CN1310181C - Optical character identifying treating method for mobile terminal with camera - Google Patents
Optical character identifying treating method for mobile terminal with camera Download PDFInfo
- Publication number
- CN1310181C CN1310181C CNB2004100744427A CN200410074442A CN1310181C CN 1310181 C CN1310181 C CN 1310181C CN B2004100744427 A CNB2004100744427 A CN B2004100744427A CN 200410074442 A CN200410074442 A CN 200410074442A CN 1310181 C CN1310181 C CN 1310181C
- Authority
- CN
- China
- Prior art keywords
- mobile terminal
- processing
- horizontal line
- optical character
- target 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 230000003287 optical effect Effects 0.000 title claims abstract 5
- 238000012545 processing Methods 0.000 claims abstract description 15
- 238000003672 processing method Methods 0.000 claims abstract description 9
- 238000012805 post-processing Methods 0.000 claims abstract description 5
- 238000012015 optical character recognition Methods 0.000 claims description 29
- 239000003550 marker Substances 0.000 claims description 5
- 230000008569 process Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000003709 image segmentation Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Landscapes
- Character Input (AREA)
Abstract
The present invention discloses an optical character identifying and processing method for mobile terminals with image pick-up devices, which is characterized in that the optical character identifying and processing method for mobile terminals with image pick-up devices comprises steps that an area which needs to be processed is determined on a target image; characters in the area are segmented out according to the position information of the area which needs to be processed corresponding to the image; the segmented characters are identified, and post-processing is carried out for a result after the characters are identified. When information identification is carried out for the target image by utilizing the method of the present invention, the method can directly help a cell phone user to limit a character area which needs to be identified with pertinence, and subsequent OCR processing only processes the characters in the limited area. Thus, interference generated by non-emphasis information is reduced, and the accuracy of identification results is also enhanced greatly.
Description
Technical Field
The present invention relates to Optical Character Recognition (OCR), and more particularly, to an optical character recognition processing method for a mobile terminal with an image pickup device.
Background
As technology has evolved, Optical Character Recognition (OCR) has entered different application areas. From bar code recognition to number and letter recognition, even printed text is entered into a computer using a scanner in conjunction with chinese Optical Character Recognition (OCR) software.
In the prior art, mobile phones, digital cameras and some handheld scanning devices with OCR functions have appeared, which can take pictures of target objects, recognize useful text information in the photographed images by using an embedded OCR function entity or an image processing chip, and store the useful text information.
However, when the mobile phones or handheld devices identify images, the entire picture is generally identified, which is poor in pertinence and causes a high error rate of the identification result; the amount of non-key information to be identified is large, and interference is easily formed on the key information; in addition, since all the screens are recognized, the overall processing speed is also slow.
Disclosure of Invention
The invention aims to provide an optical character recognition processing method of a mobile terminal with a camera device, which has strong pertinence, high speed, less interference of non-key information and relatively high accuracy when useful information is recognized.
According to the above object of the present invention, the present invention proposes the following:
an optical character recognition processing method of a mobile terminal with a camera device comprises the following steps:
determining a region to be processed on a target image;
dividing the characters of the region to be processed according to the position information of the region to be processed corresponding to the image;
and recognizing the segmented characters, and performing post-processing on the recognized result.
Wherein,
the determination of the region to be processed on the target image in the method of the invention can be realized by the following method: pressing a character row to be recognized through an auxiliary recognition horizontal line; the thickness of the lines and the color change do not depart from the protection scope of the invention;
the height position of the horizontal line on the target image can be adjusted;
setting a marker for determining the initial position of character recognition on the horizontal line;
setting a marker for determining the character recognition end position on the horizontal line;
the identifier is a mark which can be obviously compared with the horizontal line, such as a dot, a triangular dot or other patterns;
the horizontal position of the identifier on the horizontal line can be adjusted;
in addition, the determination of the region to be processed on the target image can also be achieved by the following method: defining a character line to be recognized through an auxiliary recognition area frame;
the area frame is a rectangular frame, the virtual and real of the frame line do not depart from the protection scope of the invention, and even a rectangular area surrounded by four rectangular frame corners can be provided;
the height and width of the rectangular frame can be adjusted.
Compared with the prior art, the invention has the advantages that:
when the method of the invention is used for identifying the information of the target image, the method can directly help the mobile phone user to pertinently limit the character area to be identified, and the subsequent OCR processing only processes the characters in the limited area, thereby reducing the interference generated by non-key information and greatly improving the accuracy of the identification result.
The above and other objects, features and advantages of the present invention will become more apparent from the following detailed description of certain embodiments thereof, when taken in conjunction with the accompanying drawings.
Drawings
FIG. 1 is a schematic diagram of a character row to be recognized being held down by a horizontal line for assisting recognition;
FIG. 2 is a schematic diagram of a character line to be recognized defined by a rectangular frame for assisting recognition;
fig. 3 is a flow chart of the method implementation of the present invention in a specific embodiment.
DETAILED DESCRIPTION OF EMBODIMENT (S) OF INVENTION
In the following description, well-known functions or constructions are not described in detail to avoid unnecessarily obscuring the present invention.
The scheme of the invention comprises the following steps:
determining a region to be processed on a target image; (character line to be recognized can be held down by horizontal line for auxiliary recognition)
Dividing the character of the region according to the position information of the region to be processed corresponding to the image; (using image segmentation function in OCR function entity)
And recognizing the segmented characters, and performing post-processing on the recognized result.
The method of the present invention is described below by taking a mobile phone capable of taking pictures as an example.
The hardware basis of the OCR function in the camera mobile phone is a camera built in or out of the mobile phone and an image processing chip of the mobile phone embedded digital camera; the shooting function is to complete the capture of a pair of images by driving software or hardware;
as shown in fig. 1, the method is a schematic diagram of performing recognition by pressing a character row to be recognized by a horizontal line for assisting recognition.
After the shooting function is started, a screen of the mobile phone can display a what-you-see-is-what-you-get real-time image in real time;
at this time, if the mobile phone user starts the character recognition function, a horizontal line appears on the display screen of the mobile phone by the OCR functional entity or the image processing chip embedded in the mobile phone:
meanwhile, a marked dot (equivalent to the origin of a coordinate axis) can be arranged on the horizontal line, and the dot is marked by a large circular dot or other patterns;
using a mobile phone to aim at a shooting object (such as a business card), if a certain row of characters are required to be recognized, adjusting the relative position and angle between a camera and the object to enable the horizontal line to just press the row of the characters to be recognized, and simultaneously enabling a dot point to be positioned at the position before the first character to be recognized, and pressing a shutter to capture an image;
or after capturing the image, adjusting the positions of a horizontal line and a dot on the mobile phone to enable the horizontal line to just press the line where the character to be recognized is located and enable the dot to be located at the position before the first character to be recognized;
when the OCR functional entity recognizes the image, the relative position of the horizontal line in the image is utilized to determine the auxiliary positioning information, and characters at the position of the image are directly extracted and recognized and converted into ASCII codes or characters to be output.
Wherein the horizontal line on the LCD is located at a middle height position of the LCD; by setting, the height of the horizontal line and the position of the dots can be changed; the height position information is divided with the image in the following OCR function module; extracting character function related information; the image segmentation algorithm in the OCR functional entity is carried out by utilizing the height and the position information of the dots, the accuracy is well ensured, and the direct contribution is made to improving the character recognition rate and reducing the false recognition rate.
The specific process of defining the region to be identified by the horizontal lines and dots may refer to the following method:
after the internal binarization processing is carried out on the input image, the characters are black, and the line intervals are white;
knowing that the horizontal line passes through the line of characters to be recognized and that the first character is located behind the dot;
scanning horizontally from left to right from the horizontal line upwards and downwards respectively, and if the sum of the gray values of pixels passing through the scanning is smaller than a smaller threshold value, indicating that the upper boundary or the lower boundary of the character line is reached;
thereby obtaining the longitudinal boundary coordinates of the character line;
meanwhile, when the dot corresponds to the position in the shot image, the left boundary of the character string is obtained;
this allows the character string to be segmented from the original image for subsequent single character recognition.
Of course, the height position of the horizontal line on the target image in the above scheme can be adjusted; the horizontal position of the identifier on the horizontal line can be adjusted; a marker for determining the character recognition end position may be provided on the horizontal line.
The scheme can be widely applied to various scenes, such as the recognition of business cards, the recognition of telephone numbers of advertising boards and other information, the recognition of vehicle license plates and the recognition of related information in newspapers and periodicals. The purpose of utilizing the camera mobile phone for identification is to combine identification and storage, and voice or data communication, so that people can obtain information, share the information and utilize the information more conveniently.
Fig. 3 is a flow chart for implementing the above scheme.
A user of the mobile phone operates to adjust the horizontal line and the dot point for assisting in recognition to press the character row to be recognized, so that the dot point is positioned in front of the character to be recognized;
an image segmentation functional module in the OCR functional entity segments line characters by utilizing the position information of the auxiliary horizontal line corresponding to the image;
the character recognition function module in the OCR function entity recognizes the segmented characters;
the mobile phone operator performs post-processing (operations such as storage, transmission, dialing and the like) by using the obtained character result.
Of course, the determination of the region to be processed on the target image may also be performed by defining the character line to be recognized through an auxiliary recognition region frame as shown in fig. 2; FIG. 2 illustrates a rectangular area defined by four rectangular frame corners to define a character area with recognized characters; this form is more intuitive than horizontal. Of course, the height and width of the rectangular frame may also be set to be adjustable.
The method for processing optical character recognition of a mobile terminal with camera means according to the present invention is not limited to the application listed in the description and the embodiments, but the solution described above can be applied to other electronic products capable of taking pictures, such as digital cameras, digital video cameras, etc., which are well adapted to various fields suitable for the present invention, and further advantages and modifications can be easily implemented by those skilled in the art, so that the present invention is not limited to the specific details, the representative devices and the illustrative examples shown and described herein, without departing from the spirit and scope of the general concept defined by the claims and their equivalents.
Claims (11)
1. An optical character recognition processing method of a mobile terminal with a camera device is characterized by comprising the following steps:
a. determining a region to be processed on a target image;
b. dividing the characters of the region to be processed according to the position information of the region to be processed corresponding to the image;
c. and recognizing the segmented characters, and performing post-processing on the recognized result.
2. The method for recognizing and processing the optical character of the mobile terminal with the camera device according to the claim 1, wherein the determination of the region to be processed on the target image can be realized by the following method: the character row to be recognized is pressed by a horizontal line which assists the recognition.
3. The method for processing optical character recognition of a mobile terminal with camera according to claim 2, wherein the height position of the horizontal line on the target image is adjustable.
4. The optical character recognition processing method of a mobile terminal with camera according to claim 2, characterized in that a marker for determining a character recognition start position is set on the horizontal line.
5. The method for processing optical character recognition of a mobile terminal with camera according to claim 4,
after internal binarization processing is carried out on the target image, the characters are black, and line intervals are white;
knowing that the horizontal line holds down the row of characters to be recognized and that the first character is located after the identifier;
performing horizontal scanning from left to right upwards from the horizontal line, and if the sum of the gray values of the pixels passing through the scanning is smaller than a threshold value, indicating that the upper boundary of the character line is reached;
performing horizontal scanning from left to right downwards from the horizontal line, and if the sum of the gray values of the pixels passing through the scanning is smaller than a threshold value, indicating that the lower boundary of the character line is reached;
thereby obtaining the longitudinal boundary coordinates of the character line;
meanwhile, the left boundary of the character string is obtained by the position of the identifier corresponding to the target image;
this allows the string to be segmented from the target image for subsequent single character recognition.
6. The optical character recognition processing method of a mobile terminal with camera according to claim 2, characterized in that a marker for specifying a character recognition end position is set on the horizontal line.
7. The method as claimed in claim 4 or 6, wherein the identifier is a dot or other pattern that can be compared with the horizontal line.
8. The method for processing optical character recognition of a mobile terminal with camera device according to claim 4 or 6, wherein the horizontal position of the identifier on the horizontal line can be adjusted.
9. The method for recognizing and processing the optical character of the mobile terminal with the camera device according to the claim 1, wherein the determination of the region to be processed on the target image can be realized by the following method: the character line to be recognized is defined by a recognition-assisted area frame.
10. The method as claimed in claim 9, wherein the area frame is a rectangular frame.
11. The method for processing optical character recognition of a mobile terminal with camera device according to claim 10, wherein the height position or horizontal position of the rectangular frame on the target image, and the height and width of the rectangular frame itself are adjustable.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2004100744427A CN1310181C (en) | 2004-09-15 | 2004-09-15 | Optical character identifying treating method for mobile terminal with camera |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2004100744427A CN1310181C (en) | 2004-09-15 | 2004-09-15 | Optical character identifying treating method for mobile terminal with camera |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN1750016A CN1750016A (en) | 2006-03-22 |
| CN1310181C true CN1310181C (en) | 2007-04-11 |
Family
ID=36605453
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB2004100744427A Expired - Fee Related CN1310181C (en) | 2004-09-15 | 2004-09-15 | Optical character identifying treating method for mobile terminal with camera |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN1310181C (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102238326A (en) * | 2010-04-27 | 2011-11-09 | Tcl集团股份有限公司 | Method, device and photo taking equipment for performing information record on shooting object |
| JP5647919B2 (en) * | 2011-03-07 | 2015-01-07 | 株式会社Ｎｔｔドコモ | Character recognition device, character recognition method, character recognition system, and character recognition program |
| JP2013037462A (en) * | 2011-08-05 | 2013-02-21 | Sony Corp | Information processor and information processing method |
| CN103595861A (en) * | 2013-10-23 | 2014-02-19 | 南京邮电大学 | Method for enabling terminal to identify phone number and automatically dial or send text message |
| CN104239888B (en) * | 2014-09-10 | 2017-06-30 | 河海大学 | One kind is based on Water meter disc-annular shape arrangement embossing seal character localization method |
| JP6342298B2 (en) * | 2014-10-31 | 2018-06-13 | 株式会社東芝 | Character recognition device, image display device, image search device, character recognition method and program |
| JP6675831B2 (en) * | 2015-03-27 | 2020-04-08 | 株式会社日立産機システム | Print inspection method, print inspection apparatus using the same, and print inspection apparatus main body |
| CN104915332B (en) * | 2015-06-15 | 2017-09-15 | 广东欧珀移动通信有限公司 | A kind of method and device for generating layout template |
| CN105373790B (en) * | 2015-10-23 | 2019-02-05 | 北京汉王数字科技有限公司 | Printed page analysis method and apparatus |
| CN107861667B (en) * | 2017-11-29 | 2020-07-28 | 维沃移动通信有限公司 | Method for arranging desktop application icons and mobile terminal |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5033097A (en) * | 1987-10-26 | 1991-07-16 | Ricoh Company, Ltd. | Character recognition method |
| US5619592A (en) * | 1989-12-08 | 1997-04-08 | Xerox Corporation | Detection of highlighted regions |
| US20020191847A1 (en) * | 1998-05-06 | 2002-12-19 | Xerox Corporation | Portable text capturing method and device therefor |
| CN2587124Y (en) * | 2002-10-22 | 2003-11-19 | 宋柏君 | Embedded OCR mobile phone |
| CN1474994A (en) * | 2000-11-17 | 2004-02-11 | �Ÿ���˹ | Applications for mobile digital camera, that distinguish between text and imag-information in an image |
| CN1489359A (en) * | 2002-10-08 | 2004-04-14 | 宋柏君 | OCR mobile phone |
-
2004
- 2004-09-15 CN CNB2004100744427A patent/CN1310181C/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5033097A (en) * | 1987-10-26 | 1991-07-16 | Ricoh Company, Ltd. | Character recognition method |
| US5619592A (en) * | 1989-12-08 | 1997-04-08 | Xerox Corporation | Detection of highlighted regions |
| US20020191847A1 (en) * | 1998-05-06 | 2002-12-19 | Xerox Corporation | Portable text capturing method and device therefor |
| CN1474994A (en) * | 2000-11-17 | 2004-02-11 | �Ÿ���˹ | Applications for mobile digital camera, that distinguish between text and imag-information in an image |
| CN1489359A (en) * | 2002-10-08 | 2004-04-14 | 宋柏君 | OCR mobile phone |
| CN2587124Y (en) * | 2002-10-22 | 2003-11-19 | 宋柏君 | Embedded OCR mobile phone |
Also Published As
| Publication number | Publication date |
|---|---|
| CN1750016A (en) | 2006-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3163504B1 (en) | Method, device and computer-readable medium for region extraction | |
| CN107977659B (en) | Character recognition method and device and electronic equipment | |
| CN101667251B (en) | OCR recognition method and device with auxiliary positioning function | |
| CN1278533C (en) | Handset capable of automatically recording characters and images, and method of recording and processing thereof | |
| CN1310181C (en) | Optical character identifying treating method for mobile terminal with camera | |
| CN102063611B (en) | Method and system for inputting characters | |
| CN107767379B (en) | PCB label printing quality detection method | |
| KR101907414B1 (en) | Apparus and method for character recognition based on photograph image | |
| CN1207924C (en) | Method for testing face by image | |
| CN1303517C (en) | Image processing apparatus, image processing method and computer program | |
| CN103984930A (en) | Digital meter recognition system and method based on vision | |
| CN113012059B (en) | Shadow elimination method and device for text image and electronic equipment | |
| CN1691050A (en) | 2D rectangular code symbol scanning device and 2D rectangular code symbol scanning method | |
| CN105809166A (en) | Vehicle license plate recognition method, device and system | |
| CN112418214B (en) | Vehicle identification code identification method and device, electronic equipment and storage medium | |
| CN1878182A (en) | Name card input recognition mobile phone and its recognizing method | |
| CN1172264C (en) | Method for automatically identifying characters on texture background by means of combination of background and character model | |
| CN1804858A (en) | Novel assistant positioning system for implementing OCR function on mobile terminals with camera | |
| CN113159029A (en) | Method and system for accurately capturing local information in picture | |
| CN110059695B (en) | Character segmentation method based on vertical projection and terminal | |
| KR100802605B1 (en) | Apparatus and method of recognizing numerals from vehicle licenseplate | |
| CN1154039C (en) | Device and method for recording hand-written information | |
| CN102567982A (en) | Extraction system and method for specific information of video frequency program and mobile terminal | |
| CN113533375A (en) | Forward and reverse scanning modeling detection method for printed circuit board | |
| CN2829225Y (en) | Mobile phone with namecard identification function |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20070411 Termination date: 20120915 |