WO2020213166A1 - 画像処理装置、画像処理方法、及び画像処理プログラム - Google Patents
画像処理装置、画像処理方法、及び画像処理プログラム Download PDFInfo
- Publication number
- WO2020213166A1 WO2020213166A1 PCT/JP2019/016869 JP2019016869W WO2020213166A1 WO 2020213166 A1 WO2020213166 A1 WO 2020213166A1 JP 2019016869 W JP2019016869 W JP 2019016869W WO 2020213166 A1 WO2020213166 A1 WO 2020213166A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- face
- subject
- change
- image processing
- image
- Prior art date
Links
- 238000012545 processing Methods 0.000 title claims description 57
- 238000003672 processing method Methods 0.000 title claims description 5
- 230000008859 change Effects 0.000 claims abstract description 93
- 230000009471 action Effects 0.000 claims abstract description 19
- 238000000034 method Methods 0.000 claims description 40
- 230000008569 process Effects 0.000 claims description 36
- 238000003702 image correction Methods 0.000 claims description 5
- 230000002146 bilateral effect Effects 0.000 claims 3
- 239000000284 extract Substances 0.000 abstract description 6
- 230000001815 facial effect Effects 0.000 description 21
- 230000010365 information processing Effects 0.000 description 19
- 230000005856 abnormality Effects 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 9
- 238000000605 extraction Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 125000002066 L-histidyl group Chemical group [H]N1C([H])=NC(C([H])([H])[C@](C(=O)[*])([H])N([H])[H])=C1[H] 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000005452 bending Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 210000001747 pupil Anatomy 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 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 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 210000003462 vein Anatomy 0.000 description 1
Images
Classifications
-
- 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
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
-
- 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
- G06V40/165—Detection; Localisation; Normalisation using facial parts and geometric relationships
-
- 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
-
- 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
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
-
- 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
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- 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
- G06V40/40—Spoof detection, e.g. liveness detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Definitions
- the present invention relates to an image processing apparatus, an image processing method, and an image processing program.
- Biometric authentication technology is a technology that authenticates the person using the biometric information of the person to be authenticated.
- the biometric authentication technology includes face authentication technology, fingerprint authentication technology, vein authentication technology, voiceprint authentication technology and the like.
- biometric information obtained from the face image of the person to be authenticated is used when performing personal authentication.
- biometric information obtained from the face image of the person to be authenticated is used when performing personal authentication.
- it is possible for another person to impersonate the person by receiving the person's authentication using the person's photo it is possible to perform a spoofing attack more easily than other biometric authentication techniques.
- the authenticity is determined by detecting the facial feature points indicating the position of the facial part from the face image and using the movement of the facial feature points when the person to be authenticated performs a predetermined action.
- the technology is known (see, for example, Patent Document 1 and Patent Document 2).
- the present invention aims to determine the authenticity of a subject using an image of the subject.
- the image processing device includes a storage unit, an operation identification unit, and a determination unit.
- the storage unit stores a plurality of time-series images taken of the subject when the subject is instructed to change the direction of the face.
- the motion specifying unit extracts a face region from each of a plurality of images, obtains a change characteristic of pixel values of a plurality of pixels arranged in a predetermined direction in the face region, and obtains a time series of change characteristics obtained from each of the plurality of images. Identify the movement of the subject based on the change. The determination unit determines the authenticity of the subject based on the movement of the subject.
- the authenticity of the subject can be determined using the captured image of the subject.
- the positions of the eyes and nostrils are used as facial feature points, and the person to be authenticated is made to perform an arbitrary or predetermined movement, and the facial image is genuine from the movement of the eyes and nostrils during the movement. It is determined whether or not the face is.
- facial feature points are not always correctly detectable. For example, it is difficult to accurately detect one eye when the face is largely facing left or right, the nostril when the face is facing greatly downward, and the like. Therefore, even if the person himself / herself performs the operation as instructed, the operation may not be correctly determined.
- FIG. 1 shows an example of a functional configuration of the image processing device of the embodiment.
- the image processing device 101 of FIG. 1 includes a storage unit 111, an operation specifying unit 112, and a determination unit 113.
- the storage unit 111 stores a plurality of time-series images taken of the subject when the subject is instructed to change the direction of the face.
- the operation specifying unit 112 and the determination unit 113 perform image processing using the image stored in the storage unit 111.
- FIG. 2 is a flowchart showing an example of image processing performed by the image processing device 101 of FIG.
- the motion specifying unit 112 extracts a face region from each of the plurality of images (step 201).
- the motion specifying unit 112 obtains the change characteristics of the pixel values of the plurality of pixels arranged in a predetermined direction in the face region (step 202), and is based on the time-series change of the change characteristics obtained from each of the plurality of images.
- the movement of the subject is specified (step 203).
- the determination unit 113 determines the authenticity of the subject based on the movement of the subject (step 204).
- the authenticity of the subject can be determined using the captured image of the subject.
- FIG. 3 shows a functional configuration example showing a specific example of the image processing device 101 of FIG.
- the image processing device 301 of FIG. 3 includes a storage unit 311, an image acquisition unit 312, a display unit 313, an operation instruction unit 314, an operation identification unit 315, a determination unit 316, a selection unit 317, a feature extraction unit 318, a registration unit 319, and The authentication unit 320 is included.
- the storage unit 311, the operation identification unit 315, and the determination unit 316 correspond to the storage unit 111, the operation identification unit 112, and the determination unit 113 of FIG. 1, respectively.
- the image pickup device 302 is a camera having an image pickup element such as a CCD (Charged-Coupled Device) or a CMOS (Complementary Metal-Oxide-Semiconductor), and captures an image of a subject.
- the image captured by the image pickup apparatus 302 includes a plurality of time-series images. The image at each time is sometimes called a frame.
- the image processing device 301 is, for example, a biometric authentication device, and performs biometric information processing based on the image of the person to be registered or the person to be authenticated.
- biometric information processing is the registration process for registering the biometric information of the registration target person
- the subject is the registration target person
- the biometric information processing is the authentication process for authenticating the authentication target person
- the subject is the authentication target person.
- another person makes a spoofing attack using his / her own photo
- the subject is his / her own photo.
- the operation instruction unit 314 instructs the subject to perform a specific operation such as changing the direction of the face in the registration process or the authentication process.
- the change of the face orientation includes an action of turning the face to the front toward the image pickup apparatus 302, an action of turning the face to the left or right, an action of turning the face up or down, and the like.
- the operation instruction unit 314 can instruct the subject to perform a specific operation by using a text message, an illustration, a voice message, or the like.
- the display unit 313 notifies the subject of the instruction by displaying a text message or an illustration output from the operation instruction unit 314 on the screen.
- the image pickup device 302 photographs the face of the subject while the subject is performing the instructed operation, and outputs the captured image to the image processing device 301.
- the image acquisition unit 312 acquires N time-series images (N is an integer of 2 or more) 331 from the video output by the image pickup apparatus 302 and stores them in the storage unit 311.
- the motion specifying unit 315 detects the position of the face shown in the image 331 from each image 331, extracts a rectangular face area including the face, and generates a face image which is an image of the face area. N face images are generated from N images 331. At this time, the motion specifying unit 315 detects the positions of the left and right eyes and the nose from each image 331, and creates a face image such that the positions of the left and right eyes are horizontal and the position of the nose is in the center of the face image. Generate.
- FIG. 4 shows an example of a face image generated from the image 331.
- the x-axis and the y-axis are set as coordinate axes
- the x-axis represents the direction of the short side of the face image (horizontal direction)
- the y-axis is the direction of the long side of the face image (the direction of the long side of the face image). (Vertical direction).
- the direction of the short side is the left-right direction of the face
- the direction of the long side is the vertical direction of the face.
- the nose is located on the center line 401 passing through the midpoint of the short side, and the left and right eyes are lined up on a straight line parallel to the short side.
- the face image is divided into a left side region 411 and a right side region 412 by the center line 401.
- the operation specifying unit 315 obtains the change characteristics of the pixel values of a plurality of pixels arranged in the left-right direction in each of the N face images, and the time series of the change characteristics of the pixel values obtained from the N face images. Seeking change. Further, the motion specifying unit 315 obtains the aspect ratio of each of the N face images, and obtains the time-series change of the aspect ratio obtained from the N face images.
- the motion specifying unit 315 identifies the motion of the subject by using the time-series change of the pixel value change characteristic and the time-series change of the aspect ratio, and generates the motion information 333 indicating the specified motion.
- the motion information 333 indicates an action of turning the face to the front, an action of turning the face to the left, an action of turning the face to the right, an action of turning the face upward, an action of turning the face downward, and the like.
- the determination unit 316 updates the correct answer counter 334 and the incorrect answer counter 335 using the operation information 333, and also uses the time-series change of the pixel value change characteristic and the time-series change of the aspect ratio to make the abnormality counter 336. To update.
- the correct answer counter 334, the incorrect answer counter 335, and the abnormal answer counter 336 are used when the subject is instructed to change the direction of the face multiple times.
- the correct answer counter 334 indicates the number of times that the operation indicated by the operation information 333 matches the operation instructed for the subject.
- the incorrect answer counter 335 indicates the number of times that the operation indicated by the operation information 333 does not match the operation instructed for the subject.
- the abnormality counter 336 indicates the number of times that inappropriate movement of the subject is detected. For example, an act of trying to reproduce an instructed motion by another person holding the photograph of the person and changing the direction of the photograph or deforming the photograph is detected as an inappropriate motion.
- the determination unit 316 determines the authenticity of the subject by using the count values indicated by the correct answer counter 334, the incorrect answer counter 335, and the abnormality counter 336. In the authenticity determination, it is determined whether or not the subject is genuine, that is, whether the subject is genuine or fake.
- the determination unit 316 determines that the subject is genuine when the count value of the correct answer counter 334 is larger than the predetermined value, and the subject is a fake when the count value of the incorrect answer counter 335 is larger than the predetermined value. Is determined. Then, the determination unit 316 stores the determination result 337 indicating whether the subject is genuine or fake in the storage unit 311.
- the selection unit 317 selects the image to be processed from the N face images generated from each of the N images 331. For example, as the image to be processed, a face image determined that the face is facing the front is selected.
- the feature extraction unit 318 extracts the feature information of the face shown in the image to be processed.
- the facial feature information position information indicating the position of each part of the face can be used.
- a face image in which the face is facing the front as a processing target image, feature information suitable for registration processing and authentication processing can be extracted.
- the registration unit 319 stores the extracted feature information in the storage unit 311 as the registered biometric information 338 of the registration target person.
- the authentication unit 320 authenticates the person to be authenticated by collating the extracted feature information with the registered biometric information 338.
- the face image area can use an image of a partial face area as a face image instead of an image of the entire face.
- the partial region of the face may be an region including a portion from the eyes to the chin.
- the motion specifying unit 315 can apply a predetermined image correction process to the pixels of the face image, and can obtain the change characteristic of the pixel value by using the face image to which the image correction process is applied.
- a filter process by a frequency filter, a luminance correction process by flattening a histogram, and the like are used. For example, by applying a blur filter (low-pass filter), the influence of minute parts such as moles can be reduced, and by applying a histogram flattening process, the influence of a light source can be reduced.
- the left-right symmetry of the pixel value can be used as the change characteristic of the pixel value in the left-right direction of the face image.
- the motion specifying unit 315 calculates the left-right symmetry Sym by, for example, the following equation.
- W represents the width of the face image
- H represents the height of the face image.
- I (x, y) in the formula (1) represents the luminance value at the coordinates (x, y) of the face image
- I (W-x + 1, y) bisects the face image into two equal parts. Represents the luminance value at a position symmetrical to the coordinates (x, y) with respect to the line.
- the Diff in the equation (1) represents the sum of the information on the difference between the brightness values of the two pixels existing at symmetrical positions with respect to the bisector of the face image, added to the entire face image.
- the Sym of the formula (2) becomes larger as the Diff is smaller, and becomes maximum when the face image is completely symmetrical.
- the maximum value of Sym is 1 and the minimum value is 0.
- the operation specifying unit 315 may calculate the Diff by using RGB, a color difference signal, or the like of each pixel instead of the luminance value of each pixel.
- a person's face has greater left-right symmetry when facing the front, and less left-right symmetry when facing left or right. Symmetry is maintained when the face is facing up or down. Therefore, by instructing the subject to change the direction of the face in a predetermined order and calculating Sym from the face image while the subject is performing the instructed action, the time-series change of left-right symmetry is performed. Can be calculated.
- FIG. 5 shows an example of a time-series change in left-right symmetry when the subject changes the direction of the face in the order of front, left, front, right, and front.
- the horizontal axis represents the angle of the face in the left-right direction. 0 ° represents the front, a positive value represents the left orientation when viewed from the subject, and a negative value represents the right orientation when viewed from the subject.
- the vertical axis represents the left-right symmetry Sym.
- FIG. 5A shows an example of a time-series change in left-right symmetry when the subject is a real face.
- the time-series change appears as a smooth curve, and the larger the angle toward the left or right, the smaller the left-right symmetry.
- FIG. 5B shows an example of a time-series change in left-right symmetry when the subject is a photograph and another person attempts to reproduce the real facial movement by rotating the photograph left and right.
- the generated face image is an affine transformation of the original photo, the left-right symmetry hardly changes.
- FIG. 5C shows an example of a time-series change in left-right symmetry when the subject is a photograph and another person applies a shape change such as bending when the photograph is rotated.
- the left-right symmetry is reduced by adding a shape change to the photograph.
- the motion specifying unit 315 determines that the subject has performed an motion facing left or right. For example, the motion specifying unit 315 can detect the time-series change in FIG. 5A by performing frequency analysis on the time-series change of Sym.
- the motion specifying unit 315 records the statistical value of the Sym at each angle when a plurality of unspecified persons perform the same motion, and the Sym and the statistical value calculated from the face image of the subject. By evaluating the error, the time-series change in FIG. 5A can also be detected.
- the statistical value the average value, the median value, the mode value and the like are used.
- the motion identification unit 315 uses, for example, the following method to make the face left or right. Identify if it is suitable. (A1) When the nose shown in the face image is to the left of the center position of the left and right pupils, the motion specifying unit 315 determines that the subject's face is facing right, and the nose is left and right pupils. If it is to the right of the center position of, it is determined that the subject's face is facing left.
- the operation specifying unit 315 compares the average value LV of the brightness values in the left region of the face image with the average value RV of the brightness values in the right region of the face image. Then, the motion specifying unit 315 determines that the subject's face is facing right when the LV is larger than the RV, and determines that the subject's face is facing left when the RV is larger than the LV.
- the motion specifying unit 315 obtains the change characteristics of the pixel values of a plurality of pixels arranged in directions other than the left and right, such as the vertical direction of each face image, and uses the time-series change of the change characteristics to obtain the change characteristic of the subject.
- the behavior may be specified.
- the aspect ratio of the face image represents the ratio H / W of the height H to the width W of the face image, and can be obtained by dividing the height H by the width W.
- the width W of the face image is almost the same as the face image with the face facing the front, but the height H is smaller than the face image facing the front. Therefore, by instructing the subject to change the orientation of the face in a predetermined order and calculating the aspect ratio from the face image while the subject is performing the instructed action, the aspect ratio changes in time series. Can be sought.
- FIG. 6 shows an example of a time-series change in the aspect ratio when the subject changes the direction of the face in the order of front, top, front, bottom, and front.
- the horizontal axis represents the angle of the face in the vertical direction. 0 ° represents the front, positive values represent upwards, and negative values represent downwards.
- the vertical axis represents the aspect ratio.
- the motion specifying unit 315 can detect the time-series change as shown in FIG. 6 by performing frequency analysis for the time-series change of the aspect ratio. Further, the motion specifying unit 315 records the statistical value of the aspect ratio at each angle when a plurality of unspecified persons perform the same motion, and the aspect ratio and the statistical value calculated from the face image of the subject. By evaluating the error with, the time-series change in FIG. 6 can also be detected. In this way, by using the time-series change in the aspect ratio of the face image, it is possible to detect the state in which the subject is facing upward or downward.
- the operation instructing unit 314 instructs the subject to face the front
- the operation specifying unit 315 indicates that the left-right symmetry is within the predetermined range R1 and the aspect ratio is within the predetermined range R2.
- the face is facing the front.
- the left-right symmetry and the aspect ratio at that time are stored in the storage unit 311 as the reference left-right symmetry and the reference aspect ratio, respectively.
- the motion specifying unit 315 has the left-right symmetry calculated from the face image of the person to be registered facing the front in the registration process, or the left-right symmetry calculated from the face images of a plurality of people facing the front in the registration process.
- the predetermined range R1 is determined by setting the tolerance.
- the motion specifying unit 315 refers to the aspect ratio calculated from the face image of the person to be registered facing the front in the registration process, or the aspect ratio calculated from the face images of a plurality of people facing the front in the registration process.
- the predetermined range R2 is determined by setting the tolerance.
- the operation instruction unit 314 instructs the subject to face left, right, up, or down.
- the motion specifying unit 315 calculates the difference D1 between the left-right symmetry obtained from the face image and the reference left-right symmetry, and calculates the difference D2 between the aspect ratio obtained from the face image and the reference aspect ratio. Then, the motion specifying unit 315 identifies whether the face is facing left or right based on the time-series change of the difference D1, and the face is either up or down based on the time-series change of the difference D2. Identify if you are facing.
- the left-right symmetry and aspect ratio when the face is facing the front are affected by individual differences in the position of the face part, the shooting environment, etc., but these effects are absorbed by using the difference D1 and the difference D2. , It becomes possible to accurately identify the orientation of the face.
- the operation instruction unit 314 may record the number of instructions for instructing the subject to perform an operation, and determine the authenticity of the subject based on the ratio of the count values of the correct answer counter 334 and the incorrect answer counter 335 to the number of instructions. It is possible.
- the ratio of the count value of the correct answer counter 334 to the indicated number of times represents the correct answer rate, and the ratio of the count value of the incorrect answer counter 335 to the indicated number of times represents the incorrect answer rate.
- the determination unit 316 determines that the subject is genuine when the accuracy rate is larger than a predetermined value. On the other hand, when the correct answer rate is equal to or less than the predetermined value and the incorrect answer rate is larger than the predetermined value, the determination unit 316 determines that the subject is a fake.
- the determination unit 316 can determine the sharpness of each of the N facial images, and can determine the authenticity of the subject based on the time-series change in the sharpness of those facial images.
- the sharpness of an image represents the magnitude of blurring or blurring of an image, and can be calculated using, for example, DOG (Difference of Gaussian) or the like. The smaller the blur or blur, the greater the sharpness.
- FIG. 5 (c) As shown in, sudden changes are likely to occur.
- the determination unit 316 calculates the difference between the maximum value and the minimum value for each of the left-right symmetry, aspect ratio, and sharpness of the past M facial images, and any difference is larger than the predetermined value. If so, it is determined that an inappropriate movement has been performed. M may be an integer of 2 or more and N or less. Then, the determination unit 316 increments the abnormality counter 336, and when the count value of the abnormality counter 336 exceeds the threshold value, determines that the subject is a fake. In this way, inappropriate movement can be detected by utilizing the time-series changes in the left-right symmetry, aspect ratio, and sharpness of the facial image.
- the subject may be stationary without following the instructions, or the subject may be fake and no change may appear. There is. In such a case, it is not preferable to determine that the subject is genuine.
- the determination unit 316 calculates the difference between the maximum value and the minimum value for each of the left-right symmetry, aspect ratio, and sharpness of the past M facial images, and when all the differences are smaller than the predetermined values. , Increment the stationary state detection counter. Then, when the count value of the rest state detection counter exceeds the threshold value, the determination unit 316 determines that the subject is a fake.
- the selection unit 317 selects a face image having a sharpness larger than a predetermined value from the face images determined that the face is facing the front as the processing target image. You may.
- FIG. 7 is a flowchart showing a specific example of image processing performed by the image processing device 301 of FIG.
- the operation instruction unit 314 instructs the subject to perform an operation such as changing the direction of the face (step 901)
- the image acquisition unit 312 instructs the subject to perform an operation such as changing the direction of the face (step 901). (Step 902).
- the motion specifying unit 315 generated a face image from each of the N images 331 (step 903), specified the motion of the subject using a part or all of the N face images, and specified the motion.
- the operation information 333 indicating the operation is generated (step 904).
- the determination unit 316 makes an authenticity determination using the operation information 333 (step 905).
- the determination unit 316 When the subject is genuine, the determination unit 316 generates a determination result 337 indicating that the subject is genuine, and when the subject is fake, the determination unit 316 generates a determination result 337 indicating that the subject is fake. If it is unknown whether it is genuine or fake, the determination result 337 is not generated.
- the selection unit 317 checks whether or not the determination result 337 indicates the real thing (step 906), and if the determination result 337 shows the real thing (step 906, YES), processes from N face images.
- the target image is selected (step 907).
- the feature extraction unit 318 extracts facial feature information from the selected image to be processed.
- the registration unit 319 or the authentication unit 320 performs biometric information processing (step 908).
- the biometric information processing is a registration process
- the registration unit 319 registers the extracted feature information in the storage unit 311 as the registered biometric information 338 of the subject.
- the biometric information processing is an authentication process
- the authentication unit 320 authenticates the subject by collating the extracted feature information with the registered biometric information 338.
- the operation instruction unit 314 checks whether the determination result 337 indicates a fake (step). 909). When the determination result 337 indicates a fake (step 909, YES), the operation instruction unit 314 performs error processing (step 910). In the error processing, the operation instruction unit 314 generates error information indicating that the subject is not genuine, and the display unit 313 displays the error information on the screen.
- step 909, NO the image processing device 301 repeats the processes after step 901.
- FIG. 8 is a flowchart showing an example of the operation specifying process in step 904 of FIG.
- the motion specifying unit 315 selects one face image from the N face images and calculates the left-right symmetry of the selected face image (step 1001). Then, the motion specifying unit 315 determines the direction of the face from the time-series change of the left-right symmetry (step 1002), and checks whether or not the face is facing left or right (step 1003). When the face is facing left or right (step 1003, YES), the motion specifying unit 315 generates motion information 333 indicating the motion of turning the face to the left or right (step 1010).
- the motion specifying unit 315 calculates the aspect ratio of the selected face image (step 1004). Then, the motion specifying unit 315 determines the direction of the face from the time-series change of the aspect ratio (step 1005), and checks whether or not the face is facing up or down (step 1006). When the face is facing up or down (steps 1006, YES), the motion specifying unit 315 generates motion information 333 indicating the motion of turning the face up or down (step 1010).
- the motion specifying unit 315 determines the direction of the face from the time-series changes in the left-right symmetry and the aspect ratio (step 1007), and the face faces the front. Check whether or not (step 1008).
- the motion specifying unit 315 generates motion information 333 indicating the motion of facing the front (step 1010).
- the motion specifying unit 315 checks whether or not the selected face image is the last face image (step 1009). When an unselected face image remains (step 1009, NO), the motion specifying unit 315 repeats the processes from step 1001 onward for the next face image. Then, when the selected face image is the last face image (step 1009, YES), the motion specifying unit 315 ends the process.
- FIG. 9 is a flowchart showing an example of the authenticity determination process in step 905 of FIG.
- the determination unit 316 obtains the sharpness of each of the past M face images, and calculates the difference between the maximum value and the minimum value for each of the left-right symmetry, aspect ratio, and sharpness of those face images. .. Then, the determination unit 316 determines whether or not the subject has made an inappropriate movement based on the calculated difference (step 1101).
- the determination unit 316 checks whether or not the movement of the subject indicated by the operation information 333 is as instructed by the operation instruction unit 314 (step). 1102). When the operation of the subject is as instructed (step 1102, YES), the determination unit 316 increments the correct answer counter 334 by 1 (step 1103). On the other hand, when the movement of the subject is not as instructed (step 1102, NO), the determination unit 316 increments the incorrect answer counter 335 by 1 (step 1104).
- the determination unit 316 compares the count value of the correct answer counter 334 with the threshold value TH1 (step 1105). When the count value of the correct answer counter 334 is larger than TH1 (step 1105, YES), the determination unit 316 determines that the subject is genuine and generates a determination result 337 indicating that the subject is genuine (step 1107). ).
- the determination unit 316 compares the count value of the incorrect answer counter 335 with the threshold value TH2 (step 1106). When the count value of the incorrect answer counter 335 is larger than TH2 (step 1106, YES), the determination unit 316 determines that the subject is a fake, and generates a determination result 337 indicating that the subject is a fake (step 1106, YES). 1108).
- step 1106, NO the determination unit 316 ends the process.
- the determination unit 316 increments the abnormality counter 336 by 1 (step 1109), and compares the count value of the abnormality counter 336 with the threshold value TH3 (step 1110). ). When the count value of the abnormality counter 336 is larger than TH3 (step 1110, YES), the determination unit 316 determines that the subject is a fake, and generates a determination result 337 indicating that the subject is a fake (step 1111). ).
- the determination unit 316 ends the process.
- the determination unit 316 is a subject that matches the instructed face orientation change from the image 331 taken within a predetermined time after the operation instruction unit 314 instructs the subject to change the face orientation. If the operation of is not specified, it is determined that the subject is a fake.
- the configuration of the image processing device 101 of FIG. 1 and the image processing device 301 of FIG. 3 is only an example, and some components may be omitted or changed depending on the use or conditions of the image processing device.
- the image processing device 301 of FIG. 3 when N images 331 of the time series are stored in the storage unit 311 in advance, the image acquisition unit 312, the display unit 313, and the operation instruction unit 314 are omitted. be able to.
- the selection unit 317, the feature extraction unit 318, the registration unit 319, and the authentication unit 320 can be omitted.
- the image processing device 301 may perform another information processing using the face image instead of performing the biometric information processing using the face image.
- FIGS. 2 and 7 to 9 are merely examples, and some processing may be omitted or changed depending on the configuration or conditions of the image processing device.
- the processing of steps 901 and 902 can be omitted.
- steps 907 and 908 can be omitted.
- the image processing device 301 may perform another information processing instead of the biometric information processing.
- step 1101 and steps 1109 to 1111 can be omitted.
- step 1104, step 1106, and step 1108 can be omitted.
- Equations (1) and (2) are merely examples, and the left-right symmetry of the face image may be calculated using another calculation equation.
- FIG. 10 shows a configuration example of an information processing device (computer) used as the image processing device 101 of FIG. 1 and the image processing device 301 of FIG.
- the information processing device of FIG. 10 includes a CPU (Central Processing Unit) 1201, a memory 1202, an input device 1203, an output device 1204, an auxiliary storage device 1205, a medium drive device 1206, and a network connection device 1207. These components are connected to each other by bus 1208.
- the imaging device 302 of FIG. 3 may be connected to bus 1208.
- the memory 1202 is, for example, a semiconductor memory such as a ROM (ReadOnlyMemory), a RAM (RandomAccessMemory), or a flash memory, and stores a program and data used for processing.
- the memory 1202 can be used as the storage unit 111 of FIG. 1 or the storage unit 311 of FIG.
- the CPU 1201 (processor) operates as the operation specifying unit 112 and the determination unit 113 in FIG. 1 by executing a program using, for example, the memory 1202.
- the CPU 1201 executes an image acquisition unit 312, an operation instruction unit 314, an operation identification unit 315, a determination unit 316, a selection unit 317, a feature extraction unit 318, and a registration unit 319 in FIG. , And also operates as the authentication unit 320.
- the input device 1203 is, for example, a keyboard, a pointing device, or the like, and is used for inputting instructions or information from an operator or a user.
- the output device 1204 is, for example, a display device, a printer, a speaker, or the like, and is used for inquiring or instructing an operator or a user and outputting a processing result.
- the instruction to the operator or the user may be an operation instruction to the subject, and the processing result may be the determination result 337.
- the output device 1204 can be used as the display unit 313 of FIG.
- the auxiliary storage device 1205 is, for example, a magnetic disk device, an optical disk device, a magneto-optical disk device, a tape device, or the like.
- the auxiliary storage device 1205 may be a hard disk drive or a flash memory.
- the information processing device can store programs and data in the auxiliary storage device 1205 and load them into the memory 1202 for use.
- the auxiliary storage device 1205 can be used as the storage unit 111 of FIG. 1 or the storage unit 311 of FIG.
- the medium drive device 1206 drives the portable recording medium 1209 and accesses the recorded contents.
- the portable recording medium 1209 is a memory device, a flexible disk, an optical disk, a magneto-optical disk, or the like.
- the portable recording medium 1209 may be a CD-ROM (CompactDiskReadOnlyMemory), a DVD (DigitalVersatileDisk), a USB (UniversalSerialBus) memory, or the like.
- the operator or the user can store the programs and data in the portable recording medium 1209 and load them into the memory 1202 for use.
- the computer-readable recording medium that stores the programs and data used for processing is physical (non-temporary) recording such as memory 1202, auxiliary storage device 1205, or portable recording medium 1209. It is a medium.
- the network connection device 1207 is a communication interface circuit that is connected to a communication network such as LAN (Local Area Network) or WAN (Wide Area Network) and performs data conversion associated with communication.
- the information processing device can receive programs and data from an external device via the network connection device 1207, load them into the memory 1202, and use them.
- the information processing device does not have to include all the components of FIG. 10, and some components may be omitted depending on the application or conditions. For example, if an interface with an operator or a user is not required, the input device 1203 and the output device 1204 may be omitted. When the portable recording medium 1209 or the communication network is not used, the medium driving device 1206 or the network connecting device 1207 may be omitted.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Collating Specific Patterns (AREA)
- Image Analysis (AREA)
Abstract
Description
特許文献1の技術では、顔特徴点として目、口、及び鼻の位置が用いられ、顔画像の登録時に、登録対象者に所定の顔の動作を行わせ、そのときの目、口、及び鼻の動きが登録される。そして、認証時に、認証対象者に同じ動作を行わせ、そのときの目、口、及び鼻の動きから、顔画像が本物の顔であるか否かが判定される。
(A1)動作特定部315は、顔画像に写っている鼻が、左右の瞳の中央の位置よりも左にある場合、被写体の顔が右を向いていると判定し、鼻が左右の瞳の中央の位置よりも右にある場合、被写体の顔が左を向いていると判定する。
(A2)動作特定部315は、顔画像の左側領域の輝度値の平均値LVと、顔画像の右側領域の輝度値の平均値RVとを比較する。そして、動作特定部315は、LVがRVよりも大きい場合、被写体の顔が右を向いていると判定し、RVがLVよりも大きい場合、被写体の顔が左を向いていると判定する。
Claims (14)
- 被写体に対して顔の向きの変更が指示された際に前記被写体を撮影した、時系列の複数の画像を記憶する記憶部と、
前記複数の画像それぞれから顔領域を抽出し、前記顔領域において所定方向に並んでいる複数の画素の画素値の変化特性を求め、前記複数の画像それぞれから求められた変化特性の時系列変化に基づいて、前記被写体の動作を特定する動作特定部と、
前記被写体の動作に基づいて、前記被写体の真正性を判定する判定部と、
を備えることを特徴とする画像処理装置。 - 前記被写体に対して指示された前記顔の向きの変更は、前記顔を左又は右に向ける動作を表し、
前記所定方向は前記顔の左右の方向であり、
前記所定方向に並んでいる複数の画素の画素値の変化特性は、前記複数の画素の画素値の左右対称性を表し、
前記被写体の動作は、前記被写体が前記顔を左又は右に向ける動作であることを特徴とする請求項1記載の画像処理装置。 - 前記動作特定部は、前記顔領域の画素に対して画像補正処理を適用し、前記画像補正処理が適用された顔領域から、前記複数の画素の画素値の変化特性を求めることを特徴とする請求項1又は2記載の画像処理装置。
- 前記動作特定部は、前記顔領域のアスペクト比をさらに求め、前記複数の画像それぞれから求められたアスペクト比の時系列変化に基づいて、前記被写体の動作を特定することを特徴とする請求項1乃至3のいずれか1項に記載の画像処理装置。
- 前記動作特定部は、前記顔領域のアスペクト比をさらに求め、前記左右対称性が所定範囲内であり、かつ、前記アスペクト比が所定範囲内である場合に、前記被写体を撮影した撮像装置に対して前記顔が正面を向いていると判定し、前記顔が正面を向いていると判定されたときの左右対称性及びアスペクト比を、基準左右対称性及び基準アスペクト比として前記記憶部にそれぞれ格納し、前記基準左右対称性及び前記基準アスペクト比が前記記憶部に格納された後に求められた左右対称性と、前記基準左右対称性との差分の時系列変化に基づいて、前記顔が左又は右のいずれを向いているかを特定することを特徴とする請求項2記載の画像処理装置。
- 前記動作特定部は、前記基準左右対称性及び前記基準アスペクト比が前記記憶部に格納された後に求められたアスペクト比と、前記基準アスペクト比との差分の時系列変化に基づいて、前記顔が上又は下のいずれを向いているかを特定することを特徴とする請求項5記載の画像処理装置。
- 前記複数の画像それぞれから抽出された顔領域のうち、前記顔が正面を向いていると判定された顔領域の画像を、登録対象又は認証対象の顔画像として選択する選択部をさらに備えることを特徴とする請求項5又は6記載の画像処理装置。
- 前記判定部は、前記被写体に対して前記顔の向きの変更が複数回指示され、かつ、前記動作特定部によって特定された前記被写体の動作が前記被写体に対して指示された前記顔の向きの変更と一致した回数が、所定値よりも大きい場合、前記被写体は真正であると判定することを特徴とする請求項1乃至7のいずれか1項に記載の画像処理装置。
- 前記判定部は、前記被写体に対して前記顔の向きの変更が指示された後、所定時間内に撮影された画像から、前記顔の向きの変更と一致する被写体の動作が特定されない場合、前記被写体は真正ではないと判定することを特徴とする請求項1乃至8のいずれか1項に記載の画像処理装置。
- 前記判定部は、前記顔領域の鮮明性を求め、前記複数の画像それぞれから求められた鮮明性の時系列変化に基づいて、前記被写体の真正性を判定することを特徴とする請求項1乃至9のいずれか1項に記載の画像処理装置。
- コンピュータによって実行される画像処理方法であって、
前記コンピュータが、
被写体に対して顔の向きの変更が指示された際に前記被写体を撮影した、時系列の複数の画像それぞれから、顔領域を抽出し、
前記顔領域において所定方向に並んでいる複数の画素の画素値の変化特性を求め、
前記複数の画像それぞれから求められた変化特性の時系列変化に基づいて、前記被写体の動作を特定し、
前記被写体の動作に基づいて、前記被写体の真正性を判定する、
ことを特徴とする画像処理方法。 - 前記被写体に対して指示された前記顔の向きの変更は、前記顔を左又は右に向ける動作を表し、
前記所定方向は前記顔の左右の方向であり、
前記所定方向に並んでいる複数の画素の画素値の変化特性は、前記複数の画素の画素値の左右対称性を表し、
前記被写体の動作は、前記被写体が前記顔を左又は右に向ける動作であることを特徴とする請求項11記載の画像処理方法。 - 被写体に対して顔の向きの変更が指示された際に前記被写体を撮影した、時系列の複数の画像それぞれから、顔領域を抽出し、
前記顔領域において所定方向に並んでいる複数の画素の画素値の変化特性を求め、
前記複数の画像それぞれから求められた変化特性の時系列変化に基づいて、前記被写体の動作を特定し、
前記被写体の動作に基づいて、前記被写体の真正性を判定する、
処理をコンピュータに実行させるための画像処理プログラム。 - 前記被写体に対して指示された前記顔の向きの変更は、前記顔を左又は右に向ける動作を表し、
前記所定方向は前記顔の左右の方向であり、
前記所定方向に並んでいる複数の画素の画素値の変化特性は、前記複数の画素の画素値の左右対称性を表し、
前記被写体の動作は、前記被写体が前記顔を左又は右に向ける動作であることを特徴とする請求項13記載の画像処理プログラム。
Priority Applications (6)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2021514780A JP7268725B2 (ja) | 2019-04-19 | 2019-04-19 | 画像処理装置、画像処理方法、及び画像処理プログラム |
KR1020217032248A KR20210136092A (ko) | 2019-04-19 | 2019-04-19 | 화상 처리 장치, 화상 처리 방법 및 화상 처리 프로그램 |
PCT/JP2019/016869 WO2020213166A1 (ja) | 2019-04-19 | 2019-04-19 | 画像処理装置、画像処理方法、及び画像処理プログラム |
EP19925334.5A EP3958208A4 (en) | 2019-04-19 | 2019-04-19 | IMAGE PROCESSING DEVICE, IMAGE PROCESSING METHOD AND IMAGE PROCESSING PROGRAM |
CN201980095279.7A CN113678164A (zh) | 2019-04-19 | 2019-04-19 | 图像处理装置、图像处理方法以及图像处理程序 |
US17/478,477 US12033429B2 (en) | 2019-04-19 | 2021-09-17 | Image processing device of determining authenticity of object, image processing method of determining authenticity of object, and storage medium storing program of determining authenticity of object |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2019/016869 WO2020213166A1 (ja) | 2019-04-19 | 2019-04-19 | 画像処理装置、画像処理方法、及び画像処理プログラム |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US17/478,477 Continuation US12033429B2 (en) | 2019-04-19 | 2021-09-17 | Image processing device of determining authenticity of object, image processing method of determining authenticity of object, and storage medium storing program of determining authenticity of object |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2020213166A1 true WO2020213166A1 (ja) | 2020-10-22 |
Family
ID=72837237
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2019/016869 WO2020213166A1 (ja) | 2019-04-19 | 2019-04-19 | 画像処理装置、画像処理方法、及び画像処理プログラム |
Country Status (6)
Country | Link |
---|---|
US (1) | US12033429B2 (ja) |
EP (1) | EP3958208A4 (ja) |
JP (1) | JP7268725B2 (ja) |
KR (1) | KR20210136092A (ja) |
CN (1) | CN113678164A (ja) |
WO (1) | WO2020213166A1 (ja) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP7033228B1 (ja) | 2021-07-14 | 2022-03-09 | 日本コンピュータビジョン株式会社 | 認証システム、認証方法および認証プログラム |
WO2023144929A1 (ja) * | 2022-01-26 | 2023-08-03 | 日本電気株式会社 | 認証システム、認証装置、認証方法、およびプログラム |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20210295504A1 (en) * | 2020-03-19 | 2021-09-23 | Unitedhealth Group Incorporated | Systems and methods for automated digital image content extraction and analysis |
JP7457991B1 (ja) * | 2023-03-14 | 2024-03-29 | 有限会社バラエティーエム・ワン | なりすまし検知システムおよびなりすまし検知プログラム |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH11339048A (ja) * | 1998-05-29 | 1999-12-10 | Omron Corp | 個人識別装置、個人識別方法および個人識別プログラムを記録した記録媒体 |
JP2003099763A (ja) | 2001-05-25 | 2003-04-04 | Toshiba Corp | 顔画像記録装置、情報管理システム、顔画像記録方法、及び情報管理方法 |
JP2006235718A (ja) * | 2005-02-22 | 2006-09-07 | Nec Corp | 顔認証装置、その顔認証方法、その顔認証装置を組み込んだ電子機器およびその顔認証プログラムを記録した記録媒体 |
JP2008071179A (ja) | 2006-09-14 | 2008-03-27 | Toshiba Corp | 顔照合装置、通行制御装置、顔照合方法、および、通行制御方法 |
JP2015041307A (ja) * | 2013-08-23 | 2015-03-02 | 日本電気株式会社 | 照合装置及び照合方法、照合システム、並びにコンピュータ・プログラム |
JP2016173813A (ja) * | 2015-03-16 | 2016-09-29 | 株式会社リコー | 情報処理装置、情報処理システム、認証方法、及びプログラム |
WO2019017080A1 (ja) * | 2017-07-20 | 2019-01-24 | パナソニックIpマネジメント株式会社 | 照合装置及び照合方法 |
Family Cites Families (41)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2003150963A (ja) | 2001-11-13 | 2003-05-23 | Japan Science & Technology Corp | 顔画像認識方法及び顔画像認識装置 |
KR100608595B1 (ko) * | 2004-11-16 | 2006-08-03 | 삼성전자주식회사 | 얼굴 인식 방법 및 장치 |
JP2010267257A (ja) | 2009-04-16 | 2010-11-25 | Panasonic Corp | 画像処理装置、画像処理方法及び画像処理プログラム |
US9202105B1 (en) * | 2012-01-13 | 2015-12-01 | Amazon Technologies, Inc. | Image analysis for user authentication |
US8542879B1 (en) * | 2012-06-26 | 2013-09-24 | Google Inc. | Facial recognition |
US10129251B1 (en) * | 2014-02-11 | 2018-11-13 | Morphotrust Usa, Llc | System and method for verifying liveliness |
US20160057138A1 (en) * | 2014-03-07 | 2016-02-25 | Hoyos Labs Ip Ltd. | System and method for determining liveness |
US11256792B2 (en) * | 2014-08-28 | 2022-02-22 | Facetec, Inc. | Method and apparatus for creation and use of digital identification |
US9767358B2 (en) * | 2014-10-22 | 2017-09-19 | Veridium Ip Limited | Systems and methods for performing iris identification and verification using mobile devices |
US10331291B1 (en) * | 2014-12-31 | 2019-06-25 | Morpho Trust USA, LLC | Visual verification of digital identifications |
CN105893920B (zh) * | 2015-01-26 | 2019-12-27 | 阿里巴巴集团控股有限公司 | 一种人脸活体检测方法和装置 |
US10339362B2 (en) * | 2016-12-08 | 2019-07-02 | Veridium Ip Limited | Systems and methods for performing fingerprint based user authentication using imagery captured using mobile devices |
CN106960177A (zh) * | 2015-02-15 | 2017-07-18 | 北京旷视科技有限公司 | 活体人脸验证方法及系统、活体人脸验证装置 |
US10079827B2 (en) * | 2015-03-16 | 2018-09-18 | Ricoh Company, Ltd. | Information processing apparatus, information processing method, and information processing system |
US9852543B2 (en) * | 2015-03-27 | 2017-12-26 | Snap Inc. | Automated three dimensional model generation |
US9922238B2 (en) * | 2015-06-25 | 2018-03-20 | West Virginia University | Apparatuses, systems, and methods for confirming identity |
US9898674B2 (en) * | 2015-12-10 | 2018-02-20 | International Business Machines Corporation | Spoof detection for facial recognition |
CN106897658B (zh) * | 2015-12-18 | 2021-12-14 | 腾讯科技(深圳)有限公司 | 人脸活体的鉴别方法和装置 |
US9619723B1 (en) * | 2016-02-17 | 2017-04-11 | Hong Kong Applied Science and Technology Research Institute Company Limited | Method and system of identification and authentication using facial expression |
US10698998B1 (en) * | 2016-03-04 | 2020-06-30 | Jpmorgan Chase Bank, N.A. | Systems and methods for biometric authentication with liveness detection |
US10956544B1 (en) * | 2016-04-01 | 2021-03-23 | Massachusetts Mutual Life Insurance Company | Access control through head imaging and biometric authentication |
US10084776B2 (en) * | 2016-04-04 | 2018-09-25 | Daon Holdings Limited | Methods and systems for authenticating users |
US10157323B2 (en) * | 2016-08-30 | 2018-12-18 | Qualcomm Incorporated | Device to provide a spoofing or no spoofing indication |
US10282530B2 (en) * | 2016-10-03 | 2019-05-07 | Microsoft Technology Licensing, Llc | Verifying identity based on facial dynamics |
JP6897082B2 (ja) * | 2016-12-13 | 2021-06-30 | 富士通株式会社 | 顔向き推定用コンピュータプログラム、顔向き推定装置及び顔向き推定方法 |
US10764281B1 (en) * | 2017-01-09 | 2020-09-01 | United Services Automobile Association (Usaa) | Systems and methods for authenticating a user using an image capture device |
WO2018225642A1 (ja) * | 2017-06-05 | 2018-12-13 | 日本電気株式会社 | 顔認証システム、顔認証方法、生体認証システム、生体認証方法及び記録媒体 |
US10579783B1 (en) * | 2017-07-31 | 2020-03-03 | Square, Inc. | Identity authentication verification |
EP4156129A1 (en) * | 2017-09-09 | 2023-03-29 | Apple Inc. | Implementation of biometric enrollment |
DE102017216837A1 (de) * | 2017-09-22 | 2019-03-28 | Audi Ag | Gestik- und Mimiksteuerung für ein Fahrzeug |
WO2019056310A1 (en) * | 2017-09-22 | 2019-03-28 | Qualcomm Incorporated | SYSTEMS AND METHODS FOR DETECTING FACIAL ACTIVITY |
US10606994B2 (en) * | 2017-11-16 | 2020-03-31 | Bank Of America Corporation | Authenticating access to a computing resource using quorum-based facial recognition |
US10728241B2 (en) * | 2018-01-26 | 2020-07-28 | Jumio Corporation | Triage engine for document authentication |
US10963681B2 (en) * | 2018-01-30 | 2021-03-30 | Alarm.Com Incorporated | Face concealment detection |
CN109260593B (zh) * | 2018-09-27 | 2020-09-08 | 武汉资联虹康科技股份有限公司 | 一种经颅磁刺激治疗方法及设备 |
CN109492551B (zh) * | 2018-10-25 | 2023-03-24 | 腾讯科技(深圳)有限公司 | 活体检测方法、装置及应用活体检测方法的相关系统 |
CN109492550B (zh) | 2018-10-25 | 2023-06-06 | 腾讯科技(深圳)有限公司 | 活体检测方法、装置及应用活体检测方法的相关系统 |
SG11202104685WA (en) * | 2018-11-05 | 2021-06-29 | Nec Corp | Information processing apparatus, information processing method, and storage medium |
US11138302B2 (en) * | 2019-02-27 | 2021-10-05 | International Business Machines Corporation | Access control using multi-authentication factors |
US10977355B2 (en) * | 2019-09-11 | 2021-04-13 | Lg Electronics Inc. | Authentication method and device through face recognition |
US20210397945A1 (en) * | 2020-06-18 | 2021-12-23 | Nvidia Corporation | Deep hierarchical variational autoencoder |
-
2019
- 2019-04-19 EP EP19925334.5A patent/EP3958208A4/en active Pending
- 2019-04-19 WO PCT/JP2019/016869 patent/WO2020213166A1/ja active Application Filing
- 2019-04-19 CN CN201980095279.7A patent/CN113678164A/zh active Pending
- 2019-04-19 KR KR1020217032248A patent/KR20210136092A/ko not_active Application Discontinuation
- 2019-04-19 JP JP2021514780A patent/JP7268725B2/ja active Active
-
2021
- 2021-09-17 US US17/478,477 patent/US12033429B2/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH11339048A (ja) * | 1998-05-29 | 1999-12-10 | Omron Corp | 個人識別装置、個人識別方法および個人識別プログラムを記録した記録媒体 |
JP2003099763A (ja) | 2001-05-25 | 2003-04-04 | Toshiba Corp | 顔画像記録装置、情報管理システム、顔画像記録方法、及び情報管理方法 |
JP2006235718A (ja) * | 2005-02-22 | 2006-09-07 | Nec Corp | 顔認証装置、その顔認証方法、その顔認証装置を組み込んだ電子機器およびその顔認証プログラムを記録した記録媒体 |
JP2008071179A (ja) | 2006-09-14 | 2008-03-27 | Toshiba Corp | 顔照合装置、通行制御装置、顔照合方法、および、通行制御方法 |
JP2015041307A (ja) * | 2013-08-23 | 2015-03-02 | 日本電気株式会社 | 照合装置及び照合方法、照合システム、並びにコンピュータ・プログラム |
JP2016173813A (ja) * | 2015-03-16 | 2016-09-29 | 株式会社リコー | 情報処理装置、情報処理システム、認証方法、及びプログラム |
WO2019017080A1 (ja) * | 2017-07-20 | 2019-01-24 | パナソニックIpマネジメント株式会社 | 照合装置及び照合方法 |
Non-Patent Citations (2)
Title |
---|
MOTOO YAMAMOTO, TAKAYOSHI YAMASHITA, MASATO KAWADE: "A method of anti-imposter for face recognition using user interaction", INTERACTION 2007, PAPERS; MARCH 15TH - 16TH, 2007, 2 July 2013 (2013-07-02) - 16 March 2007 (2007-03-16), JP, pages 1 - 2, XP009530419 * |
See also references of EP3958208A4 |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP7033228B1 (ja) | 2021-07-14 | 2022-03-09 | 日本コンピュータビジョン株式会社 | 認証システム、認証方法および認証プログラム |
JP2023012581A (ja) * | 2021-07-14 | 2023-01-26 | 日本コンピュータビジョン株式会社 | 認証システム、認証方法および認証プログラム |
WO2023144929A1 (ja) * | 2022-01-26 | 2023-08-03 | 日本電気株式会社 | 認証システム、認証装置、認証方法、およびプログラム |
Also Published As
Publication number | Publication date |
---|---|
US12033429B2 (en) | 2024-07-09 |
CN113678164A (zh) | 2021-11-19 |
EP3958208A4 (en) | 2022-04-20 |
JP7268725B2 (ja) | 2023-05-08 |
JPWO2020213166A1 (ja) | 2021-11-04 |
KR20210136092A (ko) | 2021-11-16 |
EP3958208A1 (en) | 2022-02-23 |
US20220019771A1 (en) | 2022-01-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2020213166A1 (ja) | 画像処理装置、画像処理方法、及び画像処理プログラム | |
EP2580711B1 (en) | Distinguishing live faces from flat surfaces | |
US8515136B2 (en) | Image processing device, image device, image processing method | |
CN108549886A (zh) | 一种人脸活体检测方法及装置 | |
KR20170006355A (ko) | 모션벡터 및 특징벡터 기반 위조 얼굴 검출 방법 및 장치 | |
WO2010137157A1 (ja) | 画像処理装置、方法、プログラム | |
JP5170094B2 (ja) | なりすまし検知システム、なりすまし検知方法およびなりすまし検知用プログラム | |
WO2006051607A1 (ja) | 顔特徴点検出装置、特徴点検出装置 | |
US11315360B2 (en) | Live facial recognition system and method | |
JP6822482B2 (ja) | 視線推定装置、視線推定方法及びプログラム記録媒体 | |
CN107798279A (zh) | 一种人脸活体检测方法及装置 | |
WO2019003973A1 (ja) | 顔認証装置、顔認証方法およびプログラム記録媒体 | |
CN107944395B (zh) | 一种基于神经网络验证人证合一的方法及系统 | |
JP6025557B2 (ja) | 画像認識装置、その制御方法及びプログラム | |
CN109087429B (zh) | 基于人脸识别技术的图书馆借书证人证一致性检验的方法 | |
WO2019078310A1 (ja) | 顔三次元形状推定装置、顔三次元形状推定方法、及び、非一時的なコンピュータ可読媒体 | |
JP6098133B2 (ja) | 顔構成部抽出装置、顔構成部抽出方法及びプログラム | |
JP2011159030A (ja) | 被写体認証装置、被写体認証方法及びプログラム | |
JP5048691B2 (ja) | 画像認識方法およびその装置 | |
WO2017114285A1 (zh) | 眼球识别方法及系统 | |
JP2005084979A (ja) | 顔認証システムおよび方法並びにプログラム | |
JP4446383B2 (ja) | 画像処理装置および画像認識装置 | |
JP2021043914A (ja) | 画像処理装置、画像処理方法、及び画像処理プログラム | |
JP7457991B1 (ja) | なりすまし検知システムおよびなりすまし検知プログラム | |
JP7103443B2 (ja) | 情報処理装置、情報処理方法、およびプログラム |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 19925334 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2021514780 Country of ref document: JP Kind code of ref document: A |
|
ENP | Entry into the national phase |
Ref document number: 20217032248 Country of ref document: KR Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2019925334 Country of ref document: EP |