CN100349172C - Method for pickup mobile terminal to identify business card under the nonideal condition - Google Patents
Method for pickup mobile terminal to identify business card under the nonideal condition Download PDFInfo
- Publication number
- CN100349172C CN100349172C CNB2005100634402A CN200510063440A CN100349172C CN 100349172 C CN100349172 C CN 100349172C CN B2005100634402 A CNB2005100634402 A CN B2005100634402A CN 200510063440 A CN200510063440 A CN 200510063440A CN 100349172 C CN100349172 C CN 100349172C
- Authority
- CN
- China
- Prior art keywords
- character
- business card
- image
- identification
- mobile terminal
- 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 38
- 239000004744 fabric Substances 0.000 claims description 26
- 238000010586 diagram Methods 0.000 description 4
- 238000012015 optical character recognition Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000007812 deficiency Effects 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 1
- 238000011065 in-situ storage Methods 0.000 description 1
Images
Landscapes
- Character Input (AREA)
- Character Discrimination (AREA)
Abstract
The present invention discloses a method for an image pickup mobile terminal to identify business cards under the non ideal conditions. The present invention comprises the following steps: step 1, auxiliary positioning identification is arranged on a mobile terminal with an image pickup device; step 2, the auxiliary positioning identification is adopted for positioning character zones to be identified on the business card; step 3, the business card is continuous taken photos for at least twice, so at least two business card images are obtained; step 4, the business card image is analyzed to judge whether characters exists in auxiliary positioning identification images on the business card image; step 5, when one image accords with the condition of the step 4, character identification processing is carried out in the character zone to be identified of the image; when at least two images accord with the condition of the step 4, the character identification processing is respectively carried out in each character zone to be identified of the images which accord with the condition, the character identification results of each image are carried out for validity judgment to obtain final results; when no image accord with the condition of the step 4, the business card identification judgement fails.
Description
Technical field
The present invention relates to the method that a kind of business card scan carries out literal identification, under particularly a kind of undesirable condition, the portable terminal that can make a video recording carries out the method for business card identification.
Technical background
At present, the method of the auxiliary positioning optical character recognition of the portable terminal of band camera head generally all is that business card to be identified is placed on the horizontal table top, auxiliary positioning with portable terminal identifies on the zone to be identified that moves on on the business card then, and adopt the camera head of portable terminal that it is carried out once photo taking, obtain still image, the character information that utilizes this still image of optical character recognition tool analysis to comprise then, thus Word message in the zone to be identified obtained.To establish a capital be (business card being positioned on the horizontal table top of carrying out under very desirable condition yet the environment when the optical character recognition system of band camera head portable terminal discerns business card often differs, light is even, device there is no any violent rocking during shooting, and this situation can be regarded ideal conditions as).Sometimes the operator wish can be when he arbitrarily takes out business card, operation such as carry out the identification of business card literal after utilizing the camera head of portable terminal that it is taken pictures or dial.This moment, the effect of identification was also inequality owing to the various scene differences of operation.In more stable scene such as the operator operation that is seated, common optical character recognition method can obtain good recognition effect, and be in the compartment in the scene of relatively upheaval, when the common method of utilization is taken in the walking, owing to the reason of rocking, locating effect is not necessarily fine, in most cases can be subjected to displacement and causes discerning the situation of makeing mistakes.Therefore be badly in need of the method for the business card identification under undesirable situation, to remedy the deficiencies in the prior art.
Summary of the invention
The objective of the invention is: at the deficiencies in the prior art, provide a kind of simple to operate, easy to use, but particularly be applicable to the method for pickup mobile terminal business card identification under the undesirable condition.
In order to solve the problems of the technologies described above, the technical solution used in the present invention is: but the method for pickup mobile terminal business card identification under a kind of undesirable condition comprises the steps:
Character zone to be identified on step 2, the employing auxiliary positioning mark location business card;
Step 3, business card is taken pictures at least twice continuously, thereby obtain at least two width of cloth business card images;
Step 4, analyze described business card image, judge on every width of cloth business card image whether have character in the auxiliary positioning identification image;
If step 5 meets the piece image that has only of step 4 condition, then in the character zone to be identified of this image, carry out character recognition and handle, thereby obtain the result that final business card is discerned;
If meet two width of cloth images that have at least of step 4 condition, then carry out the character recognition processing in the character zone to be identified to qualified image respectively, and the character identification result of each width of cloth image is carried out validity judge, thereby obtain the result of final business card identification;
If do not meet the image of step 4 condition, then judge this time business card recognition failures.
In the described step 5 character identification result being carried out the method that validity judges can be specially: the character identification result of each width of cloth image is carried out the comparison of individual character, add up the quantity of individual character inequality, thereby judge the validity of character identification result according to the individual character comparison result.
When all individual character identification homogeneous phase whiles, can think that then the character identification result of each width of cloth image is identical, get the wherein result of the final business card identification of character identification result conduct of a sub-picture.
When comparing, individual character has individual character identification inequality, and when the quantitative proportion that can work as individual character inequality is lower than a pre-set threshold, the degree of confidence of each character in the character identification result of each width of cloth image relatively respectively then, and get the result of that character of degree of confidence maximum as final character recognition.
Described degree of confidence can be degree of confidence for the sum of errors of getting distance.
When individual character is compared, there is individual character identification inequality, and when the quantitative proportion of individual character inequality is higher than a pre-set threshold, then can judges this time business card recognition failures.
Described auxiliary positioning sign can be horizontal line or rectangle frame.
Described step 2 can be specially, and moves described horizontal line, and to pushing down character to be identified, thereby the character to be identified that the position level line pressure is lived is a character zone to be identified.
In the described step 4, can with the horizontal line benchmark, horizontal scanning image from left to right successively up or down, thus whether the image-region of searching the horizontal line place exists character.
Open the step that secondary light source carries out floor light before can also being included in described step 2.
In technique scheme, the present invention is because under undesirable condition, can utilize the character area to be identified on the auxiliary positioning mark location business card that the dollying device had, and, obtain final literal recognition result thereby from multiple image, analyze by the acquisition multiple image of repeatedly taking pictures to this zone.Therefore, the present invention can improve the accuracy of the literal identification under undesirable condition, effectively reduces false recognition rate, and relative prior art, has characteristics such as easy to use, that degree of intelligence is higher.
Description of drawings
Accompanying drawing 1 is the process flow diagram of the inventive method;
Accompanying drawing 2 is the method flow diagram of a kind of preferred embodiment of the present invention;
Accompanying drawing 3 is the synoptic diagram A of business card image captured in the specific implementation process of the present invention;
Accompanying drawing 4 is the synoptic diagram B of business card image captured in the specific implementation process of the present invention.
Embodiment
Below in conjunction with Figure of description and specific embodiment the present invention is described in further detail.
With reference to the accompanying drawings 1, but the invention provides the method for pickup mobile terminal business card identification under a kind of undesirable condition, comprise the steps:
Character zone to be identified on step 2, the employing auxiliary positioning mark location business card; Generally speaking, be the method (this method is present prior art, ominous herein stating) of utilizing the auxiliary positioning of portable terminal, move described auxiliary positioning sign to described character zone to be identified.Described move operation can have various ways, as utilizes the directionkeys of portable terminal auxiliary positioning to be identified the move operation that carries out upper and lower, left and right; Perhaps, auxiliary positioning sign fixedly is presented at a certain position on the display screen of portable terminal, and the camera of dollying device identifies auxiliary positioning to move relative to business card etc.Its objective is follow-up graphical analysis and literal identification step are only carried out in the character zone to be identified again, thereby reduce identified region, improve recognition speed and accuracy.
Step 3, business card is taken pictures at least twice continuously, thereby obtain at least two width of cloth business card images; Described double at least taking pictures is the continuous camera function that utilizes the camera head of portable terminal, and (in 0.5S) takes pictures repeatedly continuously in a short period of time, to obtain several business card images.
Step 4, analyze described business card image, judge on every width of cloth business card image whether have character in the auxiliary positioning identification image; Particularly, search the auxiliary positioning identification image part on every width of cloth business card image exactly, differentiate whether there is character at this image section then.
If step 5 meets the piece image that has only of step 4 condition, then in the character zone to be identified of this image, carry out character recognition and handle, thereby obtain the result that final business card is discerned;
If meet two width of cloth images that have at least of step 4 condition, then carry out the character recognition processing in the character zone to be identified to qualified image respectively, and the character identification result of each width of cloth image is carried out validity judge, thereby obtain the result of final business card identification;
If do not meet the image of step 4 condition, then judge this time business card recognition failures.
Below in conjunction with accompanying drawing 2, describe a kind of preferable specific embodiment of the present invention in detail.
With reference to figure 2, the flow process of this specific embodiment is as follows:
01) on the portable terminal of band camera head, horizontal line is set in advance and identifies, and horizontal line is presented on the display screen of portable terminal with the form of flicker as auxiliary positioning.Also preestablish the comparison threshold value in addition, described comparison threshold value can be set according to the literal recognition performance of the character recognition instrument of different portable terminals, and present embodiment is set at 50%.
02) when extraneous light condition is undesirable, carries out this step, promptly turn on secondary light source (as the LED lamp) and carry out floor light;
03) camera of camera head is aimed at business card, make demonstration business card to be taken on the portable terminal.Regulate horizontal position, make it push down literal line to be identified on the business card, thereby locate character area to be identified.
04) adopts camera head that business card is taken pictures twice continuously, thereby obtain two width of cloth business card images.
05) with the horizontal line respectively benchmark to two width of cloth images, horizontal scanning image successively from left to right up or down.
06) judge whether the horizontal line on two width of cloth business card images does not all push down character row, if, then jump to step 014, otherwise execution in step 07.Shown in Figure 4ly be the situation that horizontal line (dotted line among the figure) is not pushed down character row.
07) judge whether to have only the horizontal line on the width of cloth business card image to push down character row, if, then jump to step 012, otherwise execution in step 08.Shown in Figure 3ly be the situation that horizontal line (dotted line among the figure) has been pushed down character row.
08) character row of respectively horizontal line on two width of cloth images being pushed down carries out the character recognition processing, and the character identification result of each width of cloth image is carried out the comparison of individual character.
09) judge whether that all individual character identification is all identical, if, then jump to step 015, otherwise execution in step 010.
010) the individual character quantity that the statistical recognition result is different is calculated the ratio of its shared individual character comparison result;
011) is the different individual character proportion of recognition result greater than predefined comparison threshold value 50%? if, then jump to step 014, if not, then execution in step 013.
012) have only when horizontal line has been pushed down character row on the sub-picture, this character row is carried out character recognition handle, and as final character identification result output.
013) degree of confidence of each character in the character identification result of each width of cloth image relatively respectively, and that character of getting the degree of confidence maximum is as final character identification result output.The calculating of described degree of confidence will be decided according to the design of the character recognition instrument that portable terminal adopted.Generally speaking, the distance of sum of errors often get to(for) the identification facility of statistical nature is a degree of confidence.Present embodiment promptly adopts this method to calculate degree of confidence.
014) exports this time business card recognition failures information.
015) gets the character identification result of a sub-picture wherein as final business card recognition result output.
In above-mentioned flow process, because under the undesirable condition, as user's scanned business card on the car that starts, the auxiliary positioning sign (horizontal line) that is positioned on the character recognition zone may produce displacement in the process of repeatedly taking pictures, make the position after the horizontal line of pushing down character row is originally taken pictures have three kinds of possibilities, a kind of may be for also in situ, another kind may be for moving to the top or following NULI character zone of former character row, the third may be for moving to its adjacent character row, thereby cause twice recognition result different or invalid.Therefore, by step 06～015, multiple may situation the processing accordingly to existing makes recognition result or obtains correct recognition result, or output recognition failures information, requires the user to discern again.So, then improved under the undesirable condition accuracy of literal identification greatly.
Though above more at large described the present invention, these descriptions only are illustrative and not restrictive.Obviously, the present invention can change in many ways for those of ordinary skill.
For example, be to adopt horizontal line or rectangle frame for auxiliary positioning sign, also or other similar sign, the flow process of its method is all identical with present embodiment, so repeats no more.
All such variations all belong within the scope of the present invention, and should not be considered to depart from scope of the present invention.The present invention is limited by marrow of claims and scope only.
Claims (10)
1, but the method for pickup mobile terminal business card identification under a kind of undesirable condition comprises the steps:
Step 1, auxiliary positioning sign is set on the portable terminal of band camera head;
Character zone to be identified on step 2, the employing auxiliary positioning mark location business card;
Step 3, business card is taken pictures at least twice continuously, thereby obtain at least two width of cloth business card images;
Step 4, analyze described business card image, judge on every width of cloth business card image whether have character in the auxiliary positioning identification image;
If step 5 meets the piece image that has only of step 4 condition, then in the character zone to be identified of this image, carry out character recognition and handle, thereby obtain the result that final business card is discerned;
If meet two width of cloth images that have at least of step 4 condition, then carry out the character recognition processing in the character zone to be identified to qualified image respectively, and the character identification result of each width of cloth image is carried out validity judge, thereby obtain the result of final business card identification;
If do not meet the image of step 4 condition, then judge this time business card recognition failures.
But 2, the method for pickup mobile terminal business card identification under the undesirable according to claim 1 condition, it is characterized in that: in the described step 5 character identification result being carried out the method that validity judges is: the character identification result of each width of cloth image is carried out the comparison of individual character, add up the quantity of individual character inequality, thereby judge the validity of character identification result according to the individual character comparison result.
But 3, as the method for pickup mobile terminal business card identification under the undesirable condition as described in the claim 2, it is characterized in that: when all individual character identification homogeneous phase whiles, think that then the character identification result of each width of cloth image is identical, get the wherein result of the final business card identification of character identification result conduct of a sub-picture.
But 4, as the method for pickup mobile terminal business card identification under the undesirable condition as described in the claim 2, it is characterized in that: when individual character is compared, have individual character identification inequality, and when the quantitative proportion of individual character inequality is lower than a pre-set threshold, the degree of confidence of each character in the character identification result of each width of cloth image relatively respectively then, and get the result of that character of degree of confidence maximum as final character recognition.
But 5, as the method for pickup mobile terminal business card identification under the undesirable condition as described in the claim 4, it is characterized in that: described degree of confidence is that the sum of errors of getting distance is a degree of confidence.
But 6, as the method for pickup mobile terminal business card identification under the undesirable condition as described in the claim 2, it is characterized in that: when individual character is compared, have individual character identification inequality, and when the quantitative proportion of individual character inequality is higher than a pre-set threshold, then judge this time business card recognition failures.
7, but as the method for pickup mobile terminal business card identification under the undesirable condition as described in one of in the claim 1 to 6, it is characterized in that: described auxiliary positioning is designated horizontal line or rectangle frame.
But 8, as the method for pickup mobile terminal business card identification under the undesirable condition as described in the claim 7, it is characterized in that: described step 2 is, move described horizontal line, to pushing down character to be identified, thereby the character to be identified that the position level line pressure is lived is a character zone to be identified.
But 9, as the method for pickup mobile terminal business card identification under the undesirable condition as described in the claim 8, it is characterized in that: in the described step 4, with the horizontal line is benchmark, horizontal scanning image from left to right successively up or down, thus whether the image-region of searching the horizontal line place exists character.
But 10,, it is characterized in that: open the step that secondary light source carries out floor light before also being included in described step 2 as the method for pickup mobile terminal business card identification under the undesirable condition as described in one of in the claim 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2005100634402A CN100349172C (en) | 2005-04-08 | 2005-04-08 | Method for pickup mobile terminal to identify business card under the nonideal condition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2005100634402A CN100349172C (en) | 2005-04-08 | 2005-04-08 | Method for pickup mobile terminal to identify business card under the nonideal condition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN1655176A CN1655176A (en) | 2005-08-17 |
| CN100349172C true CN100349172C (en) | 2007-11-14 |
Family
ID=34894622
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB2005100634402A Expired - Fee Related CN100349172C (en) | 2005-04-08 | 2005-04-08 | Method for pickup mobile terminal to identify business card under the nonideal condition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN100349172C (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102446266A (en) * | 2010-09-30 | 2012-05-09 | 北京中远通科技有限公司 | Device, system and method for automatically identifying industrial number |
| CN102724397B (en) * | 2011-03-31 | 2014-11-19 | 汉王科技股份有限公司 | Name card automatic detection method and device thereof |
| CN103279743A (en) * | 2013-05-28 | 2013-09-04 | 深圳市中兴移动通信有限公司 | Business card recognition method and device |
| US8805125B1 (en) | 2013-06-28 | 2014-08-12 | Google Inc. | Comparing extracted card data using continuous scanning |
| CN106203425B (en) * | 2016-07-01 | 2020-02-04 | 北京旷视科技有限公司 | Character recognition method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5455872A (en) * | 1993-04-26 | 1995-10-03 | International Business Machines Corporation | System and method for enhanced character recogngition accuracy by adaptive probability weighting |
| JPH10258595A (en) * | 1997-03-19 | 1998-09-29 | Yasuyoshi Ochiai | Business card |
| CN1245935A (en) * | 1999-06-21 | 2000-03-01 | 李虹 | Full-automatic recognizing, logging-in and retrieval system of calling cards |
| CN1329323A (en) * | 2001-07-31 | 2002-01-02 | 郭根龙 | Automatic scanning identification and management method for credentials and its system |
| CN1339775A (en) * | 2000-08-22 | 2002-03-13 | 英业达集团(上海)电子技术有限公司 | Automatic identifying method and system for name card |
-
2005
- 2005-04-08 CN CNB2005100634402A patent/CN100349172C/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5455872A (en) * | 1993-04-26 | 1995-10-03 | International Business Machines Corporation | System and method for enhanced character recogngition accuracy by adaptive probability weighting |
| JPH10258595A (en) * | 1997-03-19 | 1998-09-29 | Yasuyoshi Ochiai | Business card |
| CN1245935A (en) * | 1999-06-21 | 2000-03-01 | 李虹 | Full-automatic recognizing, logging-in and retrieval system of calling cards |
| CN1339775A (en) * | 2000-08-22 | 2002-03-13 | 英业达集团(上海)电子技术有限公司 | Automatic identifying method and system for name card |
| CN1329323A (en) * | 2001-07-31 | 2002-01-02 | 郭根龙 | Automatic scanning identification and management method for credentials and its system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN1655176A (en) | 2005-08-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101667251B (en) | OCR recognition method and device with auxiliary positioning function | |
| US10157326B2 (en) | Method and device for character area identification | |
| US11961242B2 (en) | Target tracking method, computer device, and storage medium | |
| US20150254507A1 (en) | Image-Based Character Recognition | |
| CN100349172C (en) | Method for pickup mobile terminal to identify business card under the nonideal condition | |
| CN103916592A (en) | Apparatus and method for photographing portrait in portable terminal having camera | |
| US9418292B2 (en) | Methods, apparatuses, and computer program products for restricting overlay of an augmentation | |
| CN106295638A (en) | Certificate image sloped correcting method and device | |
| CN105550633A (en) | Area recognition method and device | |
| RU2012110212A (en) | METHOD AND SYSTEM FOR MEASURING SPEED OF A VEHICLE | |
| CN110460838B (en) | Lens switching detection method and device and computer equipment | |
| CN105808542B (en) | Information processing method and information processing apparatus | |
| CN101609505A (en) | The method and apparatus of identification character | |
| JP2017054285A (en) | Scan system, terminal device, and scan method | |
| US9113002B2 (en) | Method and system for automatically capturing an object using a mobile terminal | |
| CN109891427A (en) | Shape detection | |
| US20140085402A1 (en) | Conference terminal and method for processing videos from other conference terminals | |
| KR100683248B1 (en) | Method of sub-pixel motion calculation and Sensor for chasing a position using this method | |
| TWI671686B (en) | Image data retrieving method and image data retrieving device | |
| KR102057581B1 (en) | Apparatus and method for automatically focusing an object in device having a camera | |
| WO2019097690A1 (en) | Image processing device, control method, and control program | |
| CN110766671B (en) | Image processing method based on machine vision software | |
| CN111368726B (en) | Construction site operation face personnel number statistics method, system, storage medium and device | |
| KR20190001873A (en) | Apparatus for searching object and method thereof | |
| US20210182588A1 (en) | Object detection method for static scene and associated electronic device |
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 | ||
| C41 | Transfer of patent application or patent right or utility model | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20151116 Address after: 519031 Guangdong city of Zhuhai province Hengqin Baohua Road No. 6, room 105 -478 Patentee after: GUANGDONG ZHONGXING ELECTRONICS CO., LTD. Address before: 100083, Haidian District, Xueyuan Road, Beijing No. 35, Nanjing Ning building, 15 Floor Patentee before: Beijing Vimicro Corporation |
|
| DD01 | Delivery of document by public notice |
Addressee: GUANGDONG ZHONGXING ELECTRONICS CO., LTD. Document name: Notification of Passing Examination on Formalities |
|
| DD01 | Delivery of document by public notice | ||
| DD01 | Delivery of document by public notice |
Addressee: GUANGDONG ZHONGXING ELECTRONICS CO., LTD. Document name: Notification to Pay the Fees |
|
| DD01 | Delivery of document by public notice | ||
| DD01 | Delivery of document by public notice |
Addressee: GUANGDONG ZHONGXING ELECTRONICS CO., LTD. Document name: Notification of Termination of Patent Right |
|
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20071114 Termination date: 20170408 |