WO2011058807A1 - 映像処理装置および映像処理方法 - Google Patents
映像処理装置および映像処理方法 Download PDFInfo
- Publication number
- WO2011058807A1 WO2011058807A1 PCT/JP2010/065196 JP2010065196W WO2011058807A1 WO 2011058807 A1 WO2011058807 A1 WO 2011058807A1 JP 2010065196 W JP2010065196 W JP 2010065196W WO 2011058807 A1 WO2011058807 A1 WO 2011058807A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- face
- unit
- feature
- image
- face image
- Prior art date
Links
- 238000003672 processing method Methods 0.000 title claims description 21
- 238000009795 derivation Methods 0.000 abstract description 29
- 238000003384 imaging method Methods 0.000 abstract description 19
- 238000000034 method Methods 0.000 description 29
- 230000008569 process Effects 0.000 description 23
- 238000010586 diagram Methods 0.000 description 11
- 230000014509 gene expression Effects 0.000 description 10
- 230000006835 compression Effects 0.000 description 9
- 238000007906 compression Methods 0.000 description 9
- 230000006837 decompression Effects 0.000 description 9
- 230000006870 function Effects 0.000 description 9
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 7
- 230000009466 transformation Effects 0.000 description 7
- 210000000887 face Anatomy 0.000 description 4
- 230000007704 transition Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000005401 electroluminescence Methods 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000008921 facial expression Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 210000003127 knee Anatomy 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/61—Control of cameras or camera modules based on recognised objects
- H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
Definitions
- the present invention relates to an image processing apparatus and an image processing method for storing feature amounts of a face image so as to specify a subject.
- a digital still camera or digital video camera or the like that specifies the face image (face image) of a person specified by the user from the generated video and automatically adjusts the focus and exposure to the specified face image
- Video processing devices are in widespread use.
- Such a video processing apparatus derives in advance the feature amount of the face image from the face image designated by the user, and stores the feature amount later for specifying the face image.
- the feature amount of the face image is affected by the direction of the face, even if the subject is the same person, if the direction of the face is changed too much, it may be misjudged as being a different person.
- Patent Document 1 When the technique of Patent Document 1 described above is used, a certain degree of robustness can be given to the orientation of the face when specifying the face image, but the face image whose posture (direction of the face) is changed is Since the prediction is generated, if the change in the direction or expression of the face becomes large, there is a possibility that an erroneous determination may occur in the face authentication process.
- the video processing apparatus previously obtains a plurality of face images having different face orientations and expressions for the same person and derives and stores the feature amount, the accuracy of specifying the face image in the face authentication process is obtained. It can be improved. However, for this purpose, it is necessary to repeat the imaging and registration operations while having the person of the subject change the direction and expression of the face each time. In this case, not only the user but also the person of the subject feels bothersome. Furthermore, in this imaging and registration operation, whether or not a face image having a sufficiently different face orientation or expression can be imaged and registered can be left to the user's judgment, so a plurality of similar feature quantities can be used. It may be registered, and the accuracy at the time of specifying a face image may deteriorate.
- the present invention provides an image processing apparatus and an image processing method capable of deriving an appropriate feature amount that can reliably specify a face image without the user having a bother.
- the purpose is that.
- a video processing apparatus stores a video acquisition unit for acquiring a video, a position specifying unit for specifying one face image from the video, a specified face image, and a storage unit.
- a face associating unit for associating the extracted face information with one or more feature amounts
- a feature amount deriving unit for deriving a feature amount of the identified face image
- a derived feature amount and
- a storage control unit that compares one or more feature amounts of face information associated with a face image and adds the derived feature amount to the face information and stores it in the storage unit when a predetermined condition is satisfied; It is characterized by having.
- the predetermined condition may be that the degree of similarity between the derived feature amount and all one or more feature amounts of face information associated with the identified face image is less than a predetermined value.
- the video processing apparatus may include a display control unit that causes the display unit to display an image indicating the number of feature amounts actually stored with respect to the upper limit number of storable feature amounts.
- another video processing apparatus includes a video acquisition unit for acquiring a video, a position specifying unit for specifying one face image from the video, a specified face image, and a storage unit.
- a face associating unit that associates one or more feature amounts stored in the image with face information that summarizes the face direction
- a face direction deriving unit that derives the face direction of the identified face image
- the feature quantity deriving unit that derives the feature quantity of the captured face image, the orientation of the derived face, and the orientation of one or more faces of face information associated with the identified face image are compared, and a predetermined condition is established.
- a storage control unit that adds the derived feature amount and the derived face orientation to the face information and stores the face information in the storage unit.
- the predetermined condition is one or more ranges including the face direction of the face information associated with the identified face image out of a predetermined number of ranges regarding the face direction divided based on the pitch angle and the yaw angle
- the orientation of the derived face may not be included in any of the above.
- the image processing apparatus is configured to calculate the number of feature amounts actually stored with respect to the upper limit number of storable feature amounts or a predetermined number of ranges regarding the face direction divided based on the pitch angle and the yaw angle.
- a display control unit may be provided that causes the display unit to display an image indicating one or both of the range in which the stored face orientation is included.
- the video processing method of the present invention acquires a video, identifies one face image from the video, and identifies the identified face image, and face information in which one or more feature amounts are summarized. Relating the identified face image, and comparing the derived feature with one or more feature amounts of face information associated with the identified face image, and satisfying a predetermined condition. , And adding and storing the derived feature amount to face information.
- another video processing method of the present invention acquires a video, identifies one face image from the video, and identifies the identified face image, one or more feature quantities, and the direction of the face. And the face information associated with each other, the face direction of the identified face image is derived, and the derived face direction is compared with the face direction of the face information associated with the identified face image. When the predetermined condition is satisfied, the feature amount of the identified face image and the derived face direction are added to the face information and stored.
- FIG. 2 is an external view showing an example of a video processing apparatus.
- FIG. 2 is a functional block diagram showing a schematic configuration of a video processing device in the first embodiment. It is an explanatory view for explaining direction of a face. It is an explanatory view for explaining control of storage to a feature storage unit of a feature according to the first embodiment. It is a flowchart which shows the flow of a process of the video processing method in 1st Embodiment. It is a functional block diagram showing a schematic configuration of a video processing device in a second embodiment. It is an explanatory view for explaining classification of a face picture based on direction of a face in a 2nd embodiment.
- FIG. 1 shows the flowchart which shows the flow of a process of the video processing method in 1st Embodiment.
- It is a functional block diagram showing a schematic configuration of a video processing device in a second embodiment. It is an explanatory view for explaining classification of a face picture based on direction of a face in a
- FIG. 6 is an explanatory diagram for describing an image indicating the number of feature amounts and an image indicating a range including the orientation of a face. It is an explanatory view for explaining processing at the time of acquiring a feature-value from an external apparatus. It is a flowchart which shows the flow of a process of the video processing method in 2nd Embodiment.
- Feature amount storage unit storage unit 170: position specifying unit 172: face direction deriving unit 174, 474: face associating unit 176, 476: feature value deriving unit 178, 478: storage control unit 180, 480: display control unit
- FIG. 1 is an external view showing an example of a video processing apparatus 100.
- FIG. 1A shows a digital still camera as the video processing device 100
- FIG. 1B shows a video camera as the video processing device 100.
- the image processing apparatus 100 may be portable, and includes a main body 102, an imaging lens 104, an operation unit 106, and a viewfinder 108 which functions as a display unit.
- FIG. 2 is a functional block diagram showing a schematic configuration of the video processing apparatus 100 in the first embodiment.
- a video camera shown in FIG. 1B is given as the video processing apparatus 100.
- the video processing apparatus 100 specifies one face image on the captured video data, newly derives and stores a feature different from the feature stored for the face image, that is, An object of the present invention is to derive and store feature amounts of various face images different in the direction and expression of the face of the same person.
- the feature quantities of various face images derived and stored in this way can be used thereafter to authenticate any face image in the video (authentication mode).
- the video processing apparatus 100 includes an operation unit 106, an imaging unit 120, a data processing unit 122, a video holding unit 124, a viewfinder 108, a compression / decompression unit 128, a storage reading unit 130, and an external input / output unit 132. , A feature amount storage unit 134, and a central control unit 136.
- the operation unit 106 includes an operation key including a release switch, a cross key, and a switch such as a joystick, and receives user's operation input.
- a touch panel may be provided on the display surface of the viewfinder 108 described later, and the operation unit 106 may be used.
- the imaging unit 120 includes a focus lens 150 used for focus adjustment, a diaphragm 152 used for exposure adjustment, an image sensor 156 photoelectrically converting light incident through the imaging lens 104 and converting the light into image data, and a focus lens A drive circuit 158 for driving the aperture 150 and the aperture 152 functions as an image acquisition unit for acquiring an image (image data) of a subject in the imaging direction, and outputs the acquired image data to the data processing unit 122.
- the data processing unit 122 performs predetermined processing such as white balance adjustment, noise reduction processing, level correction processing, A / D conversion processing, color correction processing (gamma correction processing, knee processing), etc. on the image data output from the imaging unit 120. Processing is performed, and the processed video data is output to the video holding unit 124.
- predetermined processing such as white balance adjustment, noise reduction processing, level correction processing, A / D conversion processing, color correction processing (gamma correction processing, knee processing), etc.
- the video holding unit 124 is configured by a random access memory (RAM), a flash memory, a hard disk drive (HDD) or the like, and the video data input from the data processing unit 122, the compression / decompression unit 128, and the external input / output unit 132 Hold temporarily.
- RAM random access memory
- HDD hard disk drive
- the view finder 108 is composed of a liquid crystal display, an organic EL (Electro Luminescence) display, etc., and is linked to the image data output from the data processing unit 122 and the compression / decompression unit 128 and held in the image holding unit 124 or the operation unit 106 It functions as a display unit that displays instruction items.
- the user can check the video (image) displayed on the viewfinder 108 at the time of imaging and the video of the video data stored by the storage reading unit 130 described later. Further, the user can capture the subject at a desired position and occupied area by operating the operation unit 106 while visually recognizing the image displayed in the viewfinder 108. Further, the viewfinder 108 displays an image indicating the number of feature amounts actually stored with respect to the upper limit number of storable feature amounts described later.
- the compression / decompression unit 128 is configured to transmit video data output from the data processing unit 122 to M-JPEG (motion JPEG), MPEG (Moving Picture Experts Group) -2, H.264, and so on. Code data encoded by a predetermined coding method such as H.264 is output to the storage reading unit 130.
- M-JPEG motion JPEG
- MPEG Motion Picture Experts Group
- H.264 Motion Picture Experts Group
- the compression / decompression unit 128 outputs, to the video holding unit 124, video data obtained by decoding the code data encoded by the predetermined coding method, which the storage reading unit 130 has read from the storage medium 200.
- the storage reading unit 130 stores the code data encoded by the compression / decompression unit 128 in an arbitrary storage medium 200.
- an optical disc medium such as a DVD (Digital Versatile Disc) or a BD (Blu-ray Disc), or a medium such as a RAM, an EEPROM, a non-volatile RAM, a flash memory, or an HDD can be applied.
- the storage medium 200 is removable, but may be integrated with the video processing apparatus 100.
- the storage and reading unit 130 also reads encoded data from an arbitrary storage medium 200 storing encoded data obtained by encoding video data according to a predetermined encoding method, and outputs the encoded data to the compression / decompression unit 128.
- the external input / output unit 132 outputs the video data held in the video holding unit 124 to, for example, the display device 204 connected to the video processing device 100. Also, the external input / output unit 132 is connected to an external video reproduction device 206 such as, for example, a DVD player, a BD player, an HDD player, receives video data output from the video reproduction device, and outputs the video data to the video holding unit 124.
- an external video reproduction device 206 such as, for example, a DVD player, a BD player, an HDD player
- the feature storage unit 134 is configured by a RAM, a flash memory, an HDD, etc., and according to an instruction from a storage control unit described later, the face information combining one or more feature derived from the face image of the same person is identical. It functions as a storage unit that stores only the number of people.
- the central control unit 136 is constituted by a semiconductor integrated circuit including a central processing unit (CPU) and a signal processing unit (DSP: Digital Signal Processor), and manages and controls the entire video processing apparatus 100 using a predetermined program.
- CPU central processing unit
- DSP Digital Signal Processor
- the central control unit 136 also functions as a position specifying unit 170, a face direction deriving unit 172, a face associating unit 174, a feature value deriving unit 176, a storage control unit 178, and a display control unit 180.
- the video processing apparatus 100 In the registration mode, the video processing apparatus 100 according to the present embodiment identifies one face image on the captured video data, newly derives and stores a feature different from the feature stored for the face, In the authentication mode, this feature is used to authenticate the face in the video.
- this feature is used to authenticate the face in the video.
- the video processing apparatus 100 will be described separately for the registration mode and the authentication mode.
- the position specifying unit 170 specifies (selects) one face image from the video data acquired by the imaging unit 120 and stored in the video storage unit 124 in the registration mode in accordance with the user input through the operation unit 106 , The face image is tracked using existing image processing technology. Then, the position specifying unit 170 outputs the image information related to the face image for each frame to the face direction deriving unit 172 and the feature quantity deriving unit 176. When a plurality of face images are detected, the position specifying unit 170 similarly tracks each face image, and outputs image information on all the face images to the feature amount deriving unit 176.
- the imaging unit 120 is used as a video acquisition unit here, the storage reading unit 130 and the external input / output unit 132 function as a video acquisition unit, and the position specifying unit 170 is not limited thereto. Alternatively, one face image may be specified based on the image acquired by the external input / output unit 132.
- Such specification of one face image is performed by displaying an image based on the image data held in the image holding unit 124 on the viewfinder 108 and allowing the user to select the one face image through the operation of the operation unit 106. Be done.
- a touch panel is superimposed on the display surface of the viewfinder 108 as the operation unit 106, the user performs specification of the face image of the user by bringing the part corresponding to the position of the face image of 1 through the touch panel.
- the position specifying unit 170 automatically selects all face images present in the screen, and the display control unit 180 described later displays a plurality of frames so as to surround all the selected face images. In the state, it may be displayed on the screen as “which person will you register?”, And the user may be allowed to select one of the face images.
- the position specifying unit 170 positions the person of the subject so that the face appears in, for example, a predetermined area in the center of the screen, and an area in the image corresponding to the predetermined area at an arbitrary timing by the user's operation input.
- the face image of may be specified.
- the predetermined area may be arbitrarily designated by the user on the screen.
- the display control unit 180 superimposes and displays an index such as a square frame on the boundary of the predetermined area displayed on the viewfinder 108.
- the position specifying unit 170 scans a search area of a predetermined size in the image, and the feature points indicating features of organs constituting the face such as eyes, nose and mouth are displayed.
- the face image is extracted by detection
- the face image extraction means is not limited to the detection of feature points.
- the face image may be extracted by detecting a skin color area or performing pattern matching.
- the position specifying unit 170 instructs the face direction deriving unit 172 to obtain image information including at least coordinates of the face image and the size of the face image, and image information including at least the coordinates of the face image, the size of the face image, and the likelihood of the face image.
- the coordinates of the face image indicate the relative coordinates of the face area to the image size
- the size of the face image indicates the relative size of the face area to the image size
- the likelihood of the face image indicates that the face image is It indicates the certainty of being an image of a face, and may be derived as, for example, a similarity indicating the degree of similarity to a standard face image.
- the position specifying unit 170 may weight the similarity based on the detection result of the skin color area, and may correct the similarity to a low value, for example, if the skin color area is small.
- FIG. 3 is an explanatory view for explaining the direction of the face.
- the image information includes the coordinates of the face image described above, the size of the face image, and the certainty of the face image, as well as the roll angle of the face image for rotational correction of the face image.
- the roll angle of the face image to be output to the feature quantity derivation unit 176 is the rotation angle of the face image about the roll axis defined in FIG.
- definitions of a pitch angle (rotation angle around the pitch axis) and a yaw angle (rotation angle around the yaw axis), which will be described later, are also shown in FIGS. 3 (b) and 3 (c).
- the position specifying unit 170 In the face direction deriving unit 172, based on the coordinates of the face image indicated by the image information output from the position specifying unit 170 and the size of the face image, the position specifying unit 170 generates image data based on the video data stored in the video storage unit 124.
- the specified face image is read out, and the face direction other than the roll angle, that is, the pitch angle and the yaw angle of the face are derived from the eye and face of the face image that are feature points of the face image and the like. ), (C)).
- the feature quantity deriving unit 176 reads the face image from the video data stored in the video storage unit 124 based on the coordinates of the face image indicated by the image information output from the position specifying unit 170 and the size of the face image. . Then, for the read face image, resolution conversion and rotation correction in the roll angle direction are performed based on the size of the face image indicated in the image information and the roll angle of the face image, and normalized (with a predetermined size Convert to upright) face image.
- the feature quantity derivation unit 176 features the face image identified by the position identification unit 170 based on the face image transformed by itself and the pitch angle and the yaw angle that are the face orientation derived by the face direction derivation unit 172. Derive the quantity. Specifically, first, the feature quantity deriving unit 176 further performs affine transformation on the normalized face image from the pitch angle and the yaw angle of the face derived by the face direction deriving unit 172, and the face turned to the front Correct to the face image of.
- the feature quantity derivation unit 176 attempts to detect feature points related to the face image after affine transformation.
- affine-transform feature points relating to the face image before affine transformation that is detected in advance not from the face image after affine transformation
- the feature points of the face image after affine transformation are derived.
- the certainty of the feature points indicating the certainty that each feature point is the feature point of each part of the face is derived for each feature point.
- the certainty of being a feature point of the eyes is lowered.
- the feature quantity deriving unit 176 determines whether the face image is a face image worth processing, and, for example, the pitch angle of the face image is in the range of -15 ° to + 15 °, and the yaw angle of the face image is Is in the range of ⁇ 30 ° to + 30 °, and the certainty of the face image indicated in the image information and the certainty of being a feature point satisfy the predetermined conditions respectively corresponding to the preset
- Gabor jet is derived as the feature amount of the face image.
- the Gabor filter used to determine the Gabor jet, is a filter with both direction selectivity and frequency response.
- the feature quantity deriving unit 176 performs convolution of the face image using a plurality of Gabor filters having different directions and frequencies.
- the set of scalar values obtained is called Gabor jet.
- the feature quantity deriving unit 176 obtains Gabor jet as a local feature quantity in the vicinity of the feature point on the face image.
- the feature quantity deriving unit 176 outputs the feature quantity derived based on the feature points of the face image after affine transformation to the face associating unit 174.
- the feature quantity is represented as a vector quantity as a set of a plurality of sets of scalar values (Gaboa-jet).
- One vector quantity is derived from one face image.
- the face associating unit 174 combines the face image specified by the position specifying unit 170 according to the user's input and the face information obtained by putting together the feature amounts derived from the face image of the same person (hereinafter referred to simply as the face information of the same person) Is determined based on the degree of similarity between feature amounts, for example.
- the face associating unit 174 determines that the face image specified by the position specifying unit 170 according to the user's input and the face information of the same person are not yet stored in the feature amount storage unit 134, the feature amount is updated. It is stored in the feature storage unit 134 as face information.
- the face associating unit 174 includes the face image identified by the position identifying unit 170 according to the user input, and the identified face image if the face information of the same person is already stored in the feature amount storage unit 134; The face information of the same person stored in the feature amount storage unit 134 is associated.
- specific processing of the face associating unit 174 will be described.
- the feature amount storage unit 134 stores a plurality of pieces of face information in which a plurality of feature amounts derived from a plurality of face images of one person are grouped according to the number of persons.
- the face associating unit 174 derives the similarity for each of the feature amount derived by the feature amount deriving unit 176 and the plurality of feature amounts of the plurality of pieces of face information read out from the feature amount storage unit 134.
- the face associating unit 174 stores the feature amount derived by the feature amount deriving unit 176 and the 1 face stored in the feature amount storage unit 134. Derivation of similarity with one feature of information. In addition, when a plurality of feature quantities are grouped and stored in one piece of face information, the face associating unit 174 stores the feature quantities derived by the feature quantity deriving unit 176 and the feature quantity storage unit 134.
- the similarities between one or more face information and a plurality of feature quantities are derived, and the highest similarity among the derived one or more similarities is output from the feature quantity output from the feature quantity deriving unit 176, and It is assumed that the similarity of face information with a plurality of feature quantities.
- the face associating unit 174 applies the above-described process of deriving the degree of similarity to one piece of face information to all of the plurality of pieces of face information.
- the face associating unit 174 first performs the feature amount output from the feature amount deriving unit 176 and the one feature amount of, for example, one piece of face information read from the feature amount storage unit 134. Then, the similarity d0, d1, d2,..., Dn (n is a positive number) for each feature point is obtained by a method such as normalized correlation calculation.
- the face associating unit 174 derives the similarity Fi as a whole face from the similarity vector D using, for example, an AdaBoost algorithm or a support vector machine (SVM). Then, the face associating unit 174 derives the similarity Fi with respect to all of a plurality of feature quantities of face information of 1, and the maximum value among them is the feature quantity output from the feature quantity deriving section 176, and It is assumed that the degree of similarity F with a plurality of feature quantities of face information.
- AdaBoost AdaBoost algorithm
- SVM support vector machine
- the face associating unit 174 derives the similarity F with respect to all face information, and if the largest among the derived similarity F is smaller than a predetermined first threshold, the position identifying unit 170 It is determined that the identified face image and the face information of the same person are not stored in the feature storage unit 134 yet.
- the face associating unit 174 stores the feature amount output from the feature amount deriving unit 176 in the feature amount storage unit 134 as a new feature amount of face information. Then, the face associating unit 174 associates the face image specified by the position specifying unit 170 with the face information newly stored in the feature storage unit 134 as the same person.
- the face associating unit 174 determines that the face information having the largest similarity F is It is determined that the face image of the same person as that of the face image specified by the position specifying unit 170 is already stored in the feature amount storage unit 134. Then, the face associating unit 174 associates the face image identified by the position identifying unit 170 with the face information stored in the feature storage unit 134 and having the maximum similarity F as the same person.
- the face associating unit 174 associates the face image specified by the position specifying unit 170 with the face information stored in the feature storage unit 134, for example, based on the user's operation input through the operation unit 106. It is also good. Specifically, as described above, the user specifies (selects) one face image from the video data stored in the video storage unit 124, and at the same time, the feature quantity is stored in advance in the feature storage unit 134. When face information of the person of the subject whose feature amount is to be stored is selected from among the existing face information, the face associating unit 174 executes the determination process of the same person through derivation of the similarity.
- the face image specified by the position specifying unit 170 can be associated with the face information selected by the user in the feature storage unit 134 as the same person.
- the face image identified by the position identification unit 170 is associated with face information without deriving the similarity, and the first image (first frame) of the face images identified and tracked by the position identification unit 170. From the face image of, it can be the target of storage of feature quantities. Furthermore, for example, even in the case of only one frame of video (in the case of photographing), the position specifying unit 170 specifies a face image but does not track the first face image as a feature amount. It can also be an object of memory.
- the feature quantity derivation unit 176 derives feature quantities from the image information continuously captured for the face image identified by the position identification unit 170.
- the storage control unit 178 compares the feature amount derived by the feature amount deriving unit 176 with one or more feature amounts of face information associated with the identified face image, and when the predetermined condition is satisfied, the feature is derived.
- the feature amount is added to the face information and stored in the feature amount storage unit 134.
- the storage control unit 178 only the feature amount of the face image that satisfies the predetermined condition among the specified face images is automatically stored in the feature amount storage unit 134. It is possible to identify and improve the operability of the user.
- the face associating unit 174 associates the face image specified by the position specifying unit 170 with the face information in the feature storage unit 134 as the same person, next, regarding the face information of the same person, The face image not yet registered (different) is extracted, and the feature amount of the extracted face image is stored in the feature amount storage unit 134.
- the feature amount newly derived by the feature amount deriving unit 176 and the face image identified by the position identifying unit 170 stored in the feature amount storage unit 134 are associated.
- the predetermined condition is that the degree of similarity of the face information with one or more feature amounts is less than a predetermined value.
- the storage control unit 178 causes the feature amount storage unit 134 to store feature amounts of face images having different face orientations and expressions.
- the similarity F is equal to or greater than the second threshold, it is considered that the current face image and the face image registered earlier are the same face orientation and expression. In this case, even if the current face image is registered, the storage control unit 178 does not contribute much to the improvement of the accuracy of authentication in the authentication mode for determining whether or not the face in the image described later is registered. Does not store such feature amounts of face images in the feature amount storage unit 134.
- FIG. 4 is an explanatory diagram for describing control of storage of the feature amount in the feature amount storage unit 134 in the first embodiment.
- indices M1, M2, M3 and M4 and values m1a, m1b, ... of the respective feature points with respect to feature amounts 230a to 230d of arbitrary face information. Is stored.
- the feature amount 230 e newly derived from the face image associated with the face information as the same person is output from the feature amount deriving unit 176.
- the storage control unit 178 derives the similarity between each of the feature amounts 230a to 230d of the face information and the newly derived feature amount 230e, and the highest feature amount, for example, the feature amount 230d here,
- the feature amount is not stored in the feature amount storage unit 134 when it is greater than or equal to the second threshold value in comparison with the second threshold value. If the value is less than the second threshold, as shown in FIG. 4B, the feature amount 230e is stored in the feature amount storage unit 134 as the feature amount of the face information.
- the feature amount of the face image stored in the feature amount storage unit 134 is used in deriving the similarity with the feature amount derived from the face image included in the video generated by the imaging unit 120 in the authentication mode.
- the video processing apparatus 100 determines whether the candidate for the feature quantity to be stored from now on is different from the feature quantity already stored based on the similarity, which is the same determination criterion as the authentication mode. A plurality of different feature quantities relating to the same person effective even in the authentication mode can be reliably extracted, and the accuracy of authentication can be improved with a small number of comparison processes.
- the storage of the feature amount described above is executed, for example, in a registration mode for registering the feature amount of the identified face image, triggered by the user's operation input.
- the feature quantity deriving unit 176 sequentially determines the feature quantities of the identified face images associated with the face information by the face associating section 174. Derivation is performed, and the storage control unit 178 registers feature amounts that satisfy the predetermined condition among the derived feature amounts as needed.
- the display control unit 180 superimposes an image indicating the number of feature amounts of face information associated with the identified face image stored in the feature amount storage unit 134 on the generated image of the subject. Display on the viewfinder 108. For example, when storing up to eight feature quantities for face information of one person, it is assumed that three feature quantities are already stored for face information of a certain person. In this case, a pie chart filled with 3/8 is displayed. As described above, the display control unit 180 causes the viewfinder 108 to display an image indicating the number of feature amounts actually stored relative to the upper limit number of storable feature amounts.
- the user can visually recognize the image indicating the number of feature amounts of the displayed face information, check the progress of storage of the feature amounts of the face image, and improve the operability of the user. It becomes possible.
- the registration mode when the registration of the maximum number, for example, eight feature quantities is completed with respect to the face of the person to be registered, or when the registration mode is ended by the user's operation input, the registration feature of the registered feature quantities Transition to the input mode to input personal information.
- the registration feature of the registered feature quantities Transition to the input mode to input personal information.
- the display control unit 180 causes the viewfinder 108 to display a message such as “Please enter the name of the registered person” or “Please enter the date of birth of the registered person”. Then, the user inputs personal information such as the name and date of birth of the feature amount to be registered through the operation unit 106.
- the storage control unit 178 causes the feature amount storage unit 134 to store the personal information and date and time information indicating date and time of registration time in association with the feature amount. In addition, the user can also input the personal information immediately and not later.
- the mode may automatically shift to the registration mode.
- the display control unit 180 causes the viewfinder 108 to display a message such as “Do you want to continue registering Mr. A”, and the user confirms the face information to be registered for the feature amount and transitions to the registration mode Allow the choice.
- the feature storage unit 134 stores the feature for each face information, it may store, for example, the face image itself used when deriving the feature.
- the face image By storing the face image as described above, the user can actually visually recognize the face image used for face authentication in the authentication mode. Therefore, the user can recognize a face image that is considered unnecessary, such as a face image of an extreme expression. , And can be deleted from the feature storage unit 134.
- the feature storage unit 134 stores only the face image without storing the feature, and the feature derivation unit 176 reads the face image from the feature storage unit 134 based on the face image.
- Feature quantities may be derived.
- the feature amount stored in the feature amount storage unit 134 is used when authenticating the face of the subject in the authentication mode.
- the display control unit 180 causes the viewfinder 108 to display one or more pieces of face information stored in the feature amount storage unit 134.
- the position specifying unit 170 acquires the face image for all the face images included in the video data acquired by the imaging unit 120 and stored in the video storage unit 124. , And outputs image information including the coordinates of the face image for each frame to the feature quantity derivation unit 176.
- the feature quantity deriving unit 176 derives the feature quantity of the face image identified by the position identifying unit 170 based on the coordinates of the face image output from the position identifying unit 170.
- the storage control unit 178 derives, from the feature amounts stored in the feature amount storage unit 134, the similarity between the feature amount in the face information selected by the user and the feature amount derived by the feature amount deriving unit 176.
- the drive circuit 158 drives the focus lens 150 and the diaphragm 152 to adjust focus and exposure in accordance with the corresponding subject.
- the display control unit 180 superimposes and displays an index such as a square frame on the corresponding face image in the video displayed on the viewfinder 108, for example.
- the storage control unit 178 changes the face orientation and expression for the feature amount of the face image of the subject that can be regarded as the same person as the face information, and the similarity is less than the second threshold.
- the feature amount storage unit 134 is automatically stored. Therefore, in the registration of the feature amount, it is possible to derive an appropriate feature amount capable of reliably authenticating the face without causing the user to feel bothersome.
- FIG. 5 is a flowchart showing the flow of processing of the video processing method in the first embodiment.
- FIG. 5 particularly shows the flow of processing in the registration mode described above.
- the imaging unit 120 acquires a video (S300), and the position specifying unit 170 determines whether one face image can be specified from the video data held in the video holding unit 124 (S302). If the position specifying unit 170 can not specify the face image of 1 (NO in S302), the process returns to the image acquisition step (S300).
- the position specifying unit 170 can specify one face image (YES in S302), the face image is tracked, and image information regarding the face image for each frame is output to the feature quantity deriving unit 176 (S304).
- the feature amount derivation unit 176 has, for example, a pitch angle in the range of -15 ° to + 15 ° and a yaw angle is in the face direction derived by the face direction derivation unit 172.
- a feature amount when it is in the range of -30 ° to + 30 ° and the certainty of the face image indicated in the image information and the certainty of being the feature point satisfy predetermined conditions respectively set in advance Are derived (S306).
- the face associating unit 174 determines whether the face image identified by the position identifying unit 170 is associated with the face information stored in the feature storage unit 134 (S308). If not associated (NO in S308), the face associating unit 174 sets the feature amount derived by the feature amount deriving unit 176 and one of the plurality of face information read out from the feature amount storage unit 134. The similarity is derived for one of the plurality of feature quantities (S310).
- the face associating unit 174 compares the maximum value of the degree of similarity derived so far with the degree of similarity derived at that time with respect to the face information related to the feature amount from which the degree of similarity is derived (S312), If the degree of similarity derived at that time is larger than the maximum value of degrees of similarity derived so far (YES in S312), the maximum value of the degree of similarity for the target face information is replaced with the degree of similarity derived at that time (S314).
- the face associating unit 174 determines whether the derivation of the similarity has been completed for all the feature amounts of one piece of face information read from the feature amount storage unit 134 (S316). If the process has not been completed (NO in S316), the process returns to the similarity derivation step (S310), and the same process is performed on feature quantities whose similarity has not yet been derived.
- the face associating unit 174 reads the feature amounts from the feature amount storage unit 134. It is determined whether the derivation of the degree of similarity is complete for all feature amounts of face information (S318). If the process has not been completed (NO in S318), the process returns to the similarity derivation step (S310), and the same process is performed on feature quantities of other face information whose similarity has not yet been derived.
- the face associating unit 174 determines the degree of similarity for each derived face information. Of the maximum values, it is determined whether the maximum similarity is equal to or greater than a first threshold (S320). If it is equal to or greater than the first threshold (YES in S320), the face associating unit 174 determines that the feature information storage unit 134 has already stored face information of the same person as the face image specified by the position specifying unit 170. Then, the face image identified by the position identification unit 170 is associated with the corresponding face information (S324).
- the face associating unit 174 determines that the feature information storage unit 134 does not store face information of the same person as the face image specified by the position specifying unit 170, The derived feature quantity is stored in the feature quantity storage unit 134 as a feature quantity of new face information (S322), and the face image specified by the position specifying unit 170 is associated with the new face information (S324). Then, the process returns to the video acquisition step (S300).
- the storage control unit 178 When the face image identified by the position identification unit 170 is associated with the face information stored in the feature storage unit 134 (YES in S308), the storage control unit 178 The similarity between the feature quantity derived by the quantity deriving unit 176 and one of the other feature quantities of the same face information is derived (S326).
- the storage control unit 178 compares, for the other feature quantities of the same face information, the maximum value of the degree of similarity derived so far and the degree of similarity derived at that time (S 328) If the degree of similarity derived at that time is larger than the maximum value of similarity (YES in S328), the maximum value of the degree of similarity is replaced with the degree of similarity derived at that time (S330).
- the storage control unit 178 determines whether the derivation of the similarity has been completed for other feature quantities of the same face information (S332). If the process has not been completed (NO in S332), the process returns to the similarity derivation step (S326), and the same process is performed on the feature quantities for which the similarity has not yet been derived.
- the storage control unit 178 determines whether the maximum value of the derived similarity satisfies the predetermined condition, ie, It is determined whether it is less than the second threshold (S334). If it is less than the second threshold (YES in S334), the storage control unit 178 sets the feature quantity newly derived by the feature quantity derivation unit 176 as the feature quantity of face information of the same same person in the feature quantity storage unit 134. It memorizes (S336). Then, the central control unit 136 determines whether the number of feature amounts related to target face information stored in the feature amount storage unit 134 has already reached the maximum number (S338). If the number of feature amounts has reached the maximum number (YES in S 338), the display control unit 180 causes the viewfinder 108 to display that the maximum number of feature amounts to be stored for one face information has been reached, and the registration mode Urges the end of (S340).
- the central control unit 136 determines whether or not there is an instruction to end the registration mode by an operation input by the user (S342). When there is no instruction to end (NO in S342), the process returns to the video acquisition step (S300). If the end instruction has been issued (YES in S342), the registration mode is ended.
- the storage control unit 178 derives the similarity and compares it with the second threshold to determine whether to store the newly derived feature amount in the feature amount storage unit 134 or not.
- the second embodiment an image processing apparatus 400 will be described which narrows and determines an angle of a face which has a large influence on the feature amount.
- the components substantially the same as those of the above-described video processing apparatus 100 will be assigned the same reference numerals and descriptions thereof will be omitted.
- FIG. 6 is a functional block diagram showing a schematic configuration of the video processing apparatus 400 in the second embodiment.
- the video processing apparatus 400 includes an operation unit 106, an imaging unit 120, a data processing unit 122, a video holding unit 124, a viewfinder 108, a compression / decompression unit 128, a storage reading unit 130, and an external input / output unit 132. , A feature amount storage unit 134 functioning as a storage unit, and a central control unit 436.
- the operation unit 106, the imaging unit 120, the data processing unit 122, the video holding unit 124, the view finder 108, the compression / decompression unit 128, and the storage reading unit 130 which have already been described as components in the first embodiment.
- the functions of the external input / output unit 132 and the feature amount storage unit 134 are substantially the same, and thus redundant description will be omitted.
- the central control unit 436 having a different configuration will be mainly described.
- the central control unit 436 is formed of a semiconductor integrated circuit including a central processing unit (CPU) and a signal processing unit (DSP), and manages and controls the entire video processing apparatus 400 using a predetermined program.
- the central control unit 436 also functions as a position specifying unit 170, a face direction deriving unit 172, a face associating unit 474, a feature value deriving unit 476, a storage control unit 478, and a display control unit 480.
- the face associating unit 474 performs the same process as the face associating unit 174 of the first embodiment, and associates the identified face image with face information. At this time, since the face information stored in the feature storage unit 134 includes not only the feature but also the direction of the face, the face associating unit 474 includes one or more such features and The face information in which the face direction is summarized is associated with the identified face image.
- the feature quantity deriving unit 476 compares the direction of the face derived by the face direction deriving unit 172 with the direction of one or more faces of the face information associated with the face image identified by the position identifying unit 170, and the predetermined condition If the above condition is satisfied, the feature amount of the identified face image is derived. In the present embodiment, the feature quantity deriving unit 476 derives the feature quantity of the identified face image only when the predetermined condition is satisfied, but the feature quantities of all the identified face images regardless of the predetermined condition May be derived.
- the storage control unit 478 compares the direction of the face derived by the face direction deriving unit 172 with the direction of one or more faces of the face information associated with the face image identified by the position identifying unit 170, and determines a predetermined condition. If satisfied, the feature amount newly derived by the feature amount deriving unit 476 and the face direction derived by the face direction deriving unit 172 are added to the face information and stored in the feature amount storage unit 134.
- the predetermined condition is the face information associated with the face image identified by the position identifying unit 170 within a predetermined number of ranges regarding the face direction divided based on the pitch angle and the yaw angle. It is assumed that the face orientation derived by the face orientation deriving unit 172 is not included in any one or a plurality of ranges including the face orientation.
- FIG. 7 is an explanatory diagram for explaining classification of a face image based on the orientation of a face in the second embodiment.
- FIG. 7 (a) is an explanatory diagram for explaining the state of storage of feature amounts for certain face information
- FIG. 7 (b) is a diagram in which the feature amounts are newly stored in FIG. 7 (a). It is explanatory drawing for demonstrating the subsequent state.
- the feature storage unit 134 stores face images (for example, face images 410 having different face orientations shown in FIGS. 7A and 7B) instead of the feature amount.
- the table 412 is the face image itself recorded in the feature storage unit 134
- the table 414 is the presence or absence of the face image included in the range of the predetermined face orientation. Indicates
- the face direction deriving unit 172 derives the pitch angle and the yaw angle of the face image, and the feature quantity deriving unit 476 has a pitch angle of + 15 ° to -15. If the yaw angle is outside the range of + 30 ° to -30 °, the feature amount is not derived.
- the feature amount deriving unit 476 has a pitch angle and a yaw angle, which are face orientations of the face image newly derived by the face direction deriving unit 172, in the range shown in FIG. 7A (about -15 ° to -5 of the pitch angle). Judge the range within the range of -5 ° to 5 °, 5 ° to 15 °, yaw angle of -30 ° to -10 °, -10 ° to 10 °, 10 ° to 30 °) Do. Then, the feature quantity deriving unit 476 is configured such that the flag of the table 414 shown in FIG. 7A corresponding to the range among the plurality of flags stored in association with the feature quantity for the face information of the same person is already If the feature amount is “1” indicating that the feature amount is stored, the feature amount of the face image is not derived.
- the flag shown in FIG. 7A is “0” indicating that the feature amount is not stored yet, that is, a predetermined number of face orientations divided based on the pitch angle and the yaw angle
- one or more ranges including the face orientation of the face information associated with the face image specified by the position specifying unit 170 stored in the feature storage unit 134 among the nine ranges in the embodiment If the face orientation of the face image newly derived by the face orientation deriving unit 172 is not included in any of the above, the feature amount deriving unit 476 derives the feature amount of the face image identified by the position identifying unit 170.
- the storage control unit 478 adds the feature amount derived by the feature amount deriving unit 476 and the face direction derived by the face direction deriving unit 172 to the face information and stores it, and sets the corresponding flag of the table 414 to “1 Change to ".
- the pitch angle and the yaw angle of the face direction of the face image newly derived by the face direction deriving unit 172 are the position 416 (pitch angle -15 ° to -5 ° of N7) shown in FIG. If it is 10 ° to 30 °, as shown in FIG. 7B, the feature amount is newly stored, and the flag is changed from “0” to “1”.
- FIG. 8 is an explanatory diagram for describing an image 418a indicating the number of feature amounts and an image 418b indicating a range including the orientation of the face.
- the display control unit 480 divides the number of feature amounts actually stored relative to the upper limit number of storable feature amounts based on the pitch angle and the yaw angle.
- the viewfinder 108 displays an image indicating one or both of the range including the face orientation actually stored for the predetermined number of ranges regarding the face orientation to be processed.
- the display control unit 480 when the table 412 illustrated in FIG. 7B is recorded in the feature storage unit 134, the display control unit 480, similar to the display control unit 180 according to the first embodiment, has an upper limit of storable feature amounts.
- An image 418 a) can be displayed on the viewfinder 108.
- the display control unit 480 sets the positions of N1, N2, N5, N6, N7, and N8 as the range of face orientations actually stored with respect to the above-described predetermined number of ranges regarding the face orientation.
- An image (for example, an image 418b shown in FIG. 8B) of 3 ⁇ 3 squares in vertical and horizontal directions in which squares corresponding to 3 ⁇ 3 squares are filled is displayed on the viewfinder 108.
- the number of feature quantities actually stored is 9 for the upper limit number of feature quantities that can be stored. It is shown that there are six.
- the user can set which of the image 418a and the image 418b is to be displayed by an operation input.
- the image is displayed so that not only an image indicating the number of feature amounts but also a range of face orientations in which the feature amounts are actually stored and a range of face orientations in which the feature amounts are not stored are known. Therefore, there is an advantage that it is easy for the user to grasp the situation such as, for example, the orientation of the face to be imaged and the orientation of the face which is less necessary to be imaged.
- the derivation of the feature amount of the face image is largely influenced by the direction of the face.
- the image processing apparatus 400 stores the feature amount limited to the face images having different face orientations, so that the influence of the facial expression is excluded and the face image having a difference only in the face orientations Can be stored.
- the orientation of the face that has a large influence on the feature amount can be classified by the pitch angle and the yaw angle.
- the face direction necessary for facilitating the authentication is determined in advance in a frame of a predetermined pitch angle and yaw angle range, and the storage control unit 478 classifies the face in the same face direction.
- the stored feature amounts are not stored, and the stored feature amounts are classified into different face orientations. Therefore, the storage control unit 478 can refer to a feature amount of a wide range of face orientations with respect to the face orientation having a large influence in the authentication mode.
- the feature amount of the face image generated by a device other than the video processing device 400 can also be taken inside.
- the storage control unit 478 features the received feature amount. It is stored in the amount storage unit 134.
- the storage control unit 478 causes the feature amount storage unit 134 to store the read feature amount.
- FIG. 9 is an explanatory diagram for explaining processing when a feature amount is acquired from the external device 420.
- FIG. 9 (a) is a table 414a showing the range of the orientation of the face in which the feature amount of any face information stored in the feature amount storage unit 134 is classified
- FIG. 9 (b) is an external view
- FIG. 9C is a table 414b showing the range of the face direction in which the feature amount of the face image of the same person as the arbitrary face information acquired from the device 420 is classified;
- FIG. 9 is a table 414a showing the range of the orientation of the face in which the feature amount of any face information stored in the feature amount storage unit 134 is classified
- FIG. 9 (b) is an external view
- FIG. 9C is a table 414b showing the range of the face direction in which the feature amount of the face image of the same person as the arbitrary face information acquired from the device 420 is classified
- FIG. 9 (a) is a table 414a showing the range of the orientation of the face
- FIGS. 9 (a) to 9 (c) are similar to the flag on each of N1 to N9 in FIGS. 7 (a) and 7 (b). It corresponds to the presence or absence.
- the storage control unit 478 is configured such that the feature amount received from the external device 420 (read from the storage medium 422) has a similarity to the feature amount of face information stored in the feature amount storage unit 134 equal to or higher than the first threshold.
- the feature amount of the target face information is compared with the face direction of the face image from which the feature amount is derived.
- the storage control unit 478 does not update the feature amount for the range of the face direction in which the flag illustrated in FIG. 9A is “1”, and the face in which the flag is “0”. If the feature amount received from the external device 420 has a feature amount of the corresponding face direction in the range of the direction of the image (N5 to N9 in FIG. 9A), the feature amount is stored in the feature amount storage unit 134 Let In FIG. 9B, since there is a feature amount of the face direction of N5, the storage control unit 478 stores this feature amount in the feature amount storage unit 134. As a result, as shown in FIG. 9C, the flag of N5 is also changed from “0” to “1” shown in FIG. 9A. Also, for example, when the feature quantity storage unit 134 stores the feature quantity derivation time as auxiliary information together and the feature quantity in the same face direction range is already stored, the storage control unit 478 May be stored in favor of the more recently derived features.
- the storage control unit 478 is configured to determine whether or not to store the feature amount based on the face direction.
- the feature quantities can be stored uniformly and efficiently without increasing the amount too much.
- the image processing apparatus 400 of the present embodiment it is possible to store feature quantities of a wide range of face orientations with respect to the face orientation that has a large influence on the authentication mode. It is possible to improve the accuracy.
- FIG. 10 is a flowchart showing a flow of processing of the video processing method in the second embodiment. Also in FIG. 10, as in FIG. 5, the flow of processing in the registration mode is particularly shown. About the process substantially equal to the image processing method of 1st Embodiment mentioned above, the same code
- the face associating unit 174 performs the position specifying unit 170. It is determined whether the identified face image is associated with the face information stored in the feature storage unit 134 (S500).
- the feature quantity derivation unit 476 derives the feature quantity of the face image identified by the position identification unit 170 (S502).
- the processes from the similarity derivation step (S310) to the face information associating step (S324) are substantially the same as the image processing method described in the first embodiment, so I omit it.
- the face direction deriving unit 172 The orientation of the face of the face image identified by the position identification unit 170 is derived (S504).
- the feature quantity deriving unit 476 compares the direction of the face derived by the face direction deriving unit 172 with the direction of one or more faces of the face information associated with the face image identified by the position identifying unit 170, and the predetermined condition
- the face orientation derived by the face orientation deriving unit 172 is divided into a predetermined number of face orientations based on the pitch angle and the yaw angle of face information associated with the identified face image. It is determined whether or not it is any of the above (whether the face is an unregistered face) (S506).
- the feature quantity deriving unit 476 derives the feature quantity of the face image specified by the position specifying unit 170 (S508), and the storage control unit 478 derives the feature quantity deriving unit 476
- the feature amount and the face orientation derived by the face direction deriving unit 172 are added to the existing face information of the same person and stored in the feature amount storage unit 134 (S336).
- the face direction derived by the face direction deriving unit 172 is any of the predetermined number of face directions divided based on the pitch angle and the yaw angle of the face information associated with the identified face image (S506 (NO), the maximum number determination step (S338).
- the maximum number determination step (S338) to the mode transition step (S342) are substantially the same as the image processing method described in the first embodiment, so the same reference numerals are given and the description is omitted.
- Each step in the image processing method of the present specification does not necessarily have to be processed in chronological order according to the order described as the flowchart, and may include processing in parallel or by a subroutine.
- the present invention can be used for a video processing apparatus and a video processing method for storing feature quantities of a face image in order to specify a subject.
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Studio Devices (AREA)
- Image Analysis (AREA)
- Processing Or Creating Images (AREA)
- Image Processing (AREA)
Abstract
Description
108 …ビューファインダ(表示部)
120 …撮像部(映像取得部)
130 …記憶読取部(映像取得部)
132 …外部入出力部(映像取得部)
134 …特徴量記憶部(記憶部)
170 …位置特定部
172 …顔向き導出部
174、474 …顔関連付部
176、476 …特徴量導出部
178、478 …記憶制御部
180、480 …表示制御部
図1は、映像処理装置100の一例を示した外観図である。図1(a)は、映像処理装置100としてデジタルスチルカメラを、図1(b)は、映像処理装置100としてビデオカメラを示している。映像処理装置100は、携帯性を有すものもあり、本体102と、撮像レンズ104と、操作部106と、表示部として機能するビューファインダ108を含んで構成される。
位置特定部170は、登録モードにおいて、撮像部120が取得し、映像保持部124に保持された映像データから、操作部106を通じたユーザ入力に応じて、1の顔画像を特定(選択)し、その顔画像を既存の画像処理技術を用いて追尾する。そして、位置特定部170は、フレーム毎の顔画像に関する画像情報を顔向き導出部172および特徴量導出部176に出力する。位置特定部170は、複数の顔画像が検出された場合には各顔画像について同様に追尾し、その全ての顔画像に関する画像情報を特徴量導出部176に出力する。
上述した登録モードにおいて、特徴量記憶部134に記憶された特徴量は、認証モードにおいて、被写体の顔を認証する際に用いられる。ユーザの操作入力によって認証モードに遷移する指示があると、表示制御部180は、ビューファインダ108に特徴量記憶部134に記憶されている1または複数の顔情報を表示させる。ユーザが、所望する顔情報を選択した後、撮像を開始すると、位置特定部170は、撮像部120が取得し、映像保持部124に保持された映像データに含まれる顔画像全てについて、顔画像を追尾し、フレーム毎の顔画像の座標を含む画像情報を特徴量導出部176に出力する。
さらに、上述した映像処理装置100を用いた映像処理方法も提供される。図5は、第1の実施形態における映像処理方法の処理の流れを示すフローチャートである。図5においては、特に、上述した登録モードの処理の流れについて示している。
上述した第1の実施形態では、記憶制御部178は、新たに導出された特徴量を、特徴量記憶部134に記憶させるか否かの判断に、類似度を導出して第2閾値と比較していた。第2の実施形態では、特徴量に対して影響が大きい、顔の角度に絞って判断する映像処理装置400について説明する。なお、上述した映像処理装置100と実質的に等しい構成要素については、同一の符号を付して説明を省略する。
図6は、第2の実施形態における映像処理装置400の概略的な構成を示した機能ブロック図である。映像処理装置400は、操作部106と、撮像部120と、データ処理部122と、映像保持部124と、ビューファインダ108と、圧縮伸長部128と、記憶読取部130と、外部入出力部132と、記憶部として機能する特徴量記憶部134と、中央制御部436と、を含んで構成される。第1の実施形態における構成要素として既に述べた操作部106と、撮像部120と、データ処理部122と、映像保持部124と、ビューファインダ108と、圧縮伸長部128と、記憶読取部130と、外部入出力部132と、特徴量記憶部134とは、実質的に機能が同一なので重複説明を省略し、ここでは、構成が相違する中央制御部436を主に説明する。
さらに、上述した映像処理装置400を用いた映像処理方法も提供される。図10は、第2の実施形態における映像処理方法の処理の流れを示すフローチャートである。図10においても、図5と同様、特に、登録モードの処理の流れについて示している。上述した第1の実施形態の映像処理方法と実質的に等しい処理については、同一の符号を付して説明を省略する。
Claims (8)
- 映像を取得する映像取得部と、
前記映像から1の顔画像を特定する位置特定部と、
特定された前記顔画像と、記憶部に記憶された、1または複数の特徴量をまとめた顔情報とを関連付ける顔関連付部と、
前記特定された顔画像の特徴量を導出する特徴量導出部と、
導出された前記特徴量と、前記特定された顔画像に関連付けられた前記顔情報の1または複数の特徴量とを比較し、所定条件を満たす場合に、導出された前記特徴量を前記顔情報に追加して前記記憶部に記憶させる記憶制御部と、
を備えることを特徴とする映像処理装置。 - 前記所定条件は、前記導出された特徴量と、前記特定された顔画像に関連付けられた顔情報の1または複数の特徴量全てとの類似度が所定値未満であることを特徴とする請求項1に記載の映像処理装置。
- 記憶可能な前記特徴量の上限数に対する実際に記憶されている前記特徴量の数を示す画像を表示部に表示させる表示制御部を備えることを特徴とする請求項1または2に記載の映像処理装置。
- 映像を取得する映像取得部と、
前記映像から1の顔画像を特定する位置特定部と、
特定された前記顔画像と、記憶部に記憶された、1または複数の特徴量とその顔の向きとをまとめた顔情報とを関連付ける顔関連付部と、
前記特定された顔画像の顔の向きを導出する顔向き導出部と、
前記特定された顔画像の特徴量を導出する特徴量導出部と、
導出された前記顔の向きと、前記特定された顔画像に関連付けられた前記顔情報の1または複数の顔の向きとを比較し、所定条件を満たす場合に、導出された前記特徴量と前記導出された顔の向きとを前記顔情報に追加して前記記憶部に記憶させる記憶制御部と、
を備えることを特徴とする映像処理装置。 - 前記所定条件は、ピッチ角とヨー角とに基づいて分けられる顔の向きに関する所定数の範囲のうち、前記特定された顔画像に関連付けられた顔情報の顔の向きが含まれる1または複数の範囲のいずれにも前記導出された顔の向きが含まれないことを特徴とする請求項4に記載の映像処理装置。
- 記憶可能な前記特徴量の上限数に対する実際に記憶されている前記特徴量の数、もしくは、ピッチ角とヨー角とに基づいて分けられる顔の向きに関する所定数の範囲に対する実際に記憶されている前記顔の向きが含まれる範囲、のいずれか一方または両方を示す画像を表示部に表示させる表示制御部を備えることを特徴とする請求項4または5に記載の映像処理装置。
- 映像を取得し、前記映像から1の顔画像を特定し、
特定された前記顔画像と、1または複数の特徴量をまとめた顔情報とを関連付け、
前記特定された顔画像の特徴量を導出し、
導出した前記特徴量と、前記特定された顔画像に関連付けられた前記顔情報の1または複数の特徴量とを比較し、所定条件を満たす場合に、導出した前記特徴量を前記顔情報に追加して記憶することを特徴とする映像処理方法。 - 映像を取得し、前記映像から1の顔画像を特定し、
特定した前記顔画像と、1または複数の特徴量とその顔の向きとをまとめた顔情報とを関連付け、
前記特定した顔画像の顔の向きを導出し、
導出した前記顔の向きと、前記特定した顔画像に関連付けられた前記顔情報の1または複数の顔の向きとを比較し、所定条件を満たす場合に、前記特定した顔画像の特徴量と前記導出した顔の向きとを前記顔情報に追加して記憶することを特徴とする映像処理方法。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US13/119,373 US20110199505A1 (en) | 2009-11-13 | 2010-09-06 | Image processing apparatus and image processing method |
CN201080002809.8A CN102172014A (zh) | 2009-11-13 | 2010-09-06 | 影像处理装置及影像处理方法 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2009-260364 | 2009-11-13 | ||
JP2009260364A JP4844670B2 (ja) | 2009-11-13 | 2009-11-13 | 映像処理装置および映像処理方法 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2011058807A1 true WO2011058807A1 (ja) | 2011-05-19 |
Family
ID=43991469
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2010/065196 WO2011058807A1 (ja) | 2009-11-13 | 2010-09-06 | 映像処理装置および映像処理方法 |
Country Status (4)
Country | Link |
---|---|
US (1) | US20110199505A1 (ja) |
JP (1) | JP4844670B2 (ja) |
CN (1) | CN102172014A (ja) |
WO (1) | WO2011058807A1 (ja) |
Families Citing this family (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101877764B (zh) * | 2009-04-29 | 2012-05-30 | 鸿富锦精密工业(深圳)有限公司 | 拍摄系统及使用该拍摄系统进行辅助构图的方法 |
JP5918996B2 (ja) * | 2011-12-27 | 2016-05-18 | キヤノン株式会社 | 被写体認識装置および辞書データ登録方法 |
RU2543950C2 (ru) * | 2011-12-28 | 2015-03-10 | Кэнон Кабусики Кайся | Устройство формирования изображения и способ управления указанным устройством |
JP5899472B2 (ja) * | 2012-05-23 | 2016-04-06 | パナソニックIpマネジメント株式会社 | 人物属性推定システム、及び学習用データ生成装置 |
JP5966657B2 (ja) * | 2012-06-22 | 2016-08-10 | カシオ計算機株式会社 | 画像生成装置、画像生成方法及びプログラム |
US8855369B2 (en) * | 2012-06-22 | 2014-10-07 | Microsoft Corporation | Self learning face recognition using depth based tracking for database generation and update |
JP6132490B2 (ja) * | 2012-08-20 | 2017-05-24 | キヤノン株式会社 | 認証装置、認証方法、およびプログラム |
KR20150018264A (ko) | 2013-08-09 | 2015-02-23 | 엘지전자 주식회사 | 안경형 단말기의 정보 제공 장치 및 그 방법 |
CN105282375B (zh) * | 2014-07-24 | 2019-12-31 | 钰立微电子股份有限公司 | 附着式立体扫描模块 |
US9384385B2 (en) * | 2014-11-06 | 2016-07-05 | Intel Corporation | Face recognition using gradient based feature analysis |
JP6873639B2 (ja) * | 2016-09-23 | 2021-05-19 | キヤノン株式会社 | 画像処理装置、画像処理方法およびプログラム |
CN110050276B (zh) * | 2016-11-30 | 2023-09-29 | 皇家飞利浦有限公司 | 患者识别系统和方法 |
JP6691309B2 (ja) * | 2017-10-31 | 2020-04-28 | キヤノンマーケティングジャパン株式会社 | 情報処理装置、及びその制御方法、プログラム |
JP7389997B2 (ja) * | 2019-11-07 | 2023-12-01 | シーテックドライブ株式会社 | カメラを用いたマーケティングシステム |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2003337926A (ja) * | 2002-05-21 | 2003-11-28 | Nippon Signal Co Ltd:The | アクセスコントロールシステム |
JP2007094637A (ja) * | 2005-09-28 | 2007-04-12 | Denso Corp | 顔画像認証装置 |
JP2007140823A (ja) * | 2005-11-17 | 2007-06-07 | Omron Corp | 顔照合装置、顔照合方法及びプログラム |
JP2009252118A (ja) * | 2008-04-09 | 2009-10-29 | Sony Corp | 撮像装置、画像処理装置、これらにおける画像解析方法およびプログラム |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4314016B2 (ja) * | 2002-11-01 | 2009-08-12 | 株式会社東芝 | 人物認識装置および通行制御装置 |
JP4725377B2 (ja) * | 2006-03-15 | 2011-07-13 | オムロン株式会社 | 顔画像登録装置、顔画像登録方法、顔画像登録プログラム、および記録媒体 |
JP4862447B2 (ja) * | 2006-03-23 | 2012-01-25 | 沖電気工業株式会社 | 顔認識システム |
JP5010905B2 (ja) * | 2006-12-13 | 2012-08-29 | パナソニック株式会社 | 顔認証装置 |
CN101408929A (zh) * | 2007-10-10 | 2009-04-15 | 三星电子株式会社 | 一种用于人脸识别系统的多模板人脸注册方法和装置 |
JP4577410B2 (ja) * | 2008-06-18 | 2010-11-10 | ソニー株式会社 | 画像処理装置、画像処理方法およびプログラム |
JP4720880B2 (ja) * | 2008-09-04 | 2011-07-13 | ソニー株式会社 | 画像処理装置、撮像装置、画像処理方法およびプログラム |
-
2009
- 2009-11-13 JP JP2009260364A patent/JP4844670B2/ja active Active
-
2010
- 2010-09-06 WO PCT/JP2010/065196 patent/WO2011058807A1/ja active Application Filing
- 2010-09-06 CN CN201080002809.8A patent/CN102172014A/zh active Pending
- 2010-09-06 US US13/119,373 patent/US20110199505A1/en not_active Abandoned
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2003337926A (ja) * | 2002-05-21 | 2003-11-28 | Nippon Signal Co Ltd:The | アクセスコントロールシステム |
JP2007094637A (ja) * | 2005-09-28 | 2007-04-12 | Denso Corp | 顔画像認証装置 |
JP2007140823A (ja) * | 2005-11-17 | 2007-06-07 | Omron Corp | 顔照合装置、顔照合方法及びプログラム |
JP2009252118A (ja) * | 2008-04-09 | 2009-10-29 | Sony Corp | 撮像装置、画像処理装置、これらにおける画像解析方法およびプログラム |
Also Published As
Publication number | Publication date |
---|---|
CN102172014A (zh) | 2011-08-31 |
JP2011109275A (ja) | 2011-06-02 |
US20110199505A1 (en) | 2011-08-18 |
JP4844670B2 (ja) | 2011-12-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2011058807A1 (ja) | 映像処理装置および映像処理方法 | |
JP5567853B2 (ja) | 画像認識装置および方法 | |
JP4274233B2 (ja) | 撮影装置、画像処理装置、および、これらにおける画像処理方法ならびに当該方法をコンピュータに実行させるプログラム | |
JP4755490B2 (ja) | ブレ補正方法および撮像装置 | |
US9761013B2 (en) | Information notification apparatus that notifies information of motion of a subject | |
JP6106921B2 (ja) | 撮像装置、撮像方法および撮像プログラム | |
JP4569670B2 (ja) | 画像処理装置、画像処理方法およびプログラム | |
JP4110178B2 (ja) | 撮像装置及びその制御方法及びプログラム及び記憶媒体 | |
US8218833B2 (en) | Image capturing apparatus, method of determining presence or absence of image area, and recording medium | |
JP4732303B2 (ja) | 撮像装置 | |
US8400532B2 (en) | Digital image capturing device providing photographing composition and method thereof | |
KR101661211B1 (ko) | 얼굴 인식률 개선 장치 및 방법 | |
JP2021071794A (ja) | 主被写体判定装置、撮像装置、主被写体判定方法、及びプログラム | |
JP5594157B2 (ja) | 撮像装置および撮像方法 | |
JP2008035125A (ja) | 撮像装置、画像処理方法およびプログラム | |
US12002279B2 (en) | Image processing apparatus and method, and image capturing apparatus | |
JP5799931B2 (ja) | 撮像装置、色候補出力方法及びプログラム | |
JP5374612B2 (ja) | 画像データの識別方法及び撮像装置、プログラム、及び記憶媒体 | |
JP2017174094A (ja) | 画像処理装置、画像処理方法及びプログラム | |
JP2011077753A (ja) | カメラの顔検出方法及び装置 | |
JP2010268054A (ja) | 画像処理装置、その制御方法及びプログラム | |
JP2013142930A (ja) | 画像処理装置、その制御方法、及びプログラム | |
JP2013157675A (ja) | 撮像装置及びその制御方法、プログラム、並びに記憶媒体 | |
JP5740934B2 (ja) | 被写体検出装置、被写体検出方法及びプログラム | |
JP2010004357A (ja) | 撮像装置及び撮像方法 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 201080002809.8 Country of ref document: CN |
|
WWE | Wipo information: entry into national phase |
Ref document number: 13119373 Country of ref document: US |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 10829767 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 10829767 Country of ref document: EP Kind code of ref document: A1 |