmentation figure as the upright projection image G of Fi splits described image E, character M is obtained, character M width is w, wherein i=
0,1,2......n。
9. it is according to claim 1 extract mobile terminal image in information method, it is characterised in that：The step (5)
Frame of being hit by a bullet includes：
Viewing area, to show testing result, acquiescence is shown as numeral；
Switching push button, to switch the details for checking testing result；
Cancellation, reproduction button, to replicate to the character string.
10. according to the arbitrary described extraction element for extracting the method for information in mobile terminal image of claim 1-9, its feature
It is：The extraction element includes the opening module being sequentially connected, image interception module, image processing module, calculation process mould
Block and display editor module；
The opening module is used to open setting, including menu opening module, fingerprint recognition opening module and voice opening module；
The menu opening module is applied to menu and opens setting；
The fingerprint recognition opening module is suitable for use with fingerprint and opens setting；
The voice opening module is suitable for use with voice and opens setting；
The display editor module includes display module, mode switch module and editor module, and display module and editor module are used
The text results that the method for word draws are converted in showing and editing the image that will can receive；
The mode switch module is used for switching and shows digital information and details.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710004918.7A CN106657663A (en) | 2017-01-04 | 2017-01-04 | Method and device for extracting information in image of mobile terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710004918.7A CN106657663A (en) | 2017-01-04 | 2017-01-04 | Method and device for extracting information in image of mobile terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106657663A true CN106657663A (en) | 2017-05-10 |
Family
ID=58843665
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710004918.7A Pending CN106657663A (en) | 2017-01-04 | 2017-01-04 | Method and device for extracting information in image of mobile terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106657663A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108615032A (en) * | 2018-06-25 | 2018-10-02 | Oppo广东移动通信有限公司 | A kind of module, terminal device and fingerprint identification method for supporting full frame fingerprint recognition |
| CN110475010A (en) * | 2019-07-23 | 2019-11-19 | 深圳市六度人和科技有限公司 | A kind of number call method, apparatus and electronic equipment based on Windows shear plate |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103365988A (en) * | 2013-07-05 | 2013-10-23 | 百度在线网络技术（北京）有限公司 | Method and device for loud reading pictures and characters of mobile terminal and mobile terminal |
| CN105550686A (en) * | 2015-12-09 | 2016-05-04 | 小米科技有限责任公司 | Character segmentation method and device |
| CN105631486A (en) * | 2014-10-27 | 2016-06-01 | 深圳Tcl数字技术有限公司 | Method and device for recognizing images and characters |
| CN106156691A (en) * | 2015-03-25 | 2016-11-23 | 中测高科（北京）测绘工程技术有限责任公司 | The processing method of complex background image and device thereof |
-
2017
- 2017-01-04 CN CN201710004918.7A patent/CN106657663A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103365988A (en) * | 2013-07-05 | 2013-10-23 | 百度在线网络技术（北京）有限公司 | Method and device for loud reading pictures and characters of mobile terminal and mobile terminal |
| CN105631486A (en) * | 2014-10-27 | 2016-06-01 | 深圳Tcl数字技术有限公司 | Method and device for recognizing images and characters |
| CN106156691A (en) * | 2015-03-25 | 2016-11-23 | 中测高科（北京）测绘工程技术有限责任公司 | The processing method of complex background image and device thereof |
| CN105550686A (en) * | 2015-12-09 | 2016-05-04 | 小米科技有限责任公司 | Character segmentation method and device |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108615032A (en) * | 2018-06-25 | 2018-10-02 | Oppo广东移动通信有限公司 | A kind of module, terminal device and fingerprint identification method for supporting full frame fingerprint recognition |
| CN110475010A (en) * | 2019-07-23 | 2019-11-19 | 深圳市六度人和科技有限公司 | A kind of number call method, apparatus and electronic equipment based on Windows shear plate |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109729420B (en) | Picture processing method and device, mobile terminal and computer readable storage medium | |
| CN109189985B (en) | Text style processing method and device, electronic equipment and storage medium | |
| CN104753766B (en) | Expression sending method and device | |
| CN106506335B (en) | The method and device of sharing video frequency file | |
| CN107992812A (en) | A kind of lip reading recognition methods and device | |
| WO2017161741A1 (en) | Method and device for communicating information with deaf-mutes, smart terminal | |
| WO2020253128A1 (en) | Voice recognition-based communication service method, apparatus, computer device, and storage medium | |
| CN104144108B (en) | A kind of message responding method, apparatus and system | |
| CN110490182A (en) | A kind of point reads production method, system, storage medium and the electronic equipment of data | |
| CN104505091A (en) | Human-machine voice interaction method and human-machine voice interaction system | |
| CN108960158A (en) | A kind of system and method for intelligent sign language translation | |
| CN109819288B (en) | Method and device for determining advertisement delivery video, electronic equipment and storage medium | |
| CN102567534B (en) | Interactive product user generated content intercepting system and intercepting method for the same | |
| US20200218772A1 (en) | Method and apparatus for dynamically identifying a user of an account for posting images | |
| CN107527623A (en) | Screen transmission method, device, electronic equipment and computer-readable recording medium | |
| CN105809174A (en) | Method and device for identifying image | |
| US20210201478A1 (en) | Image processing methods, electronic devices, and storage media | |
| CN109327614B (en) | Global simultaneous interpretation mobile phone and method | |
| CN109857505A (en) | Execution method, apparatus, terminal and the storage medium of operation | |
| CN112200040A (en) | Occlusion image detection method, device and medium | |
| CN113315979A (en) | Data processing method and device, electronic equipment and storage medium | |
| CN106657663A (en) | Method and device for extracting information in image of mobile terminal | |
| CN103546613A (en) | Contact person recording method, contact person recording device and mobile terminal | |
| CN106921958A (en) | The method and apparatus for quitting the subscription of business | |
| CN114065720A (en) | Conference summary generation method and device, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170510 |
|
| RJ01 | Rejection of invention patent application after publication |