CN102111535B - Method for improving human face identification rate - Google Patents
Method for improving human face identification rate Download PDFInfo
- Publication number
- CN102111535B CN102111535B CN2009102620402A CN200910262040A CN102111535B CN 102111535 B CN102111535 B CN 102111535B CN 2009102620402 A CN2009102620402 A CN 2009102620402A CN 200910262040 A CN200910262040 A CN 200910262040A CN 102111535 B CN102111535 B CN 102111535B
- Authority
- CN
- China
- Prior art keywords
- face
- people
- information
- human face
- 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
Images
Landscapes
- Image Processing (AREA)
- Studio Devices (AREA)
Abstract
The invention provides a method for improving the human face identification rate. The method is suitable for a digital camera with a memory unit. Human face information is stored in the memory unit, and includes human face characteristics. The method for improving the human face identification rate comprises the following steps: retrieving a first human face image of a target human; executing a human face identification program to determine whether the first human face image is corresponding to human face information in the memory unit or not through the human face identification program; and executing an updating program when the first human face image is corresponding to the human face information so as to increase the human face characteristics corresponding to the target human in the memory unit.
Description
Technical field
The present invention relates to a kind of method that improves the human face recognition rate, particularly a kind of method that improves the human face recognition rate, it is applicable to the digital camera with storage element.
Background technology
In daily life now, the digital product of various replacement traditional analog technology is very universal, and digital camera is a good example.After digital camera utilizes the optical sensor pick-up image and converts digital signal into, store with the form of electronic chart file.By the various acquisition parameters of adjustment, the user can indiscriminately ad. as one wishes take the digitized video of oneself wanting.Most now digital cameras itself also offer the many functions easily of user, for example focus automatically (Auto Focusing), various scene mode or human face recognition (Facial Recognition).By the function that digital camera provides, the user can take satisfied photo more like a cork.
Wherein the technology of human face recognition is quite general in recent years, but still has the place of many deficiencies.Human face recognition is meant that the visual signature information of utilizing analysis to compare people's face to carry out the technology of status differentiation, is considered to one of the most difficult research topic of living things feature recognition field even artificial intelligence field.In fact the profile of people's face is very unstable, because the people can produce a lot of expressions through the variation of facial muscle.And in different viewing angles, the appearance that seems of people's face also differs greatly.In addition, recognition of face also receives the influence of many-sided factors such as on the face overcover (for example mouth mask, sunglasses, hair, beard etc.) of illumination condition (for example day and night, indoor and outdoors etc.), people, age.
The human face recognition of digital camera use at present is mostly only by the front pick-up image of people's face, and is not enough for the same people's face accuracy with different expressions, moulding, illumination condition, pick-up angle or acquisition distance.Therefore when the personage as the acquisition object changes expression, changes moulding, during mobile or rotary head, traditional human face recognition method also can't correctly be carried out identification.
Summary of the invention
In order to solve the not enough problem of above-mentioned discrimination power, the present invention provides a kind of method that improves the human face recognition rate.
The method of raising human face recognition rate provided by the invention can improve the human face recognition rate under the situation that does not bother the user.
The method of raising human face recognition rate provided by the invention is to be applicable to the digital camera with a storage element.
The storage unit stores of this digital camera has at least one people's face information, and each individual face information comprises at least one face characteristic.
The method that improves the human face recognition rate comprises: a target personage is captured a first face image; Carry out a human face recognition program according to storage element, to judge that through the human face recognition program whether the first face image that captures is corresponding to one of people's face information; And when the first face image is one of in corresponding to people's face information, to people's face information and executing one refresh routine, with increase according to the target personage be stored in the storage element corresponding to people's face information in target personage's face characteristic.
Wherein, refresh routine can comprise: when the first face image during corresponding to one of people's face information, with face tracking means the target personage is followed the trail of at least one second people's face image of acquisition; Analyze second people's face image to obtain at least one new face characteristic; And new face characteristic is stored to storage element with the face characteristic as the pairing people's face of the first face image information.
Implement example according to of the present invention one; The method that improves the human face recognition rate can more comprise: when the first face image during corresponding to one of people's face information; By a subject matter information that captures in the storage element in people's face information of correspondence, and corresponding target personage's image shows subject matter information.
And when the first face image does not have corresponding to people's face information arbitrary, can carry out a newly-increased program, newly-increased program comprises: obtain at least one newly-increased face characteristic according to the first face image; And will increase face characteristic newly and be stored to storage element as new people's face information.In this, sustainable tracking target personage and repeat refresh routine obtaining more face characteristic, and then improves the human face recognition rate more.
In addition, above-mentioned human face recognition program can comprise: according to the first face image and everyone face information calculations one human face similarity degree; And judged whether that arbitrary human face similarity degree is greater than one first threshold value.
According to enforcement example of the present invention; Be to use different acquisition parameters when capturing the first face image, and acquisition parameters is to be the condition during at least one pick-up image in an exposure value, acquisition focal length, a resolution or a pick-up angle or the acquisition distance with second people's face image.Face characteristic then can be the various characteristics that a facial contour, a face complexion or people's face face position etc. can be used for identification people face.
In sum; Effect of the present invention is; According to the method for raising human face recognition rate of the present invention by the face tracking means to the new face characteristic of target personage automatic pick-up; Upgrade corresponding people's face information in the storage element of digital camera with the face characteristic that obtains again, to use as follow-up human face recognition program.The face characteristic that the target personage captures can be obtained owing to improve the method for human face recognition rate under difference acquisition environment or different pick-up angle, therefore target personage's human face recognition rate can be improved effectively.And refresh routine is under the situation that the user does not discover, to carry out.
Describe the present invention below in conjunction with accompanying drawing and specific embodiment, but not as to qualification of the present invention.
Description of drawings
Fig. 1 is the configuration diagram of the digital camera that is suitable for according to the present invention;
Fig. 2 A is the schematic flow sheet of the method for the raising human face recognition rate of one enforcement example according to the present invention;
Fig. 2 B is the schematic flow sheet of the method for another raising human face recognition rate of implementing example according to the present invention;
Fig. 3 is the schematic flow sheet of the human face recognition program of one enforcement example according to the present invention;
Fig. 4 is the schematic flow sheet of the refresh routine of one enforcement example according to the present invention;
Fig. 5 is another schematic flow sheet of implementing the refresh routine of example according to the present invention; And
Fig. 6 is the schematic flow sheet of the newly-increased program of one enforcement example according to the present invention.
Wherein, Reference numeral
100 digital cameras
102 lens assemblies
106 photosensory assemblies
108 sample circuits (sample hold circuit)
112 storage elements
114 CD-ROM drive motors
116 processing units
120,120a, 120b people's face information
122 face characteristics
Embodiment
Below in execution mode, be described in detail detailed features of the present invention and advantage; Its content is enough to make any those skilled in the art to understand technology contents of the present invention and implements according to this; And according to content, the claim scope and graphic that this specification disclosed, those skilled in the art can understand purpose and the advantage that the present invention is correlated with easily.
The method that improves the human face recognition rate according to an embodiment of the invention is applicable to the digital camera with a storage element.
Fig. 1 is the configuration diagram for the digital camera that is suitable for according to the present invention.About the digital camera that the present invention was suitable for to be but to be not limited to framework shown in Figure 1.
Please refer to Fig. 1, digital camera 100 can comprise a lens assembly 102, a photosensory assembly 106, a sample circuit 108 (Sampling hold circuit), storage element 112, a CD-ROM drive motor 114 and a processing unit 116.The light that scene reflected in lens assembly 102 the place aheads of digital camera 100 gets into photosensory assembly 106 via a lens assembly 102 and an iris apparatus (not illustrating); And after photosensory assembly 106 converted the light that gets into the signal of image to and pass to sample circuit 108, image can be recorded in storage element 112.
During acquisition, processing unit 116 activated drive motors 114, capture with an acquisition shutter value and an acquisition f-number to specifying focal position with moving lens device 102 then.Photosensory assembly 106 becomes the signal of telecommunication of digitized video corresponding to lens assembly 102 and the picture conversion with the place ahead scene.Via the driving of processing unit 116, sample circuit 108 is sent to storage element 112 with the image that photosensory assembly 106 is received.
Next, introduce the method for the raising human face recognition rate of one enforcement example according to the present invention by the digital camera 100 of above-mentioned structure.
Please with reference to Fig. 2 A, it is the schematic flow sheet for the method for the raising human face recognition rate of one enforcement example according to the present invention.
In this, the storage element 112 of digital camera 100 comprises at least one people's face information 120, and each one face information 120 comprises at least one face characteristic 122.Say in more detail, can comprise a property data base in the storage element 112, as the foundation of human face recognition.People's face information 120 is in the property data base that is stored in storage element 112, and everyone face information 120 corresponds to a target personage.
Each target personage can have its different face characteristic 122.For example face characteristic 122 can be a facial contour, a face complexion or people's face face position, and face characteristic 122 also can be eye shape, nose shape, freckle has or not or the detail characteristic of face such as iris color, but the present invention is not limited to this.For instance; Have the face characteristic 122 of content corresponding to the target personage of people's face information 120a, then have the face characteristic 122 of content for " iris color: blueness " corresponding to the target personage of people's face information 120b for " facial contour: long ellipse " and " face complexion: brown ".Thus, the human face recognition program of digital camera 100 can be through the face characteristic 122 in the face characteristic in the contrast image 122 and the property data base, with distinguish with image in the corresponding people's face of target personage information 120.
Better is also can comprise a subject matter information (not illustrating) in people's face information 120, in order to describe and corresponding target personage.Subject matter information can be target personage's name, the pet name or group's classification.For example, the content of subject matter information can be " Wang Xiaoming ", " Xiao Ming ", " classmate " or " minister ".Wherein subject matter information can be by user's input, can also be to insert for example " golden hair " or " 20091010-1 " by digital camera 100 automatically according to information such as face characteristic 122 or photo opporunities.
In this embodiment, digital camera 100 captures the first face image (step S30) at least one target personage.The first face image is the image for the face with people, is clapped the photographed person that the first face image is taken the photograph and the target personage is face.In other words, digital camera 100 has target personage's scene through lens assembly 102 acquisition the place aheads, to obtain the first face image corresponding to the target personage.
Capture after the first face image, 100 pairs of the first face image executor face identification programs of digital camera are to judge that through the human face recognition program whether the first face image that captures is corresponding to one of the people's face information 120 in the storage element 112 (step S40).According to the property data base in the storage element 112, digital camera 100 judges that the target personage that in the first face image, captured is whether corresponding to anyone the face information 120 in the property data base.In other words, find out the people's face information 120 that belongs to the target personage in the property data base through the human face recognition program.
When the first face image is one of in corresponding to people's face information 120, people's face information 120 is carried out refresh routines (step S50).Wherein, when in property data base, finding the people's face information 120 that belongs to the target personage, can carry out the wherein renewal of face characteristic 122, to add more face characteristics 122 corresponding to the target personage to this person's face information 120.
Moreover when the first face image did not have corresponding to people's face information 120 arbitrary, digital camera 100 can be carried out a newly-increased program (step S60), shown in Fig. 2 B.In other words, when not having the people's face information 120 that belongs to the target personage in the property data base, then can carry out newly-increased program, in property data base, to set up the people's face information 120 that belongs to this target personage.
Please with reference to Fig. 3, the employed human face recognition program of step S40 then can comprise the following steps.
At first, digital camera 100 calculates a human face similarity degree (step S42) according to the first face image and each people's face information 120 in the human face recognition program.Digital camera 100 is the characteristics that extracted target personage's face by the first face image, calculates human face similarity degree according to the characteristic of the first face image and everyone the face data 120 in the property data base again.Say in more detail, in the human face recognition program, the characteristic of the first face image of digital camera 100 contrast and the face characteristic 122 in people's face data 120, and the inverse of the difference that for example obtains with contrast is as human face similarity degree.In addition, can give different weights for different types of face characteristic 122, and the weighted calculation human face similarity degree.For example whether hair color or iris color be identical in order to identification people face easily, can give higher weighted value.Therefore corresponding everyone face data 120 all can calculate a human face similarity degree.
Digital camera 100 is then compared everyone face similarity degree (step S44) with first threshold value in the human face recognition program, to have judged whether that arbitrary human face similarity degree is greater than first threshold value.For example; Be characterized as " facial contour: long ellipse " and " iris color: black " by what the first face image was extracted out; And people's face information 120a comprises the face characteristic 122 of " facial contour: long ellipse " and " face complexion: brown ", and people's face information 120b comprises the face characteristic 122 of " iris color: blueness ".When the human face similarity degree that calculates corresponding to people's face information 120a is higher than first threshold value, and when being lower than first threshold value corresponding to the human face similarity degree of people's face information 120b, the first face image that digital camera 100 is judged acquisition is corresponding to people's face information 120a.
In step S40 confirm the target personage of the first face image be corresponding to one of people's face information 120 after, improve the method for human face recognition rate and carry out refresh routine in step S50.And, then carry out newly-increased program, or finish to carry out the method that improves the human face recognition rate in step S60 if confirm that in step S40 the target personage of the first face image does not have corresponding to arbitrary people's face information 120.
Please with reference to Fig. 4, the performed refresh routine of step S50 can comprise the steps.
100 couples of target personages of digital camera capture after the first face image, and target personage or digital camera 100 may move.But when the target personage also is in can be by the scope of digital camera 100 pick-up images the time; Digital camera 100 can be followed the trail of at least one second people's face image (step S52) face tracking means of acquisition with face tracking means to the target personage in refresh routine can adopt technology such as motion detection (motion detection) and estimation (motion estimation), with target personage's in the locking picture scope position.100 couples of target personages of digital camera capture at least one second people's face image, to obtain the more information relevant with target person.
Digital camera 100 and in refresh routine, analyzing capture second people's face image to obtain at least one new face characteristic (step S54).New face characteristic is also corresponding to people's face information 120 of corresponding target personage in the property data base.
Second people's face image in step S52 acquisition can have different acquisition parameters with the first face image, that is to say, is to use different acquisition parameters when capturing the first face image with second people's face image.Wherein parameter is to be at least one in an exposure value, an acquisition focal length, a resolution, a pick-up angle or the acquisition distance.During the personage that following the trail of the objective any, equal fechtable second people's face images.Therefore digital camera 100 possibly use and the different exposure value that captures the first face image, acquisition focal length or resolution when acquisition second people's face image.Digital camera 100 can also be different pick-up angle the target personage is captured second people's face image, and capture the side face of target personage's different angles.Therefore can extract the different new face characteristic that stores with property data base by second people's face image.
People's face of target personage has very big difference under difference expression, different pick-up angle or different illumination condition (for example fine day, night or cloudy day); But second people's face image that digital camera 100 can capture under above-mentioned various situation in refresh routine; And analyze the various new face characteristic that second people's face image obtains the target personage, to improve the human face recognition rate.Then will analyze the resulting new face characteristic of second people's face image and be stored to storage element 112, just with the new people's face information 120 of promoting of new face characteristic corresponding to the target personage with face characteristic 122 (step S56) as the pairing people's face of the first face image information 120.Various face characteristic 122 by collecting the target personage can obtain higher human face recognition rate.Thus, except people's face information 120 original face characteristics 122 of correspondence, the face characteristic 122 that new face characteristic conduct also can be arranged is in order to executor's face identification program.
Better is, when new face characteristic is upgraded into people's face information 120, also can note down the environmental condition (for example exposure value or white balance) of second people's face image when capturing simultaneously.Thus, in the time of need carrying out human face recognition, can select suitable face characteristic 122 according to environmental condition at that time and carry out human face recognition, can improve the human face recognition rate further.For instance, at night during executor's face identification program, suitable face characteristic 122 is the resulting face characteristics 122 of second people's face image of serving as reasons and under the lower situation of night or exposure, being captured.
Moreover, can repeat refresh routine, to obtain more face characteristic 122.Please with reference to Fig. 5, in refresh routine, after execution of step 56, can continue to judge to have or not the image (step S58) that tracks the target personage.When tracking the target personage, digital camera 100 can continue acquisition second people's face image (step S52), and analyzes second people's face image (step S54), in people's face information 120 of correspondence, to increase face characteristic 122 (step S56).
As long as the face tracking means at digital camera 100 track under target personage's the situation in addition, improve the method for human face recognition rate and all can automatically follow the trail of people's face information 120 that target personage, acquisition second people's face image and newly-increased new face characteristic advance correspondence.That is to say that under the unwitting situation of user, the method for raising human face recognition rate also can be whenever and wherever possible and continuously obtained corresponding face characteristic 122, and in order to improve the human face recognition rate.
In addition, when definite the first face image during corresponding to one of people's face information 120, the method that improves the human face recognition rate shows the subject matter information in the pairing people's face of the first face image information 120.Say that in more detail above-mentioned steps S30 all carries out to step S56 when digital camera 100 still is in the S0 state, and subject matter information can be provided for the user at the S0 state.
Wherein S0 is digital camera 100 start back present preview modes (Preview).The digital camera 100 of general two-part shutter can be divided into S0, S1 and three kinds of states of S2 (pattern) in use.S0 is a preview mode, on the display screen of digital camera 100, shows the picture of low resolution usually.The user can be at the make decision composition of desiring filmed image or carry out function such as adjustment acquisition parameters of preview mode.S1 is the state (Half Shutter) of pressing for shutter key quilt half.Get into digital camera 100 in this state and focus automatically that (Auto-Focus AF), and prepares to get into the S2 state at any time.S2 be for shutter key by the state of total head (Full Shutter).When the user presses shutter key fully, digital camera 100 can be carried out last preparations such as fine setting focal lengths, and formal filmed image.
And digital camera 100 can be shown in the subject matter information of the target personage's who picks out in step S40 correspondence on the display screen, for the user with reference to or confirm the result of human face recognition.And no matter digital camera 100 is the states that are in S0, S1 or S2, and the method that improves the human face recognition rate all can be performed.
Please with reference to Fig. 6, newly-increased program can comprise the following steps.At first, obtain at least one newly-increased face characteristic (step S62) according to the first face image, and will be stored to storage element 112 according to the newly-increased face characteristic that the first face image obtains as new people's face information 120 (step S64).That is to say, in newly-increased program, will analyze the resulting face characteristic 122 of the first face image and newly promote storage element 112 as newly-increased people's face information.Be digital camera 100 in newly-increased program, in property data base, increase the data of people's face information 120 newly for the target personage.Digital camera 100 can be jumped out acknowledgement window in display screen before newly-increased, confirm whether will increase newly this target personage's data for the user.If the user confirms and will also can be imported the subject matter information of new people's face information 120 by the user with this target personage as new people's face information 120 new property data bases of promoting.The subject matter information of new people's face information 120 also as above-mentionedly insert automatically according to information such as newly-increased face characteristic or photo opporunities by digital camera 100, and the subject matter information of inserting automatically is follow-up can let user's change again voluntarily.
In addition, newly-increased program not necessarily needs when the first face image of acquisition, to be performed.If the first face image is stored in storage element 112, the user can just select whether will the target personage newly be promoted property data base when watching image follow-up.And if when having a plurality of target personage in the first face image or the second people's face image; The method that improves the human face recognition rate can be respectively to these targets personage executor face identification program, refresh routine and newly-increased program, to improve these targets personage's human face recognition rate.
In sum; According to the refresh routine of the method for raising human face recognition rate of the present invention be can be under the situation that the user does not discover by the face tracking means to the new face characteristic of target personage automatic pick-up; Upgrade corresponding people's face information in the storage element of digital camera with the face characteristic that obtains again, to use as follow-up human face recognition program.Because the method for raising human face recognition rate can be whenever and wherever possible and is continuously obtained the face characteristic of target personage under various acquisition environment, therefore can improve target personage's human face recognition rate effectively.And the action that captures second people's face image and upgrade people's face information of corresponding target personage is under the unwitting situation of user, to carry out.
Certainly; The present invention also can have other various embodiments; Under the situation that does not deviate from spirit of the present invention and essence thereof; Those of ordinary skill in the art work as can make various corresponding changes and distortion according to the present invention, but these corresponding changes and distortion all should belong to the protection range of the appended claim of the present invention.
Claims (8)
1. a method that improves the human face recognition rate is applicable to a digital camera, and wherein this digital camera has a storage element; This storage unit stores has at least one people's face information; And this people's face information comprises at least one face characteristic, it is characterized in that, the method for this raising human face recognition rate comprises:
One target personage is captured a first face image;
This first face image is carried out a human face recognition step, with this first face image of judging acquisition through this human face recognition step whether corresponding to one of in this people's face information in this storage element; And
When this first face image was one of in corresponding to this people's face information, to this people's face information and executing one step of updating, to increase this face characteristic that is stored in this corresponding in this storage element people's face information according to this target personage, wherein this step of updating comprised:
With face tracking means this target personage is followed the trail of at least one second people's face image of acquisition;
Analyze this second people face image to obtain at least one new face characteristic; And
This new face characteristic is stored to this storage element with the face characteristic as pairing this people's face information of this first face image.
2. the method for raising human face recognition rate according to claim 1 is characterized in that, also comprises:
When this first face image during,, and image that should the target personage shown this subject matter information by a subject matter information that captures in this storage element in this people's face information of correspondence corresponding to one of this people's face information.
3. the method for raising human face recognition rate according to claim 1 is characterized in that, this human face recognition step comprises:
According to this first face image and each this people's face information calculations one human face similarity degree; And
Judged whether that arbitrary this human face similarity degree is greater than one first threshold value.
4. the method for raising human face recognition rate according to claim 1 is characterized in that, also comprises:
When this first face image does not have corresponding to one of in this people's face information the time, carry out a newly-increased step, this newly-increased step comprises:
Obtain at least one newly-increased face characteristic according to this first face image; And
This newly-increased face characteristic is stored to this storage element with as this new people's face information.
5. the method for raising human face recognition rate according to claim 1 is characterized in that, also comprises: repeat this step of updating.
6. the method for raising human face recognition rate according to claim 1 is characterized in that, captures this first face image and is to use different acquisition parameters with this second people face image.
7. the method for raising human face recognition rate according to claim 6 is characterized in that, this acquisition parameters is to be in an exposure value, an acquisition focal length, a resolution, a pick-up angle or the acquisition distance at least one.
8. the method for raising human face recognition rate according to claim 1 is characterized in that, this face characteristic is to be a facial contour, a face complexion or people's face face position.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009102620402A CN102111535B (en) | 2009-12-23 | 2009-12-23 | Method for improving human face identification rate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009102620402A CN102111535B (en) | 2009-12-23 | 2009-12-23 | Method for improving human face identification rate |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102111535A CN102111535A (en) | 2011-06-29 |
| CN102111535B true CN102111535B (en) | 2012-11-21 |
Family
ID=44175547
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2009102620402A Expired - Fee Related CN102111535B (en) | 2009-12-23 | 2009-12-23 | Method for improving human face identification rate |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102111535B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI508001B (en) * | 2013-10-30 | 2015-11-11 | Wistron Corp | Method, apparatus and computer program product for passerby detection |
| CN106295482B (en) * | 2015-06-11 | 2019-10-29 | 中移信息技术有限公司 | A kind of update method and device of face database |
| CN106295672B (en) * | 2015-06-12 | 2019-10-29 | 中移信息技术有限公司 | A kind of face identification method and device |
| CN105374098A (en) * | 2015-12-14 | 2016-03-02 | 天津光电通信技术有限公司 | Method used for unlocking using human body double-characteristic identification module |
| CN109993028A (en) * | 2017-12-29 | 2019-07-09 | 技嘉科技股份有限公司 | Human face recognition device and method, the method for promoting image identification rate |
| CN111325059A (en) * | 2018-12-14 | 2020-06-23 | 技嘉科技股份有限公司 | Face recognition method, device and computer readable medium |
| US11403884B2 (en) * | 2019-01-16 | 2022-08-02 | Shenzhen GOODIX Technology Co., Ltd. | Anti-spoofing face ID sensing |
| CN109858447B (en) * | 2019-01-31 | 2021-03-23 | 维沃移动通信有限公司 | Information processing method and terminal |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1494037A (en) * | 2002-11-01 | 2004-05-05 | ��ʽ���綫֥ | Apparatus and method for identifying personnel and passage controller |
| CN1734468A (en) * | 2005-06-17 | 2006-02-15 | 中华电信股份有限公司 | System for detecting dynamic human face in complicated environment |
| CN1885911A (en) * | 2005-06-22 | 2006-12-27 | 欧姆龙株式会社 | Object determination device, imaging device and monitor |
| CN1967564A (en) * | 2005-11-17 | 2007-05-23 | 中华电信股份有限公司 | Method and device for detecting and identifying human face applied to set environment |
| WO2009069831A1 (en) * | 2007-11-29 | 2009-06-04 | Kabushiki Kaisha Toshiba | Picture processing method and picture processing apparatus |
-
2009
- 2009-12-23 CN CN2009102620402A patent/CN102111535B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1494037A (en) * | 2002-11-01 | 2004-05-05 | ��ʽ���綫֥ | Apparatus and method for identifying personnel and passage controller |
| CN1734468A (en) * | 2005-06-17 | 2006-02-15 | 中华电信股份有限公司 | System for detecting dynamic human face in complicated environment |
| CN1885911A (en) * | 2005-06-22 | 2006-12-27 | 欧姆龙株式会社 | Object determination device, imaging device and monitor |
| CN1967564A (en) * | 2005-11-17 | 2007-05-23 | 中华电信股份有限公司 | Method and device for detecting and identifying human face applied to set environment |
| WO2009069831A1 (en) * | 2007-11-29 | 2009-06-04 | Kabushiki Kaisha Toshiba | Picture processing method and picture processing apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102111535A (en) | 2011-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102111535B (en) | Method for improving human face identification rate | |
| JP4748244B2 (en) | Image selection apparatus, image selection method, and program | |
| CN1716078B (en) | Image pickup apparatus and image pickup method | |
| US8314854B2 (en) | Apparatus and method for image recognition of facial areas in photographic images from a digital camera | |
| CN101241296B (en) | Focusing device, focusing method and image-capturing device provided with the focusing device | |
| KR101155406B1 (en) | Image processing apparatus, image processing method and computer readable-medium | |
| JP4577275B2 (en) | Imaging apparatus, image recording method, and program | |
| CN103052960A (en) | Rapid auto-focus using classifier chains, mems and/or multiple object focusing | |
| CN1604621A (en) | Image sensing apparatus and its control method | |
| CN104919791A (en) | Image processing device, image processing method and program | |
| EP2241106A2 (en) | Digital camera focusing using stored object recognition | |
| CN108337429A (en) | Image processing equipment and image processing method | |
| KR101686943B1 (en) | Digital photographing apparatus and control method thereof | |
| CN103079034A (en) | Perception shooting method and system | |
| JP2009177271A (en) | Imaging apparatus, and control method and program thereof | |
| US20100209093A1 (en) | Focus adjusting apparatus and focus adjusting method | |
| CN1607817A (en) | Digital camera | |
| JP5384273B2 (en) | Camera and camera recording method | |
| CN102812699A (en) | Image processing apparatus, method, and computer program storage device | |
| CN103905727A (en) | Object area tracking apparatus, control method, and program of the same | |
| JP4952920B2 (en) | Subject determination apparatus, subject determination method and program thereof | |
| TWI466034B (en) | Methods to Improve Face Recognition | |
| CN110830712A (en) | Autonomous photographing system and method | |
| JP2009219144A (en) | Imaging apparatus, image recording method, and, program | |
| CN102104734B (en) | Image pickup apparatus and control method for the image pickup apparatus |
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 | ||
| 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: 20121121 Termination date: 20181223 |