CN100370473C - Image pick-up method for image identification - Google Patents
Image pick-up method for image identification Download PDFInfo
- Publication number
- CN100370473C CN100370473C CNB021151598A CN02115159A CN100370473C CN 100370473 C CN100370473 C CN 100370473C CN B021151598 A CNB021151598 A CN B021151598A CN 02115159 A CN02115159 A CN 02115159A CN 100370473 C CN100370473 C CN 100370473C
- Authority
- CN
- China
- Prior art keywords
- portrait
- position scale
- display device
- computing machine
- identification
- 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 25
- 239000012780 transparent material Substances 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 4
- 238000012790 confirmation Methods 0.000 claims description 4
- 238000013461 design Methods 0.000 claims description 4
- 230000007547 defect Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 210000003128 head Anatomy 0.000 description 4
- 230000001815 facial effect Effects 0.000 description 3
- 229920003023 plastic Polymers 0.000 description 3
- 239000002985 plastic film Substances 0.000 description 3
- 239000000284 extract Substances 0.000 description 2
- 230000005764 inhibitory process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 210000000887 face Anatomy 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Landscapes
- Image Analysis (AREA)
Abstract
The present invention relates to an image pick-up method for human image identification. In the prior art, after a human image is input into a computer, a complicated human image positioning process is needed, so the prior art has the defects of high computation complexity, heavy burden on computer computation, etc. In the present invention, a positioning scale is preset on a display device for displaying human images which are picked up; then, human images which are picked up by an image pick-up device are displayed for people who are shot in real time by the display device, so that the shot people can determine own positions by the positioning scale and the own images on the display device, and human images meeting requirements of specifications are acquired by a computer, with the result that images which are picked up by the computer have the same characteristics; the images can be directly used for people identification or identity identification so that the amount of calculation is largely reduced, and the stability of identification is enhanced at the same time.
Description
Technical field
The present invention relates to a kind of portrait recognition technology, more particularly, relate to a kind of portrait acquisition method that is used for Identification of Images.
Background technology
Along with the development of technology, play a part to become more and more important in the systems such as the portrait identification is maintained secrecy in finance, security control, gate inhibition.Traditional password, key exist confidentiality poor, easily lose and shortcoming such as easily forget, if with portrait as password, should " password " be difficult to duplicate, not lose and do not forget.Thereby utilizing the facial characteristics of people's face to carry out authentication becomes a kind of reliably safety precaution means easily gradually.
In the patent No. is in the utility model patent of ZL 00245826.8, discloses a kind of " the financial deposit face is as recognizer " that financial sector is used that be suitable for.The view data that this recognizer utilizes single-chip microcomputer to handle to collect at first detects the existence and the position of human head picture, confirms whether be discernible tested surface picture then, extracts the portrait feature at last and exports by communication interface.This recognizer relies on detection and the location that single-chip microcomputer carries out portrait fully, and its calculated amount is big, risk is high, and any error in this stage will cause follow-up all identifications to calculate inefficacy.
In application number was 99117360.0 patent of invention, a kind of Identification of Images gate inhibition and attendance checking system were disclosed.The camera motion capture personnel head portrait of this system by linking to each other with computing machine, again with database in the portrait of typing in advance compare, make by whether or work attendance whether judgement.Its " whether on which position really have a face, these algorithms can accurately detect many faces simultaneously occurring, and can determine their accurate position if using polytype matching algorithm to judge automatically " is described in the open text of this patent.In actual use, the portrait of arbitrary dimension, optional position detects task algorithm has been proposed challenging requirement, also makes computation complexity and computing machine burden increase many simultaneously.
In application number was 01106183.9 patent of invention, a kind of entrance guard system with human image recognition was also disclosed.Its method is " to be obtained visitor's facial image by optical camera or ccd video camera.Converting analog image to digital picture by the video frequency collection card on the computing machine is stored on the computing machine.This person's face image is carried out the image pre-service, extract the feature of people's face, the utilization automatic identification algorithm is discerned, is compared with the figure information in the database.The result of identification is as the foundation of computing machine to the access controller issue an order ".There are not other descriptions in the open text of this application again, so still fail to solve the problem of above-mentioned " algorithm validity " and " computation complexity " to its portrait input media.
As seen, for the picked-up of portrait, all there are shortcomings such as computation complexity is higher, the computation burden of computing machine is heavier in acquisition method of the prior art, has caused obstacle for applying of portrait recognition technology.
Summary of the invention
The technical problem to be solved in the present invention is, at the above-mentioned deficiency of prior art, provides a kind of computation burden that reduces computation complexity, alleviates computing machine, convenient and practical portrait acquisition method, to improve the performance of portrait recognition technology.
Technical program of the present invention lies in, when portrait absorbs, provide a predetermined scale for person taken picture's reference, allow it can determine self-position voluntarily, that is to say, allow the position that can be adjusted self on one's own initiative by the cameraman obtain the portrait that compliant requires, method of the present invention specifically may further comprise the steps:
A, be used to show on the display device that is ingested portrait default Position Scale;
B, absorb portrait with apparatus for making a video recording;
C, the portrait that is absorbed is shown to the person of being taken in real time by described display device;
D, the person of being taken regulate himself position, make its portrait meet the requirement of the Position Scale on the described display device;
E, export satisfactory portrait.
In the method for the invention, described Position Scale can be placed on display device, and this moment is default according to the following steps Position Scale in described step a: get a transparent material paper onesize with the display window of described display device; Required Position Scale draws on described transparent material paper; Then described transparent material paper is bonded at the display screen surface of described display device.
In the method for the invention, described Position Scale can be built in display device, and this moment is default according to the following steps Position Scale in described step a: according to computer program of required Position Scale design; By computing machine according to described program to described display device output signal; Display device demonstrates required Position Scale on its display screen.
In the method for the invention, described Position Scale can and be located on the horizontal line of described positive cross wire and with the perpendicular line of described positive cross wire by a positive cross wire and be formed by the eye location mark of central shaft.Certainly can also be the Position Scale of other form.
In the step e of the inventive method, can whether meet the Position Scale requirement by the portrait of the described apparatus for making a video recording picked-up of artificial judgment, and send a confirmation signal by pushbutton switch, the portrait that will meet the Position Scale requirement outputs to computing machine; Also the signal of described apparatus for making a video recording can be input to computing machine simultaneously, judge by the computing machine Automatic Cycle whether the portrait that is absorbed meets the Position Scale requirement, and obtain satisfactory portrait.
Method of the present invention can be used for portrait identification provides standardization photo, its system to be provided with flexibly, can customize scale arbitrarily; The user is easy to operate, as daily " looking in the mirror "; The result accurately and reliably, exportable normalized portrait.Can be widely used in entrance guard system with human image recognition, identity identification system and self-service photographic equipment etc.
The invention will be further described below in conjunction with drawings and Examples.
Description of drawings
Fig. 1 is the process flow diagram that the present invention is used for the portrait acquisition method of Identification of Images;
Fig. 2 is to be the synoptic diagram of the Position Scale of scaling point with eyes in one embodiment of the present of invention;
Fig. 3 is the synoptic diagram when utilizing Position Scale among Fig. 2 to carry out the portrait picked-up;
Fig. 4 is the system schematic when adopting the external Position Scale among the present invention;
Fig. 5 is the system schematic when adopting built-in Position Scale among the present invention.
Embodiment
In traditional portrait, rely on photographer to locate with the view finder on the photographic goods, need photographer's full-time control machine and shooting process this moment, can not carry out robotization and handle.The invention provides a predetermined scale and determine self-position voluntarily for " by the cameraman ", that is to say, also is photographer by the cameraman simultaneously, and the position that can adjust self on one's own initiative obtains best picked-up effect.The flow process of the inventive method is as shown in Figure 1:
Step a, be used to show on the display device that is ingested portrait default Position Scale;
Step b, absorb portrait with apparatus for making a video recording;
Step c, the portrait that is absorbed is shown to the person of being taken in real time by described display device;
Steps d, the person of being taken regulate himself position, make its portrait meet the requirement of the Position Scale on the described display device;
Step e, export satisfactory portrait.
According to actual needs, Position Scale among the present invention can be put by people's facial characteristics and design, being illustrated in figure 2 as in one embodiment of the present of invention with eyes is the synoptic diagram of the Position Scale of scaling point, this Position Scale constitutes positive cross wire by horizontal line and perpendicular line, and also being provided with on its horizontal line with the perpendicular line is two circles with little cross of symmetry.Wherein perpendicular line is used for determining normal bridge of the nose axis, and horizontal line is used for determining two horizontal level, and two circles are used for determining the accurate position of eyes, just eye location mark.Certainly, Position Scale among the present invention can also be other form, for example can not adopt eye location, but sets up two perpendicular line in the horizontal left and right sides, except that bridge of the nose line, eye level line, confine the left and right sides of people's face again with the perpendicular line of both sides.
After being preset in above-mentioned Position Scale on the display device, absorb portrait with apparatus for making a video recording again, and be presented at the portrait that is absorbed on the display device in real time, can on display device, be seen Position Scale and the portrait of oneself simultaneously by the cameraman, thereby can exactly the portrait of oneself be pressed scale and aim at, make it to meet the code requirement of Position Scale.Be illustrated in figure 3 as the Position Scale that utilizes among Fig. 2 and carry out the portrait synoptic diagram in when picked-up, this moment the people bridge of the nose aligned perpendicular line, aim at two circles for two, can obtain the portrait that compliant requires.
Position Scale among the present invention can be an external, also can be built-in, be illustrated in figure 4 as the system schematic when adopting the external Position Scale, this system is made up of video camera 2, display device 3, external Position Scale 4 and computing machine 5, wherein video camera 2 is connected to computing machine 5 and display device 3 simultaneously, to both output signals, be superimposed with a Position Scale 4 on the surface of display device 3 simultaneously.This Position Scale 4 is made by transparent plastic sheet, has drawn Position Scale as shown in Figure 2 with the oil pen above, and this Position Scale is fixed on the surface of display device 3.During use, the person of being taken 7 stands in before the video camera 2 and in the face of display device 3, just can be clear that the portrait of oneself from display device, is similar to and sees mirror.The person of being taken can adjust self-position, make its head portrait in display device 3 meet the requirement of Position Scale 4, when the person of being taken or operating personnel judge that the portrait that is absorbed meets Position Scale and requires, can send a confirmation signal by pushbutton switch or alternate manner, allow computing machine 5 obtain the portrait of this moment.Finally the portrait that will meet the Position Scale requirement by computing machine 5 is kept in the storer, files or output to miscellaneous equipment by printer prints, handles for use in follow-up identification.In the present embodiment, can also draw Position Scale without transparent plastic sheet, but Position Scale directly is plotted in the display screen surface of monitor 3, its effect is directly perceived more and simple.
System schematic as built-in Position Scale among Fig. 5 the present invention, this system is made up of video camera 2, computing machine 5 and display device 3, the Position Scale of not making in the native system 4 by transparent plastic sheet, and the signal of video camera 2 does not directly output to display device 3, but be input to computing machine 5 earlier, output to display device 3 by computing machine 5 again.Computer program according to required Position Scale design is housed in computing machine, and computing machine 5 these programs of operation to display device 3 output signals, demonstrate required Position Scale 6 on the display screen of display device.This Position Scale is presented on the display screen all the time, portrait by video camera 2 picked-ups is also shown on the display device 3 behind the machine 5 as calculated, wherein Position Scale forcibly is presented at the portrait front, a fixing Position Scale just superposes on movable portrait, Position Scale wherein is similar to the TV station's station symbol that is superimposed upon the television image surface, and its specific implementation can be controlled generation by computer software.During work, video camera 2 is caught the people's that taken pictures image continuously and it is imported computing machine 5; Each two field picture that computing machine 5 utilizes its inner central processing unit to import is presented on the display device 3; Computing machine 5 utilizes its inner central processing unit to draw Position Scale 6 at above-mentioned same position then.Based on above-mentioned plot order, its effect is equal to the Position Scale 6 of all drawing a stationkeeping on every two field picture of catching, as shown in Figure 3.When continuously the video image of importing being carried out aforesaid operations, its display effect is equal to fixing Position Scale of stack on activity video.This built-in Position Scale is identical with the function of external Position Scale, but built-in scale is more accurate, dirigibility is strong, can avoid physical hazard.During use, the person of being taken 7 stands in before the video camera 2 and in the face of display device 3, just can be clear that the portrait of oneself from display device, is similar to and sees mirror.The person of being taken can adjust self-position, makes its head portrait in display device 3 meet the requirement of Position Scale 6, sends a confirmation signal by pushbutton switch or alternate manner then, allows computing machine 5 obtain the portrait of this moment.Finally the portrait that will meet the Position Scale requirement by computing machine 5 is kept in the storer, files or output to miscellaneous equipment by printer prints, handles for use in follow-up identification.
In the above-described embodiments, the portrait that computing machine obtains has a common characteristic, and promptly the eyes in everyone picture drop on two circled positions places as shown in Figure 3 all at same position.This portrait can be directly used in personage's identification or identity and differentiate, needn't carry out in the prior art that portrait to " arbitrary dimension, optional position " detects and calculating such as location, thereby significantly reduce calculated amount, improves identification stability and degree of accuracy simultaneously.
Claims (6)
1. a portrait acquisition method that is used for Identification of Images is characterized in that, may further comprise the steps:
A, be used to show on the display device that is ingested portrait default Position Scale;
B, absorb portrait with apparatus for making a video recording;
C, the portrait that is absorbed is shown to the person of being taken in real time by described display device;
D, the person of being taken regulate himself position, make its portrait meet the requirement of the Position Scale on the described display device;
E, export satisfactory portrait.
2. method according to claim 1 is characterized in that, in described step a, and default according to the following steps Position Scale: get a transparent material paper onesize with the display window of described display device; Required Position Scale draws on described transparent material paper; Then described transparent material paper is bonded at the display screen surface of described display device.
3. method according to claim 1 is characterized in that, in described step a, and default according to the following steps Position Scale: according to computer program of required Position Scale design; By computing machine according to described program to described display device output signal; Display device demonstrates required Position Scale on its display screen.
4. according to each described method among the claim 1-3, it is characterized in that described Position Scale is by a positive cross wire and be located on the horizontal line of described positive cross wire and with the perpendicular line of described positive cross wire and formed by the eye location mark of central shaft.
5. method according to claim 1, it is characterized in that in described step e, can whether meet the Position Scale requirement by the portrait of the described apparatus for making a video recording picked-up of artificial judgment, and sending a confirmation signal by pushbutton switch, the portrait that will meet the Position Scale requirement outputs to computing machine.
6. method according to claim 1, it is characterized in that the signal of described apparatus for making a video recording is input to computing machine simultaneously, in described step e, judge by the computing machine Automatic Cycle whether the portrait that is absorbed meets the Position Scale requirement, and obtain satisfactory portrait.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB021151598A CN100370473C (en) | 2002-04-26 | 2002-04-26 | Image pick-up method for image identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB021151598A CN100370473C (en) | 2002-04-26 | 2002-04-26 | Image pick-up method for image identification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN1453737A CN1453737A (en) | 2003-11-05 |
| CN100370473C true CN100370473C (en) | 2008-02-20 |
Family
ID=29256939
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB021151598A Expired - Fee Related CN100370473C (en) | 2002-04-26 | 2002-04-26 | Image pick-up method for image identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN100370473C (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4624933B2 (en) * | 2005-03-16 | 2011-02-02 | 富士フイルム株式会社 | IMAGING DEVICE, IMAGING METHOD, ALBUM CREATION DEVICE, ALBUM CREATION METHOD, ALBUM CREATION SYSTEM, AND PROGRAM |
| JP6651911B2 (en) * | 2016-03-07 | 2020-02-19 | オムロン株式会社 | Face image processing device |
| CN106407953A (en) * | 2016-10-14 | 2017-02-15 | 蔡璟 | Intelligent people searching system based on multi-image big data identification |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN86204729U (en) * | 1986-10-22 | 1987-09-30 | 谷伯耀 | Self photography equipment capable of seeing own appearance |
| US5978495A (en) * | 1996-07-17 | 1999-11-02 | Intelnet Inc. | Method and apparatus for accurate determination of the identity of human beings |
| JP2000293663A (en) * | 1999-04-01 | 2000-10-20 | Oki Electric Ind Co Ltd | Individual identifying device |
| CN1276710A (en) * | 1997-10-24 | 2000-12-13 | 英国电讯有限公司 | Imaging apparatus |
| CN1317714A (en) * | 2001-01-16 | 2001-10-17 | 彭康 | Multiaspect photography method and equipment |
-
2002
- 2002-04-26 CN CNB021151598A patent/CN100370473C/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN86204729U (en) * | 1986-10-22 | 1987-09-30 | 谷伯耀 | Self photography equipment capable of seeing own appearance |
| US5978495A (en) * | 1996-07-17 | 1999-11-02 | Intelnet Inc. | Method and apparatus for accurate determination of the identity of human beings |
| CN1276710A (en) * | 1997-10-24 | 2000-12-13 | 英国电讯有限公司 | Imaging apparatus |
| JP2000293663A (en) * | 1999-04-01 | 2000-10-20 | Oki Electric Ind Co Ltd | Individual identifying device |
| CN1317714A (en) * | 2001-01-16 | 2001-10-17 | 彭康 | Multiaspect photography method and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN1453737A (en) | 2003-11-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Garcia-Salicetti et al. | BIOMET: A multimodal person authentication database including face, voice, fingerprint, hand and signature modalities | |
| US8649575B2 (en) | Method and apparatus of a gesture based biometric system | |
| CN110491004A (en) | A kind of residential communities personnel security management system and method | |
| WO2016112630A1 (en) | Image recognition system and method | |
| JP2002251380A (en) | User collation system | |
| CN104143086A (en) | Application technology of portrait comparison to mobile terminal operating system | |
| CN106982426A (en) | A method and system for remotely realizing the real-name registration of old cards | |
| CN101556717A (en) | ATM intelligent security system and monitoring method | |
| CN104167025A (en) | Mobile attendance system based on dynamic face recognition and WIFI positioning and method of attendance system | |
| US10915739B2 (en) | Face recognition device, face recognition method, and computer readable storage medium | |
| CN204791017U (en) | Mobile terminal users authentication device based on many biological characteristics mode | |
| CN108090469A (en) | A kind of video and image face identification system | |
| CN107730195A (en) | The method and device of relieving in parking lot | |
| CN108446687B (en) | Self-adaptive face vision authentication method based on interconnection of mobile terminal and background | |
| CN103996033B (en) | Human identification method based on tracking of human face five-sense-organ coordinates | |
| JP2001256496A (en) | Device and method for recognizing face picture | |
| CN108229124A (en) | A kind of self-service query printing testimony of a witness compares device systems and its method of work | |
| WO2022222957A1 (en) | Method and system for identifying target | |
| CN100370473C (en) | Image pick-up method for image identification | |
| CN108197599A (en) | A kind of face identification system | |
| CN107292278A (en) | A kind of face identification device and its recognition methods based on Adaboost algorithm | |
| CN106407897A (en) | Automatic social security card photograph determination inputting method | |
| KR102227908B1 (en) | Method for the guidance of elderly persons in smart automated teller machine using facial recognition | |
| CN210721506U (en) | Dynamic face recognition terminal based on 3D camera | |
| CN210052203U (en) | Attendance check-in system based on multiple identification methods |
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: 20080220 Termination date: 20130426 |