CN102169541A - Character recognition input system using optical localization and method thereof - Google Patents
Character recognition input system using optical localization and method thereof Download PDFInfo
- Publication number
- CN102169541A CN102169541A CN2011100830704A CN201110083070A CN102169541A CN 102169541 A CN102169541 A CN 102169541A CN 2011100830704 A CN2011100830704 A CN 2011100830704A CN 201110083070 A CN201110083070 A CN 201110083070A CN 102169541 A CN102169541 A CN 102169541A
- Authority
- CN
- China
- Prior art keywords
- module
- elementary area
- identification
- text
- image
- 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
Images
Landscapes
- Character Input (AREA)
Abstract
The invention provides a character recognition input system using optical localization and a method thereof. The system is provided with two optical operation devices on a hardware structure, namely a light beam emitting device and a photographic device like a camera. The construction and work method of the system are as follows: 1, the light beam emitting module starts a light beam emitting device to form a light spot on the surface of a text; 2, an image acquiring module starts the photographic device to obtain a text image; 3; an image processing module divides the text image by using a word, an individual character and a symbol as an elementary unit to form an image unit arrangement; 4, a recognition original point locating module defines the position of a light spot in the text image as a recognition original point; 5, an image unit selecting module selects single or a plurality of image units in the image unit arrangement by using the recognition original point as a start point; 6, an OCR (optical character recognition) module recognizes the selected image unit as the character and symbol; and 7, an input module inputs the character and symbol in relative software in a mobile terminal apparatus. The character recognition input system using optical localization and the method thereof are suitable for various mobile terminal apparatuses.
Description
Affiliated technical field
The present invention relates to the field of the image acquisition and processing and the optical character identification of mobile terminal device, particularly a kind of character recognition input system and method thereof that adopts optical alignment.
Background technology
At present, the method that the character in printed text or the handwritten text is input in computer or the mobile terminal device is mainly contained two kinds by optical character identification (OCR) technology: the one, the image that adopts scanning technique to obtain text carries out character recognition then; A kind of is to carry out character recognition then by the image that camera head obtains text.
Though text image can be stablized, clearly be obtained to scanning technique, often need external fixing scanning device.This is not suitable for the request for utilization of mobile terminal device.In some product, as scan translation pen, designed structure with scan function, but for the mobile terminal device of various hommizations day by day, exquisiteness, this structure influence the integrality and the aesthetic property of mobile terminal device outward appearance, and inconvenient operation.
In recent years, along with camera function popularizing in mobile terminal devices such as mobile phone, palm PC, notebook computer, obtain technology that text image carries out character recognition then by camera head and will obtain application with more and more widely.What at present, application was the most successful is the business card recognition function of mobile phone.Mobile phone is by its camera head---and camera obtains the image of business card, is literal and symbolic information through Flame Image Process and identification with the content recognition of business card, and classifies as standard format and store in the mobile phone archives.Carry out image acquisition, processing, identification and input but choose specific word, speech, sentence and symbol for how from the printing of big length or handwritten text, this technology does not also have good solution.The solution that exists is as follows at present:
A kind of method is to utilize the cursor in the mobile terminal device screen to locate.Before obtaining text image, adjust the position of mobile terminal device so that character to be identified is moved near the cursor of screen images acquired then; Perhaps after obtaining text image, the cursor of screen is moved near the character to be identified in the image.Then, be that positioning reference finds target character to discern by system with the cursor.No matter be which kind of situation, all require the operator must face the narrow and small screen of mobile device, and in minimum image, at first find the character that to discern by naked eyes.This method can not fundamentally improve the efficient of identification and input.
Another kind method is that an end of mobile terminal device is made pointed outstanding shape and camera is installed, as a kind of shooting translation pen.Necessary close and alignment of textual and scan text of camera during Image Acquisition, the image with per second 50 lattice during scanning takes required literal at a high speed, discerns then.Kind method requires: 1, in the process of scan text, the character of the teat bit alignment starting point of camera need will be installed, and guarantee that the especially long western language word of bebinning character is within the image pickup scope fully.2, in whole when scanning sentence, must guarantee the stable of gesture and can not depart from the part that causes some character and all not within image pickup scope.These all claim to the operator, have increased the difficulty of operation.These require all to run in the opposite direction with the hommization and the ease-of-use trend of mobile terminal device.In addition, the desired structure of this design is not suitable for realizing in most of mobile terminal devices.
Summary of the invention
The technical problem to be solved in the present invention is: a kind of camera head directed apace system and method for selecting word, speech, sentence and symbol to carry out collection, processing, location, identification and the input of image from printed text or handwritten text that utilizes is provided.And this system and method can be easy to realize in all mobile terminal devices.
For solving the problems of the technologies described above, the present invention by the following technical solutions:
A kind of character recognition input system that adopts optical alignment has two optics apparatus for work on its hardware configuration: beam launcher and camera head, and as camera.Beam launcher emission light beam forms hot spot clearly on the surface of printed text or handwritten text; Camera head is filmed the formation image with certain zone of printed text or handwritten text.
A kind of character recognition input system and method thereof that adopts optical alignment comprises:
1, beam emissions module, its effect are to send instruction to start beam launcher, and the time length kept of regulation light beam;
2, image capture module, its effect are to send instruction to start camera head, and as camera, carries out image is gathered operation;
3, image processing module, its effect is that the text image that image capture module obtains is carried out processing such as slant correction, denoising, counter-rotating, gray scale, be that the primary image unit is cut apart with word (alphabetic writing), individual character (Chinese, Japanese, Korean etc.) and symbol then, form the arrangement of forming by elementary area;
4, identification original point position module (hereinafter to be referred as locating module), its effect is the position at hot spot place in searching and the definite text image, and this location definition is the identification initial point;
5, elementary area is selected module (hereinafter to be referred as selecting module), and its effect is to be starting point with the identification initial point, and single or a plurality of elementary areas are selected in the requirement according to instruction in a certain direction in matrix of picture cells;
6, OCR identification module, its effect are that the elementary area that elementary area selects module to select is identified as literal and symbol;
7, load module, its effect are in the related software that will be input to mobile terminal device by the literal and the symbol of OCR identification module acquisition.
The technology path of identification original point position module:
One of technology path: according to beam launcher and camera head relatively-stationary spatial relation is arranged on mobile terminal device, identification original point position module is set up a kind of space reference structure between the two.The principle of work of this space reference structure is: light beam is in a fixing relative position forever at the hot spot of printed text or the formation of text writing surface in the image that image capture module obtains---such as the central point of image.Locating module is defined as the identification initial point with this relative position.
Two of technology path: beam emissions module emitted light beams is pointed to the zone at certain particular words, individual character or symbol place in printed text or the text writing, and in this regional inside or the next door form hot spot.After image capture module obtained image, the point at hot spot place becomes to be distinguished in the image obviously not in other regional feature locations.Locating module at first finds this feature locations in image, then this feature locations is defined as the identification initial point.
It is that starting point is followed following rule to the selection of elementary area with the identification initial point that elementary area is selected module:
One of selective rule: the position of literal target on text that is identified with respect to needs, when the regulation hot spot is positioned at the character zone at starting point place of this target when inner, will define the elementary area of discerning the initial point place be first word, individual character or the symbol that is identified for native system and method so.
Two of selective rule: the position of literal target on text that is identified with respect to needs, when the regulation hot spot is positioned at character zone when next door at the starting point place of this target, will define first elementary area by the identification initial point position be first word, individual character or the symbol that is identified for native system and method so.According to the ways of writing of different language, the next door can be defined as the left side, the right, top or bottom etc.
Three of selective rule: when needs are selected and identification is made up of two or more word, individual character or symbol words symbol combination (as phrase, Chinese idiom, short title etc.), the identification initial point can be arranged in this combination first, on any one word, individual character or the symbol of last or centre or next door.
Four of selective rule: when needs select and the identification tape punctuation mark than the combination of long word word symbol (as the sentence of title, single sentence or the several successive grown) time, except that definition identification initial point, can a certain specific punctuation mark as the terminal point of discerning (as first right punctuation marks used to enclose the title, the 3rd comma, second branch ... Deng).The Instruction Selection module is only selected the elementary area between identification initial point and identification terminal point in the matrix of picture cells.
When needs with printed text or handwritten text in a certain particular words (alphabetic writing) or individual character (Chinese, Japanese, Korean) identification when being input to mobile terminal device, its job step is as follows:
1, the beam emissions module starts beam launcher, and the inside or the next door of light beam irradiates this particular words, individual character or symbol region to the text formed hot spot;
2, image capture module starts camera head, takes text and obtains image;
3, image processing module carries out image processing such as slant correction, denoising, counter-rotating, gray scale, is divided into elementary area then, forms the arrangement of elementary area;
4, locating module is sought the position at hot spot place and initial point is discerned in its definition;
5, selecting module is starting point with the identification initial point, selects first elementary area;
6, the OCR identification module is discerned selecteed elementary area;
7, load module will be discerned in the related software that the literal that obtains or symbol be input to mobile terminal device.
When identification was input to mobile terminal device, its job step was as follows for the words symbol combination of being made up of two or more words, individual character or symbol in need be with printed text or handwritten text (as phrase, Chinese idiom, short title etc.):
1, the beam emissions module starts beam launcher, according to selective rule with light beam irradiates zone at certain word, individual character or symbol place in this specific words symbol combination to the text, and in this regional inside or next door formation hot spot;
2, image capture module starts camera head, takes text and obtains image;
3, image processing module carries out image processing such as slant correction, denoising, counter-rotating, gray scale, is divided into elementary area then, forms the arrangement of elementary area;
4, locating module is sought the position at hot spot place and initial point is discerned in its definition;
5, selecting module is starting point with the identification initial point, and selective rule is according to the rules selected elementary area;
6, the OCR identification module is discerned selecteed elementary area;
7, load module will be discerned in the related software that the literal that obtains or symbol be input to mobile terminal device.
In need be with printed text or handwritten text specific band punctuation mark when identification was input to mobile terminal device, its job step was as follows than long word word symbol combination (as the sentence of single sentence, several successive, long title etc.):
1, the beam emissions module starts beam launcher, according to selective rule with light beam irradiates zone at certain word, individual character or symbol place in this specific sentence to the text, and in this regional inside or next door formation hot spot;
2, image capture module starts camera head, takes text and obtains image;
3, image processing module carries out image processing such as slant correction, denoising, counter-rotating, gray scale, is divided into elementary area then, forms the arrangement of elementary area;
4, locating module is sought the position at hot spot place and initial point is discerned in its definition;
5, selecting module is starting point with the identification initial point, and selective rule is according to the rules selected elementary area;
6, the OCR identification module is discerned selecteed elementary area;
7, the load module words symbol combination that will discern the band punctuation mark that obtains is input in the related software of mobile terminal device.
The invention has the beneficial effects as follows, provide a cover fast, from the printing of big length or handwritten text, choose the solution that specific word, speech, sentence and symbol carry out image acquisition, identification and input easily; By adopting the character recognition input system and the method thereof of optical alignment, as long as on the position that the user accomplishes light beam irradiates is determined to the text, remaining image acquisition, accurate in locating identification and input service just can be paid mobile terminal device fully and be finished.Identification accurately fast, operation is simple, meet the hommization requirement; This system can merge with existing various mobile terminal devices well simultaneously, will expand the application of mobile terminal device greatly.
Description of drawings
Fig. 1: a kind of formation that adopts the character recognition input system of optical alignment of the present invention.Wherein:
101: printed text or handwritten text;
102: beam launcher;
103: camera head, as camera;
104: start the beam emissions module, beam launcher sends light beam, shines on the text and forms hot spot in certain location;
105: start image capture module, the instruction camera head as camera, captures as image with text;
106: starting image processing module, is that the unit is cut apart with text image with word (alphabetic writing), individual character (Chinese, Japanese, Korean etc.) or symbol, forms elementary area;
107: after image processing module was handled, text image became the orderly permutation matrix of an elementary area.Wherein each gray area is represented an elementary area;
108: the elementary area of alphabetic writing and the elementary area of Chinese character;
109: the hot spot correspondence that the light beam that beam launcher sends forms on text certain word, individual character or symbol;
110: locating module is according to the initial point of 109 selection identifications;
111: select module based on 106,107 and 108, according to the elementary area of Instruction Selection some.
Finally finish identification work, and be input to by load module in the related software of mobile terminal device by the OCR identification module.
Fig. 2: select, discern and import the embodiment explanation and the embodiment explanation of selecting, discern and import phrase of word, individual character.
Wherein, the darker marking is represented hot spot on Chinese character " in vain " and English " dream ".
Fig. 3: select, discern and import the embodiment explanation of sentence.
Wherein, the darker marking is represented hot spot on Chinese character " thousand " and English " I ".
Embodiment
Below in conjunction with accompanying drawing, the specific embodiment of the present invention is further specified.
At first, mobile device possesses camera head, as camera and beam launcher.
Specific embodiment one:
From text shown in Figure 2, Chinese character " Supreme Being " is selected to discern and be input in the mobile terminal device.
The selective rule regulation of present embodiment: first elementary area on the right, identification initial point position is first word, individual character or the symbol that is identified.Its job step is as follows:
1, the beam emissions module starts beam launcher, with the left side formation hot spot of light beam irradiates " Supreme Being " word to text;
2, image capture module starts camera head, takes text and obtains image;
3, image processing module carries out image processing such as slant correction, denoising, counter-rotating, gray scale, is divided into elementary area then, forms the arrangement of elementary area;
4, locating module is sought the position at hot spot place and initial point is discerned in its definition;
5, selecting module is starting point with the identification initial point, selects first elementary area of identification initial point the right;
6, the OCR identification module is discerned selecteed elementary area, obtains the character of Chinese character " Supreme Being ";
7, the load module character that will discern the Chinese character " Supreme Being " that obtains is input in the related software of mobile terminal device.Specific embodiment two:
From text shown in Figure 2, word " dream " is selected to discern and be input in the mobile terminal device.
The selective rule regulation of present embodiment: the elementary area at identification initial point place is first word, individual character or the symbol that is identified.Its job step is as follows:
1, the beam emissions module starts beam launcher, light beam irradiates word " dream " to the text is gone up formed hot spot;
2, image capture module starts camera head, takes text and obtains image;
3, image processing module carries out image processing such as slant correction, denoising, counter-rotating, gray scale, is divided into elementary area then, forms the arrangement of elementary area;
4, locating module is sought the position at hot spot place and initial point is discerned in its definition;
5, selecting module is starting point with the identification initial point, and selecting identification initial point region is first elementary area;
6, the OCR identification module is discerned selecteed elementary area, obtains the character of word " dream ";
7, the load module character that will discern the word " dream " that obtains is input in the related software of mobile terminal device.
Specific embodiment three:
From text shown in Figure 2, Chinese " Baidicheng " is selected to discern and be input in the mobile terminal device.
The selective rule regulation of present embodiment: the identification initial point is positioned at first word or the pairing elementary area of individual character of phrase.Select to the right to the 3rd elementary area.Its job step is as follows:
1, the beam emissions module starts beam launcher, will form hot spot on light beam irradiates " in vain " word in the phrase " Baidicheng ";
2, image capture module starts camera head, takes text and obtains image;
3, image processing module carries out image processing such as slant correction, denoising, counter-rotating, gray scale, is divided into elementary area then, forms the arrangement of elementary area;
4, locating module is sought the position at hot spot place and initial point is discerned in its definition;
5, selecting module is starting point with the identification initial point, select to comprise the identification initial point interior to the right to all images unit of the 3rd elementary area;
6, the OCR identification module is discerned selecteed elementary area, obtains the character of phrase " Baidicheng ";
7, the load module character that will discern the phrase " Baidicheng " that obtains is input in the related software of mobile terminal device.
Specific embodiment four:
From text shown in Figure 2, English phrase " American dream " is selected to discern and be input in the mobile terminal device.
The selective rule regulation of present embodiment: the identification initial point is positioned at last word of phrase or the elementary area of individual character correspondence.Select left to second elementary area.Its job step is as follows:
1, the beam emissions module starts beam launcher, light beam irradiates is gone up to the word " dream " in the phrase " American dream " form hot spot;
2, image capture module starts camera head, takes text and obtains image;
3, image processing module carries out image processing such as slant correction, denoising, counter-rotating, gray scale, is divided into elementary area then, forms the arrangement of elementary area;
4, locating module is sought the position at hot spot place and initial point is discerned in its definition;
5, selecting module is starting point with the identification initial point, select to comprise the identification initial point interior left to all images unit of second elementary area;
6, the OCR identification module is discerned selecteed elementary area, obtains the character of phrase " American dream ";
7, the load module character that will discern the phrase " American dream " that obtains is input in the related software of mobile terminal device.
Specific embodiment five:
" a thousand li Jiangling was gone back on the 1st with Chinese sentence from text shown in Figure 3." select to discern and be input in the mobile terminal device.
The selective rule regulation of present embodiment: the identification initial point is positioned at first word of sentence or the elementary area of individual character correspondence.The identification terminal point is the elementary area of first fullstop correspondence to the right.Its job step is as follows:
1, the beam emissions module starts beam launcher, and " a thousand li Jiangling was gone back on the 1st to sentence with light beam irradiates." in " thousand " word on;
2, image capture module starts camera head, takes text and obtains image;
3, image processing module carries out image processing such as slant correction, denoising, counter-rotating, gray scale, is divided into elementary area then, forms the arrangement of elementary area;
4, locating module is sought the position at hot spot place and initial point is discerned in its definition;
5, selecting module is starting point with the identification initial point, and the definition simultaneously elementary area of first fullstop correspondence to the right is the identification terminal point.The all images unit of selection between identification initial point and identification terminal point;
6, the OCR identification module is discerned selecteed elementary area, obtains the alphabetic character of this sentence;
7, the load module alphabetic character that will discern this sentence that obtains is input in the related software of mobile terminal device.
Specific embodiment six:
From text shown in Figure 3 with fragment " the It is a dream deeply rooted in the American dream.I have a dream that one day this nation will rise up and live out the true meaning of its creed: " We hold these truths to be self-evident of continuous english sentence; That all men are created equal. " " selects identification and is input in the mobile terminal device.
The selective rule regulation of present embodiment: the identification initial point is positioned at first word of sentence or the elementary area of individual character correspondence.The identification terminal point is the elementary area of second western language quotation marks correspondence to the right.Its job step is as follows:
1, the beam emissions module starts beam launcher, and light beam irradiates is arrived on first word " It " of this sentence fragment;
2, image capture module starts camera head, takes text and obtains image;
3, image processing module carries out image processing such as slant correction, denoising, counter-rotating, gray scale, is divided into elementary area then, forms the arrangement of elementary area;
4, locating module is sought the position at hot spot place and initial point is discerned in its definition;
5, selecting module is starting point with the identification initial point, and the definition simultaneously elementary area of second western language quotation marks correspondence to the right is the identification terminal point.The all images unit of selection between identification initial point and identification terminal point;
6, the OCR identification module is discerned selecteed elementary area, obtains the alphabetic character of this sentence;
7, the load module alphabetic character that will discern this sentence that obtains is input in the related software of mobile terminal device.
Claims (10)
1. a character recognition input system and method thereof that adopts optical alignment is characterized in that:
The character recognition input system of described employing optical alignment has two optics apparatus for work on hardware configuration: beam launcher and camera head, and as camera.
Beam launcher emission light beam forms hot spot on the surface of printed text or handwritten text.
Described a kind of character recognition input system that adopts optical alignment, system constitutes and job step comprises:
1-1, beam emissions module, its effect are to send instruction to start beam launcher, and the time length kept of regulation light beam;
1-2, image capture module, its effect are to send instruction to start camera head, and as camera, carries out image is gathered operation;
1-3, image processing module, its effect is that the text image that image capture module obtains is carried out processing such as slant correction, denoising, counter-rotating, gray scale, be that the primary image unit is cut apart with word (alphabetic writing), individual character (Chinese, Japanese, Korean etc.) and symbol then, form the arrangement of forming by elementary area;
1-4, identification original point position module (hereinafter to be referred as locating module), its effect is the position at hot spot place in searching and the definite text image, and this location definition is the identification initial point;
1-5, elementary area select module (hereinafter to be referred as selecting module), and its effect is to be starting point with the identification initial point, and single or a plurality of elementary areas are selected in the requirement according to instruction in a certain direction in matrix of picture cells;
1-6, OCR identification module, its effect are that the elementary area that elementary area selects module to select is identified as literal and symbol;
1-7, load module, its effect are in the related software that will be input to mobile terminal device by the literal and the symbol of OCR identification module acquisition.
2. a kind of character recognition input system and method thereof that adopts optical alignment according to claim 1 is characterized in that, identification original point position module adopts following technology path:
According to beam launcher and camera head relatively-stationary spatial relation is arranged on mobile terminal device, identification original point position module is set up a kind of space reference structure between the two.The principle of work of this space reference structure is: light beam is in a fixing relative position forever at the hot spot of printed text or the formation of text writing surface in the image that image capture module obtains---such as the central point of image.Locating module is defined as the identification initial point with this relative position.
3. a kind of character recognition input system and method thereof that adopts optical alignment according to claim 1 is characterized in that, identification original point position module also adopts following technology path:
Beam emissions module emitted light beams is pointed to the zone at certain particular words, individual character or symbol place in printed text or the text writing, and in this regional inside or the next door form hot spot.After image capture module obtained image, the point at hot spot place becomes to be distinguished in the image obviously not in other regional feature locations.Locating module at first finds this feature locations in image, then this feature locations is defined as the identification initial point.
4. a kind of character recognition input system and method thereof that adopts optical alignment according to claim 1 is characterized in that, elementary area selects module that following rule is followed in the selection of elementary area:
The position of literal target on text that is identified with respect to needs, when the regulation hot spot is positioned at the character zone at starting point place of this target when inner, will define the elementary area of discerning the initial point place be first word, individual character or the symbol that is identified for native system and method so.
5. a kind of character recognition input system and method thereof that adopts optical alignment according to claim 1 is characterized in that, elementary area selects module that following rule is followed in the selection of elementary area:
The position of literal target on text that is identified with respect to needs, when the regulation hot spot is positioned at character zone when next door at the starting point place of this target, will define first elementary area by the identification initial point position be first word, individual character or the symbol that is identified for native system and method so.According to the ways of writing of different language, the next door can be defined as the left side, the right, top or bottom etc.
6. a kind of character recognition input system and method thereof that adopts optical alignment according to claim 1 is characterized in that, elementary area selects module that following rule is followed in the selection of elementary area:
When needs are selected and identification is made up of two or more word, individual character or symbol words symbol combination (as phrase, Chinese idiom, short title etc.), the identification initial point can be arranged in this combination first, on any one word, individual character or the symbol of last or centre or next door.
7. a kind of character recognition input system that adopts optical alignment according to claim 1 is characterized in that, elementary area selects module that following rule is followed in the selection of elementary area:
When needs select and the identification tape punctuation mark than the combination of long word word symbol (as the sentence of title, single sentence or the several successive grown) time, except that definition identification initial point, can a certain specific punctuation mark as the terminal point of discerning (as first right punctuation marks used to enclose the title, the 3rd comma, second branch ... Deng).The Instruction Selection module is only selected the elementary area between identification initial point and identification terminal point in the matrix of picture cells.
8. according to claim 1,2,3,4 and 5 described a kind of character recognition input system and methods thereof that adopt optical alignment, it is characterized in that, when needs with printed text or handwritten text in a certain particular words (alphabetic writing) or individual character (Chinese, Japanese, Korean) identification when being input to mobile terminal device, its job step is as follows:
8-1, beam emissions module start beam launcher, and the inside or the next door of light beam irradiates this particular words, individual character or symbol region to the text formed hot spot;
8-2, image capture module start camera head, take text and obtain image;
8-3, image processing module carry out image processing such as slant correction, denoising, counter-rotating, gray scale, are divided into elementary area then, form the arrangement of elementary area;
8-4, locating module are sought the position at hot spot place and initial point are discerned in its definition;
8-5, selection module are starting point with the identification initial point, select first elementary area according to the principles of claim 4 or 5 regulations;
8-6, OCR identification module are discerned selecteed elementary area;
8-7, load module will be discerned in the related software that the literal that obtains or symbol be input to mobile terminal device.
9. according to claim 1,2,3 and 6 described a kind of character recognition input system and methods thereof that adopt optical alignment, it is characterized in that, when identification was input to mobile terminal device, its job step was as follows for the words symbol combination of being made up of two or more words, individual character or symbol in need be with printed text or handwritten text (as phrase, Chinese idiom, short title etc.):
9-1, beam emissions module start beam launcher, according to selective rule with light beam irradiates zone at certain word, individual character or symbol place in this specific words symbol combination to the text, and in this regional inside or next door formation hot spot;
9-2, image capture module start camera head, take text and obtain image;
9-3, image processing module carry out image processing such as slant correction, denoising, counter-rotating, gray scale, are divided into elementary area then, form the arrangement of elementary area;
9-4, locating module are sought the position at hot spot place and initial point are discerned in its definition;
9-5, selection module are starting point with the identification initial point, select elementary area according to the selective rule of claim 6 regulation;
9-6, OCR identification module are discerned selecteed elementary area;
9-7, load module will be discerned in the related software that the literal that obtains or symbol be input to mobile terminal device.
10. according to claim 1,2,3 and 7 described a kind of character recognition input system and methods thereof that adopt optical alignment, it is characterized in that, in need be with printed text or handwritten text specific band punctuation mark when identification was input to mobile terminal device, its job step was as follows than long word word symbol combination (as the sentence of single sentence, several successive, long title etc.):
10-1, beam emissions module start beam launcher, according to selective rule with light beam irradiates zone at certain word, individual character or symbol place in this specific sentence to the text, and in this regional inside or next door formation hot spot;
10-2, image capture module start camera head, take text and obtain image;
10-3, image processing module carry out image processing such as slant correction, denoising, counter-rotating, gray scale, are divided into elementary area then, form the arrangement of elementary area;
10-4, locating module are sought the position at hot spot place and initial point are discerned in its definition;
10-5, selection module are starting point with the identification initial point, select elementary area according to the selective rule of claim 7 regulation;
10-6, OCR identification module are discerned selecteed elementary area;
The words symbol combination that 10-7, load module will be discerned the band punctuation mark that obtains is input in the related software of mobile terminal device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011100830704A CN102169541A (en) | 2011-04-02 | 2011-04-02 | Character recognition input system using optical localization and method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011100830704A CN102169541A (en) | 2011-04-02 | 2011-04-02 | Character recognition input system using optical localization and method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102169541A true CN102169541A (en) | 2011-08-31 |
Family
ID=44490699
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011100830704A Pending CN102169541A (en) | 2011-04-02 | 2011-04-02 | Character recognition input system using optical localization and method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102169541A (en) |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102572347A (en) * | 2011-12-28 | 2012-07-11 | 高原 | Direction correcting device, projection transmitting device, projection image correcting system and projection image correcting method |
| CN102609699A (en) * | 2012-02-17 | 2012-07-25 | 重庆大学 | Device and method for recognizing number of cast workpiece scanned by laser |
| CN103377379A (en) * | 2012-04-27 | 2013-10-30 | 佳能株式会社 | Text detection device and method and text information extraction system and method |
| CN105427696A (en) * | 2015-11-20 | 2016-03-23 | 江苏沁恒股份有限公司 | Method for distinguishing answer to target question |
| CN105930487A (en) * | 2016-04-29 | 2016-09-07 | 广东小天才科技有限公司 | Topic searching method and device applied to mobile terminal |
| CN105930486A (en) * | 2016-04-29 | 2016-09-07 | 广东小天才科技有限公司 | Rapid search method and device for big data |
| CN105956555A (en) * | 2016-04-29 | 2016-09-21 | 广东小天才科技有限公司 | Method and device for searching questions by photographing |
| CN105975551A (en) * | 2016-04-29 | 2016-09-28 | 广东小天才科技有限公司 | Information searching method and device based on wearable device |
| CN105975193A (en) * | 2016-04-29 | 2016-09-28 | 广东小天才科技有限公司 | Rapid search method and device applied to mobile terminal |
| CN105975557A (en) * | 2016-04-29 | 2016-09-28 | 广东小天才科技有限公司 | Topic searching method and device applied to electronic equipment |
| CN105975565A (en) * | 2016-04-29 | 2016-09-28 | 广东小天才科技有限公司 | Intelligent search method and device applied to electronic equipment |
| CN105975554A (en) * | 2016-04-29 | 2016-09-28 | 广东小天才科技有限公司 | Big data searching method and device based on mobile terminal |
| CN106020662A (en) * | 2016-04-29 | 2016-10-12 | 广东小天才科技有限公司 | Content fast search method and device applied to mobile terminal |
| CN106095246A (en) * | 2016-06-21 | 2016-11-09 | 广东小天才科技有限公司 | Cursor color adjusting method and device |
| CN106126046A (en) * | 2016-08-24 | 2016-11-16 | 广东小天才科技有限公司 | Cursor brightness adjusting method and device |
| CN106202359A (en) * | 2016-07-05 | 2016-12-07 | 广东小天才科技有限公司 | Method and device for searching questions by photographing |
| CN106202539A (en) * | 2016-07-25 | 2016-12-07 | 广东小天才科技有限公司 | Aggregation search method and device |
| CN106293840A (en) * | 2016-08-11 | 2017-01-04 | 广东小天才科技有限公司 | Application program starting method and device |
| CN106815581A (en) * | 2017-01-19 | 2017-06-09 | 珠海格力电器股份有限公司 | Document input method, system and electronic equipment |
| CN107220242A (en) * | 2017-04-19 | 2017-09-29 | 广东小天才科技有限公司 | Translation method, device and system based on translation pen |
| CN109766880A (en) * | 2018-12-29 | 2019-05-17 | 航天信息股份有限公司 | Hand-held input system |
| CN110196646A (en) * | 2019-05-29 | 2019-09-03 | 维沃移动通信有限公司 | A kind of data inputting method and mobile terminal |
| CN110276335A (en) * | 2019-07-04 | 2019-09-24 | 华中师范大学 | A kind of mobile terminal paper acquisition method and device |
| CN111079760A (en) * | 2019-08-02 | 2020-04-28 | 广东小天才科技有限公司 | Character recognition method and electronic equipment |
| CN112308063A (en) * | 2019-07-29 | 2021-02-02 | 京东方科技集团股份有限公司 | Character recognition device, translation pen, image translation method, and image translation device |
| CN112926587A (en) * | 2021-02-19 | 2021-06-08 | 北京大米未来科技有限公司 | Text recognition method and device, readable storage medium and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1804858A (en) * | 2005-01-10 | 2006-07-19 | 赵国成 | Novel assistant positioning system for implementing OCR function on mobile terminals with camera |
| CN1877598A (en) * | 2005-06-06 | 2006-12-13 | 英华达(上海)电子有限公司 | Method for gathering and recording business card information in mobile phone by using image recognition |
| CN101335801A (en) * | 2008-05-09 | 2008-12-31 | 上海合合信息科技发展有限公司 | Scanning method combining camera and optical positioning |
| CN101493996A (en) * | 2009-01-15 | 2009-07-29 | 北方工业大学 | Intelligent reader and implementation method thereof |
| CN201535956U (en) * | 2009-07-24 | 2010-07-28 | 王昊 | Optical positioning point-to-read machine |
-
2011
- 2011-04-02 CN CN2011100830704A patent/CN102169541A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1804858A (en) * | 2005-01-10 | 2006-07-19 | 赵国成 | Novel assistant positioning system for implementing OCR function on mobile terminals with camera |
| CN1877598A (en) * | 2005-06-06 | 2006-12-13 | 英华达(上海)电子有限公司 | Method for gathering and recording business card information in mobile phone by using image recognition |
| CN101335801A (en) * | 2008-05-09 | 2008-12-31 | 上海合合信息科技发展有限公司 | Scanning method combining camera and optical positioning |
| CN101493996A (en) * | 2009-01-15 | 2009-07-29 | 北方工业大学 | Intelligent reader and implementation method thereof |
| CN201535956U (en) * | 2009-07-24 | 2010-07-28 | 王昊 | Optical positioning point-to-read machine |
Cited By (41)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102572347A (en) * | 2011-12-28 | 2012-07-11 | 高原 | Direction correcting device, projection transmitting device, projection image correcting system and projection image correcting method |
| CN102572347B (en) * | 2011-12-28 | 2018-02-13 | 泉州市恋乡文化发展有限公司 | Direction apparatus for correcting, projection emission device, projected image correction system and projection image correcting method |
| CN102609699A (en) * | 2012-02-17 | 2012-07-25 | 重庆大学 | Device and method for recognizing number of cast workpiece scanned by laser |
| CN103377379A (en) * | 2012-04-27 | 2013-10-30 | 佳能株式会社 | Text detection device and method and text information extraction system and method |
| CN105427696A (en) * | 2015-11-20 | 2016-03-23 | 江苏沁恒股份有限公司 | Method for distinguishing answer to target question |
| CN105975565A (en) * | 2016-04-29 | 2016-09-28 | 广东小天才科技有限公司 | Intelligent search method and device applied to electronic equipment |
| CN106020662B (en) * | 2016-04-29 | 2019-04-30 | 广东小天才科技有限公司 | Content fast search method and device applied to mobile terminal |
| CN105975551A (en) * | 2016-04-29 | 2016-09-28 | 广东小天才科技有限公司 | Information searching method and device based on wearable device |
| CN105975193A (en) * | 2016-04-29 | 2016-09-28 | 广东小天才科技有限公司 | Rapid search method and device applied to mobile terminal |
| CN105975557A (en) * | 2016-04-29 | 2016-09-28 | 广东小天才科技有限公司 | Topic searching method and device applied to electronic equipment |
| CN105930486A (en) * | 2016-04-29 | 2016-09-07 | 广东小天才科技有限公司 | Rapid search method and device for big data |
| CN105975554A (en) * | 2016-04-29 | 2016-09-28 | 广东小天才科技有限公司 | Big data searching method and device based on mobile terminal |
| CN106020662A (en) * | 2016-04-29 | 2016-10-12 | 广东小天才科技有限公司 | Content fast search method and device applied to mobile terminal |
| CN105930487B (en) * | 2016-04-29 | 2019-11-26 | 广东小天才科技有限公司 | Topic searching method and device applied to mobile terminal |
| CN105956555A (en) * | 2016-04-29 | 2016-09-21 | 广东小天才科技有限公司 | Method and device for searching questions by photographing |
| CN105975193B (en) * | 2016-04-29 | 2019-07-05 | 广东小天才科技有限公司 | Rapid search method and device applied to mobile terminal |
| CN105975557B (en) * | 2016-04-29 | 2020-01-03 | 广东小天才科技有限公司 | Topic searching method and device applied to electronic equipment |
| CN105975551B (en) * | 2016-04-29 | 2019-11-26 | 广东小天才科技有限公司 | information searching method and device based on wearable device |
| CN105975554B (en) * | 2016-04-29 | 2020-05-29 | 广东小天才科技有限公司 | Big data searching method and device based on mobile terminal |
| CN105975565B (en) * | 2016-04-29 | 2020-03-20 | 广东小天才科技有限公司 | Intelligent search method and device applied to electronic equipment |
| CN105930487A (en) * | 2016-04-29 | 2016-09-07 | 广东小天才科技有限公司 | Topic searching method and device applied to mobile terminal |
| CN106095246A (en) * | 2016-06-21 | 2016-11-09 | 广东小天才科技有限公司 | Cursor color adjusting method and device |
| CN106202359A (en) * | 2016-07-05 | 2016-12-07 | 广东小天才科技有限公司 | Method and device for searching questions by photographing |
| CN106202539A (en) * | 2016-07-25 | 2016-12-07 | 广东小天才科技有限公司 | Aggregation search method and device |
| CN106202539B (en) * | 2016-07-25 | 2019-07-26 | 广东小天才科技有限公司 | Aggregation search method and device |
| CN106293840A (en) * | 2016-08-11 | 2017-01-04 | 广东小天才科技有限公司 | Application program starting method and device |
| CN106126046A (en) * | 2016-08-24 | 2016-11-16 | 广东小天才科技有限公司 | Cursor brightness adjusting method and device |
| CN106815581A (en) * | 2017-01-19 | 2017-06-09 | 珠海格力电器股份有限公司 | Document input method, system and electronic equipment |
| CN107220242A (en) * | 2017-04-19 | 2017-09-29 | 广东小天才科技有限公司 | Translation method, device and system based on translation pen |
| CN109766880A (en) * | 2018-12-29 | 2019-05-17 | 航天信息股份有限公司 | Hand-held input system |
| WO2020238938A1 (en) * | 2019-05-29 | 2020-12-03 | 维沃移动通信有限公司 | Information input method and mobile terminal |
| CN110196646A (en) * | 2019-05-29 | 2019-09-03 | 维沃移动通信有限公司 | A kind of data inputting method and mobile terminal |
| CN110276335A (en) * | 2019-07-04 | 2019-09-24 | 华中师范大学 | A kind of mobile terminal paper acquisition method and device |
| CN112308063A (en) * | 2019-07-29 | 2021-02-02 | 京东方科技集团股份有限公司 | Character recognition device, translation pen, image translation method, and image translation device |
| WO2021018110A1 (en) * | 2019-07-29 | 2021-02-04 | 京东方科技集团股份有限公司 | Translation pen and control method therefor |
| CN112308063B (en) * | 2019-07-29 | 2022-07-29 | 京东方科技集团股份有限公司 | Character recognition device, translation pen, image translation method, and image translation device |
| US12045580B2 (en) | 2019-07-29 | 2024-07-23 | Boe Technology Group Co., Ltd. | Translation pen and control method therefor |
| CN111079760A (en) * | 2019-08-02 | 2020-04-28 | 广东小天才科技有限公司 | Character recognition method and electronic equipment |
| CN111079760B (en) * | 2019-08-02 | 2023-11-28 | 广东小天才科技有限公司 | Character recognition method and electronic equipment |
| CN112926587A (en) * | 2021-02-19 | 2021-06-08 | 北京大米未来科技有限公司 | Text recognition method and device, readable storage medium and electronic equipment |
| CN112926587B (en) * | 2021-02-19 | 2024-03-29 | 北京大米未来科技有限公司 | Text recognition method and device, readable storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102169541A (en) | Character recognition input system using optical localization and method thereof | |
| CN107656922B (en) | Translation method, translation device, translation terminal and storage medium | |
| CN107885430B (en) | Audio playing method and device, storage medium and electronic equipment | |
| US11423700B2 (en) | Method, apparatus, device and computer readable storage medium for recognizing aerial handwriting | |
| US9245193B2 (en) | Dynamic selection of surfaces in real world for projection of information thereon | |
| US7239747B2 (en) | Method and system for locating position in printed texts and delivering multimedia information | |
| US20210232298A1 (en) | Detection and visualization of a formation of a tangible interface object | |
| JP4533273B2 (en) | Image processing apparatus, image processing method, and program | |
| US20140056475A1 (en) | Apparatus and method for recognizing a character in terminal equipment | |
| CN105279152B (en) | A kind of method and apparatus for taking word to translate | |
| US20110252316A1 (en) | Translating text on a surface computing device | |
| JP2013034168A (en) | Image projection device, image projection control device, and program | |
| JP4785655B2 (en) | Document processing apparatus and document processing method | |
| US9207808B2 (en) | Image processing apparatus, image processing method and storage medium | |
| JP2009020889A (en) | Method and system for retrieving electronic document | |
| KR20090053177A (en) | Apparatus and method for recognizing characters | |
| CN102201053A (en) | Method for cutting edge of text image | |
| CN102855298A (en) | Image retrieval method and system | |
| CN109271616B (en) | Intelligent extraction method based on bibliographic characteristic value of standard literature | |
| CN104978577B (en) | Information processing method, device and electronic equipment | |
| CN111310634A (en) | Generation method of certificate type identification template, certificate identification method and device | |
| CN102682457A (en) | Rearrangement method for performing adaptive screen reading on print media image | |
| CN105204752B (en) | Projection realizes interactive method and system in reading | |
| JP2016038821A (en) | Image processing apparatus | |
| KR20130054116A (en) | Method and system for digitizing and utilizing paper documents through transparent display. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20110831 |