CN110414346A - Biopsy method, device, electronic equipment and storage medium - Google Patents
Biopsy method, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN110414346A CN110414346A CN201910557266.9A CN201910557266A CN110414346A CN 110414346 A CN110414346 A CN 110414346A CN 201910557266 A CN201910557266 A CN 201910557266A CN 110414346 A CN110414346 A CN 110414346A
- Authority
- CN
- China
- Prior art keywords
- rgb
- sequence
- value
- color
- face
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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
- G06V40/40—Spoof detection, e.g. liveness detection
- G06V40/45—Detection of the body part being alive
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The present invention provides a kind of biopsy method, device, electronic equipment and storage mediums, this method comprises: generating RGB sequence, RGB sequence includes at least two rgb values;Screen is sequentially controlled according to prefixed time interval and shows the corresponding color of rgb value in RGB sequence, so that the optical pulse irradiation of the RGB sequence corresponding color is to face, and using the face as target recorded video stream;It determines image corresponding with the rgb value that color has been displayed in video flowing, and determines the corresponding RGB detected value of human face region of image, obtain RGB detection sequence;According to the RGB display sequence of RGB detection sequence and the rgb value composition that color has been displayed, In vivo detection result is determined.The present invention can detect in time when there are living body attack due to being detected by light pulse, improve the accuracy of In vivo detection, realize offline inspection, shorten detection time.
Description
Technical field
The present invention relates to In vivo detection fields, more particularly to a kind of biopsy method, device, electronic equipment and storage
Medium.
Background technique
In the prior art, In vivo detection scheme is mostly the movement obtained according to camera or static video to judge.
The prior art excessively relies on the information of camera service feedback, and in the silent In vivo detection stage, currently existing scheme is to detect face
Afterwards, one section of video is recorded, is then matched with ID card information.
There is the risk that mobile phone camera is held as a hostage in practical applications, hacker passes through replacement single frames or multi-frame video,
It realizes the behaviors such as prosthese replacement, virtual video attack, at this moment can still detect and pass through, cause False Rate very high.Mostly attack
It hits detection all to be completed by server, that is, after needing to wait user to record, video upload server, server passes through
Huge algorithm model detect whether being attack, after detecting attack, return again to mobile phone terminal, among this by
It is very long to will lead to the time in network cause, user, which needs to wait, for a long time just will appreciate that final result, seriously affect the experience of user.
Summary of the invention
In view of the above problems, the embodiment of the present invention is proposed in order to provide overcoming the above problem or at least being partially solved
A kind of biopsy method, device, electronic equipment and the storage medium of the above problem.
According to an embodiment of the present invention in a first aspect, providing a kind of biopsy method, comprising:
RGB sequence is generated, the RGB sequence includes at least two rgb values;
Screen is sequentially controlled according to prefixed time interval and shows the corresponding color of rgb value in the RGB sequence, so that described
The optical pulse irradiation of RGB sequence corresponding color is to face, and using the face as target recorded video stream;
It determines image corresponding with the rgb value that color has been displayed in the video flowing, and determines the face in described image
The corresponding RGB detected value in region, obtains RGB detection sequence;
According to the RGB display sequence of the RGB detection sequence and the rgb value composition that color has been displayed, In vivo detection is determined
As a result.
Optionally, it is described according to the RGB detection sequence and it is described color has been displayed rgb value composition RGB show sequence
Column, determine In vivo detection result, comprising:
Determine the matching degree of the RGB detection sequence and the RGB display sequence;
If the matching degree is greater than or equal to preset threshold, it is determined that In vivo detection result is that detection passes through;
If the matching degree is less than the preset threshold, it is determined that In vivo detection result is that there are living body attacks.
Optionally, the matching degree of the determination RGB detection sequence and the RGB display sequence, comprising:
Calculate separately the similarity of the rgb value in the RGB detected value and RGB display sequence in the RGB detection sequence;
Matching degree to the similarity averaged, as the RGB detection sequence and the RGB display sequence.
Optionally, screen is sequentially controlled according to prefixed time interval described and shows that the rgb value in the RGB sequence is corresponding
Color before, further includes:
Screen intensity is adjusted in preset range.
Optionally, screen is sequentially controlled according to prefixed time interval described and shows that the rgb value in the RGB sequence is corresponding
Color before, further includes:
Face is obtained at a distance from screen, and determines the distance within the scope of pre-determined distance;And/or
The ambient light intensity of ambient enviroment is obtained, and determines the ambient light intensity in default range of light intensities.
Optionally, further includes:
If the distance not within the scope of the pre-determined distance, prompts user to adjust face at a distance from screen;And/or
If the ambient light intensity not in the default range of light intensities, prompts user to adjust position.
Optionally, the In vivo detection interface in the screen includes background area and Face datection frame region;
The screen that sequentially controls according to prefixed time interval shows the corresponding color of rgb value in the RGB sequence, comprising:
The background area is sequentially controlled according to prefixed time interval shows the corresponding color of rgb value in the RGB sequence;
And/or
The first painting canvas that the Face datection frame region is sequentially controlled according to prefixed time interval is shown in the RGB sequence
Second painting canvas of the corresponding color of rgb value, the Face datection frame region shows face preview image;First painting canvas is with pre-
If transparency is superimposed upon on second painting canvas.
Optionally, using the face as target recorded video stream, comprising:
Using the face as target recorded video stream, and control continuous frame number corresponding with a rgb value in the video flowing of recording
To preset frame number.
Optionally, the RGB display sequence according to the RGB detection sequence and the rgb value composition that color has been displayed, really
Determine In vivo detection result, comprising:
When the quantity for the rgb value that color has been displayed in the RGB sequence reaches specified number, according to the RGB detection sequence
With the RGB display sequence, In vivo detection result is determined.
Optionally, the corresponding RGB detected value of human face region in the determining described image, obtains RGB detection sequence, packet
It includes:
According to sequence of the rgb value of color in RGB sequence has been displayed, current rgb value is determined, and will be with the current rgb value
Corresponding image is as currently processed image;
It determines the human face region in the currently processed image, and obtains the pixel value of each pixel in the human face region;
The average value for determining the pixel value in the human face region, the RGB detected value as the currently processed image;
It continues to execute the currently processed image of above-mentioned determination and determines the operation of the RGB detected value of currently processed image, until obtaining
The RGB detected value of each rgb value correspondence image of color has been displayed, the RGB detected value forms RGB detection sequence.
Optionally, two neighboring rgb value is different in the RGB sequence.
Second aspect according to an embodiment of the present invention provides a kind of living body detection device, comprising:
RGB sequence generating module, for generating RGB sequence, the RGB sequence includes at least two rgb values;
Light pulse control module shows rgb value pair in the RGB sequence for sequentially controlling screen according to prefixed time interval
The color answered, so that the optical pulse irradiation of the RGB sequence corresponding color is to face, and using the face as target recorded video
Stream;
Color value detection module for determining image corresponding with the rgb value that color has been displayed in the video flowing, and determines
The corresponding RGB detected value of human face region in described image, obtains RGB detection sequence;
Judgment module is attacked in light pulse, for what is formed according to the RGB detection sequence and the rgb value that color has been displayed
RGB display sequence determines In vivo detection result.
Optionally, the light pulse attack judgment module includes:
Matching unit, for determining the matching degree of the RGB detection sequence and the RGB display sequence;
Detection is by determination unit, if being greater than or equal to preset threshold for the matching degree, it is determined that In vivo detection result is
Detection passes through;
Living body attacks determination unit, if being less than the preset threshold for the matching degree, it is determined that In vivo detection result is to deposit
In living body attack.
Optionally, the matching unit is specifically used for:
Calculate separately the similarity of the rgb value in the RGB detected value and RGB display sequence in the RGB detection sequence;
Matching degree to the similarity averaged, as the RGB detection sequence and the RGB display sequence.
Optionally, described device further include:
Screen intensity adjusts module, for being turned up screen intensity to preset range.
Optionally, described device further include:
Apart from determining module, for obtaining face at a distance from screen, and determine the distance within the scope of pre-determined distance;With/
Or
Luminous intensity determining module for obtaining the ambient light intensity of ambient enviroment, and determines the ambient light intensity in default light
In strength range.
Optionally, described device further include:
First cue module, if prompting user to adjust face and screen for the distance not within the scope of the pre-determined distance
The distance of curtain;And/or
Second cue module, if prompting user to adjust not in the default range of light intensities for the ambient light intensity
Position.
Optionally, the In vivo detection interface in the screen includes background area and Face datection frame region;
The light pulse control module includes:
Screen display control unit shows the RGB sequence for sequentially controlling the background area according to prefixed time interval
In the corresponding color of rgb value;And/or the first of the Face datection frame region is sequentially controlled according to prefixed time interval and is drawn
Cloth shows the corresponding color of rgb value in the RGB sequence, and the second painting canvas of the Face datection frame region shows face preview
Image;First painting canvas is superimposed upon on second painting canvas with default transparency.
Optionally, the light pulse control module includes:
Video record control unit for using the face as target recorded video stream, and controls in the video flowing of recording with one
The corresponding continuous frame number of a rgb value is default frame number.
Optionally, the light pulse attack judgment module is specifically used for:
When the quantity for the rgb value that color has been displayed in the RGB sequence reaches specified number, according to the RGB detection sequence
With the RGB display sequence, In vivo detection result is determined.
Optionally, the color value detection module is specifically used for:
According to sequence of the rgb value of color in RGB sequence has been displayed, current rgb value is determined, and will be with the current rgb value
Corresponding image is as currently processed image;
It determines the human face region in the currently processed image, and obtains the pixel value of each pixel in the human face region;
The average value for determining the pixel value in the human face region, the RGB detected value as the currently processed image;
It continues to execute the currently processed image of above-mentioned determination and determines the operation of the RGB detected value of currently processed image, until obtaining
The RGB detected value of each rgb value correspondence image of color has been displayed, the RGB detected value forms RGB detection sequence.
Optionally, two neighboring rgb value is different in the RGB sequence.
The third aspect according to an embodiment of the present invention, provides a kind of electronic equipment, comprising: processor, memory and deposits
The computer program that can be run on the memory and on the processor is stored up, the computer program is by the processor
The biopsy method as described in first aspect is realized when execution.
Fourth aspect according to an embodiment of the present invention provides a kind of computer readable storage medium, and the computer can
It reads to be stored with computer program on storage medium, be realized as described in relation to the first aspect when the computer program is executed by processor
Biopsy method.
Biopsy method, device, electronic equipment and storage medium provided in an embodiment of the present invention, by generating RGB sequence
Column sequentially control the corresponding color of rgb value in screen display RGB sequence according to prefixed time interval, so that the RGB sequence
The optical pulse irradiation of corresponding color is to face, and using the face as target recorded video stream, determines in the video flowing and
The corresponding image of the rgb value of display color, and determine the corresponding RGB detected value of human face region in described image, obtain RGB inspection
Sequencing column, according to RGB detection sequence and have been displayed color rgb value composition RGB display sequence, determine In vivo detection as a result,
Due to being detected by light pulse, the RGB detected value obtained when there are living body attack and the RGB that color has been displayed
Value mismatches, and so as to detect the behavior in time, improves the accuracy of In vivo detection, and do not need the view that will be recorded
Frequency is sent to server and is detected, and realizes offline inspection, shortens detection time, the user experience is improved.
The above description is only an overview of the technical scheme of the present invention, in order to better understand the technical means of the present invention,
And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects of the present invention, feature and advantage can
It is clearer and more comprehensible, the followings are specific embodiments of the present invention.
Detailed description of the invention
By reading the following detailed description of the preferred embodiment, various other advantages and benefits are common for this field
Technical staff will become clear.The drawings are only for the purpose of illustrating a preferred embodiment, and is not considered as to the present invention
Limitation.
Fig. 1 is a kind of step flow chart of biopsy method provided in an embodiment of the present invention;
Fig. 2 is a kind of step flow chart of biopsy method provided in an embodiment of the present invention;
Fig. 3 is a kind of structural block diagram of living body detection device provided in an embodiment of the present invention.
Specific embodiment
The exemplary embodiment that the present invention will be described in more detail below with reference to accompanying drawings.Although showing the present invention in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the present invention without should be by embodiments set forth here
It is limited.It is to be able to thoroughly understand the present invention on the contrary, providing these embodiments, and can be by the scope of the present invention
It is fully disclosed to those skilled in the art.
Fig. 1 is a kind of step flow chart of biopsy method provided in an embodiment of the present invention, and this method can be applied to
In electronic equipment, the electronic equipment is, for example, mobile phone etc., In vivo detection is carried out by light pulse, as shown in Figure 1, this method can
To include:
Step 101, RGB sequence is generated, the RGB sequence includes at least two rgb values.
Wherein, RGB represents the color in three channels of red, green, blue.The RGB sequence includes at least two rgb values, specifically
It can be the rgb value of predetermined number.Two neighboring rgb value is different in the RGB sequence, and the complexity of RGB sequence can be improved,
It avoids RGB sequence from being cracked, and then improves the accuracy and safety of In vivo detection.
The RGB sequence that one group includes the rgb value of predetermined number is generated by algorithm, phase is provided according to rgb value convenient for subsequent
Answer the light pulse of color.Wherein, the generation of RGB sequence can be the generation when carrying out In vivo detection, be also possible to pre-generate,
In vivo detection is improved it is preferred that can be the corresponding RGB sequence of each In vivo detection so as to avoid RGB sequence from being replicated
Accuracy.
Step 102, screen is sequentially controlled according to prefixed time interval shows the corresponding face of rgb value in the RGB sequence
Color, so that the optical pulse irradiation of the RGB sequence corresponding color is to face, and using the face as target recorded video stream.
Sequentially draw each rgb value in RGB sequence on the screen according to prefixed time interval, i.e. control screen is shown
The corresponding color of each rgb value in RGB sequence, so that the light pulse for the RGB sequence corresponding color that screen is shown successively is irradiated
To face, and using the face as target recorded video stream, after optical pulse irradiation to face, face can have corresponding color
Light, thus record video flowing in respective frame image in human face region can show corresponding color.It is adjacent due to drawing
Time interval between the color of two rgb values is prefixed time interval, so that the color for each rgb value drawn makes screen
The light of corresponding color is issued, light pulse is formed.
In some embodiments of the present application, the In vivo detection interface in the screen includes background area and Face datection
Frame region;The screen that sequentially controls according to prefixed time interval shows the corresponding color of rgb value in the RGB sequence, packet
It includes:
The background area is sequentially controlled according to prefixed time interval shows the corresponding color of rgb value in the RGB sequence;
And/or
The first painting canvas that the Face datection frame region is sequentially controlled according to prefixed time interval is shown in the RGB sequence
Second painting canvas of the corresponding color of rgb value, the Face datection frame region shows face preview image;First painting canvas is with pre-
If transparency is superimposed upon on second painting canvas.
When carrying out In vivo detection, the In vivo detection interface in screen includes background area and Face datection frame region, face
Detection frame region is usually the region depicted using the head portrait of people as profile, the facial image when the region shows In vivo detection
Live preview figure, background area be face detection block region other than screen area.It is shown in RGB sequence on the screen
When the corresponding color of rgb value, it can be and only shown in background area, is also possible to same in background area and Face datection frame region
When show.When Face datection frame region shows the corresponding color of rgb value in RGB sequence, in order to avoid the rgb value pair of display
Interference of the color answered to the face preview image got needs on the second painting canvas of display face preview image with default
Transparency is superimposed the first painting canvas, and shows the corresponding color of rgb value in RGB sequence by the first painting canvas.Pass through Face datection
Frame region and background area show the light pulse of RGB sequence corresponding color simultaneously, so that the intensity of light pulse compares uniform background
Region show it is stronger, so as to further increase the accuracy of In vivo detection.
In some embodiments of the present application, using the face as target recorded video stream, comprising:
Using the face as target recorded video stream, and control continuous frame number corresponding with a rgb value in the video flowing of recording
To preset frame number.
In view of the propagation of light and the time delay of system, show that a rgb value in RGB sequence is corresponding in control screen
It after color, controls and records continuously default frame number in the video flowing of recording, is i.e. a rgb value, which corresponds to, continuously presets frame number in video flowing
Image, guarantee that the image being recorded to can be corresponded to each other with the rgb value of display color, thereby may be ensured that the accurate of In vivo detection
Property.For example, can record 4 frames after showing the corresponding color of a rgb value, reflect the rgb value pair so as to be recorded to
Answer the facial image of color.
Step 103, image corresponding with the rgb value that color has been displayed in the video flowing is determined, and described in determination
The corresponding RGB detected value of human face region in image, obtains RGB detection sequence.
After control screen shows the corresponding color of a rgb value, the multiframe figure in the corresponding video flowing of the rgb value is determined
Picture, chooses a frame from multiple image to determine RGB detected value, can also each frame to multiple image determine RGB inspection respectively
Measured value.A frame is chosen from multiple image last frame can be chosen when determining RGB detected value, to guarantee the image chosen
It is the image for reflecting light pulse.When determining the RGB detected value of a frame image, recognition of face is carried out to the frame image, according to
The face key point identified determines human face region, the corresponding rgb value of human face region is calculated, as the corresponding RGB of the frame image
Detected value.Wherein, the video flowing is yuv video stream, in the corresponding rgb value of the human face region that determines a frame image, is needed
Yuv data is converted into RGB data, so that it is determined that the rgb value of human face region.Wherein, YUV is that compiling true-color color is empty
Between (color space) type, " Y " indicate brightness (Luminance, Luma), " U " and " V " is then coloration, concentration
(Chrominance, Chroma).
In some embodiments of the present application, the corresponding RGB detected value of human face region in the determining described image is obtained
To RGB detection sequence, comprising:
According to sequence of the rgb value of color in RGB sequence has been displayed, current rgb value is determined, and will be with the current rgb value
Corresponding image is as currently processed image;
It determines the human face region in the currently processed image, and obtains the pixel value of each pixel in the human face region;
The average value for determining the pixel value in the human face region, the RGB detected value as the currently processed image;
It continues to execute the currently processed image of above-mentioned determination and determines the operation of the RGB detected value of currently processed image, until obtaining
The RGB detected value of each rgb value correspondence image of color has been displayed, the RGB detected value forms RGB detection sequence.
First, in accordance with sequence of the rgb value of color in RGB sequence has been displayed, current rgb value is determined, by current rgb value
Corresponding image carries out recognition of face as currently processed image, to currently processed image, face key point is determined, according to face
Key point determines the human face region in currently processed image, obtains the pixel value of each pixel in human face region, and pixel value is
The value of RGB form is averaged the pixel value of pixel each in human face region, and obtained average value is as currently processed image
RGB detected value, RGB detected value is stored in sequence into an array, in each rgb value pair for obtaining having been displayed color
After the RGB detected value for answering image, all RGB detected values form RGB detection sequence, thus in subsequent determining In vivo detection result
When from array take out RGB detection sequence with have been displayed color rgb value composition RGB display sequence carry out matching determining living body
Testing result.
Step 104, it according to the RGB display sequence of the RGB detection sequence and the rgb value composition that color has been displayed, determines
In vivo detection result.
RGB detection sequence is matched with the RGB display sequence that the rgb value that color has been displayed forms, is tied according to matching
Fruit determines In vivo detection result.
It should be noted that when choosing a frame image in the corresponding multiple image of a rgb value and determining RGB detected value,
RGB display sequence is the sequence that the rgb value of color has been displayed and forms according to display order.In the corresponding multiframe figure of a rgb value
When each frame of picture determines RGB detected value respectively, which can be copied as to quantity identical with the frame number of multiple image,
And the multiple rgb value continuous arrangements obtained after a rgb value duplication, and each rgb value of color will have been displayed in sequence
Multiple rgb values after duplication form RGB display sequence.For example, control screen acquires two after showing the corresponding color of a rgb value
Frame image, then available two RGB detected values, at this moment copy as two rgb values for the rgb value that color has been displayed, for every
One rgb value that color has been displayed carries out such processing, by RGB detected value and rgb value respectively in that same order into
Row arrangement, obtains two sequences, i.e. RGB detection sequence and RGB display sequence, matches to the two sequences, according to matching
As a result In vivo detection result is determined.
In some embodiments of the present application, the rgb value according to the RGB detected value and the drafting is determined and is lived
Result is surveyed in physical examination, comprising:
When the quantity for the rgb value that color has been displayed in the RGB sequence reaches specified number, according to the RGB detection sequence
With the RGB display sequence, In vivo detection result is determined.
Since the number of rgb value in RGB sequence is certain value, so that the quantity for the rgb value drawn in RGB sequence reaches
When to specified number, determine that recording stage reaches specified phases, at this moment according to obtained RGB detection sequence and corresponding RGB
Display sequence determines In vivo detection result.Wherein, specified phases can be intermediate stage or ending phase, can also be it
His, it specifically can according to need setting in stage.For example, in RGB sequence include 10 rgb values when, specified number can be 5 or
10, it can also be other numerical value.
Biopsy method provided in this embodiment, by generating RGB sequence, according to prefixed time interval sequentially control flow
The corresponding color of rgb value in curtain display RGB sequence, so that the optical pulse irradiation of the RGB sequence corresponding color is to face, and
Using the face as target recorded video stream, image corresponding with the rgb value that color has been displayed in the video flowing is determined,
And determine the corresponding RGB detected value of human face region in image, RGB detection sequence is obtained, according to RGB detection sequence and is had been displayed
The RGB display sequence of the rgb value composition of color, determines In vivo detection as a result, existing due to being detected by light pulse
When living body attack (for example, video is held as a hostage), the RGB detected value that is obtained in video flowing by human face region in image with
The rgb value of display color mismatches, and so as to detect the behavior in time, improves the accuracy of In vivo detection, and not
It needs the video of recording being sent to server and detect, realize offline inspection, shorten detection time, improve user
Experience.
Based on the above technical solution, screen is sequentially controlled according to prefixed time interval described show the RGB
It is also optional to include: before the corresponding color of rgb value in sequence
Screen intensity is turned up to preset range.
Wherein, preset range can be the range between preset value and maximum value, and the preset range can be directly for most
Big value.
Before carrying out In vivo detection based on light pulse, first screen intensity is turned up to preset range, so that on screen
The light pulse of corresponding color is sufficiently strong, and then can be irradiated on face, reflects the corresponding face of light pulse so as to be recorded to
The facial image of color improves the accuracy of In vivo detection.
Based on the above technical solution, screen is sequentially controlled according to prefixed time interval described show the RGB
It is also optional to include: before the corresponding color of rgb value in sequence
Face is obtained at a distance from screen, and determines the distance within the scope of pre-determined distance;And/or
The ambient light intensity of ambient enviroment is obtained, and determines the ambient light intensity in default range of light intensities.
Ambient enviroment is detected, whether mainly detection ambient enviroment has an impact to light pulse, the ring only around
When border does not influence light pulse, In vivo detection could be implemented by light pulse.For example, ambient light intensity is too by force or in environment light
With color light it is too strong when, environment light can cover light pulse, reduce the accuracy of In vivo detection.Obtain the environment light of ambient enviroment
Intensity whether there is interference light primarily to determining in ambient enviroment, can obtain ambient enviroment by photoelectric sensor
Ambient light intensity, alternatively, the ambient light intensity of ambient enviroment can be determined by the brightness of image acquired in preview pane, or
Person can also determine the environment light of ambient enviroment according to some values such as f-number, exposure and aperture times of shutter output
Intensity.
Face can be obtained at a distance from screen by a variety of methods, such as by transmitting infrared light and can receive
Reflection light determines face at a distance from screen according to launch time and the time for receiving reflection light, or according to face
Size in preview pane determines face at a distance from screen, when at a distance from face with screen within the scope of pre-determined distance,
It can guarantee on the optical pulse irradiation to face of sufficient intensity, and obtain the facial image of suitable size, guarantee In vivo detection knot
The accuracy of fruit.It, can when the distance is within the scope of pre-determined distance and the ambient light intensity is in default range of light intensities
To guarantee the accuracy of In vivo detection.
Based on the above technical solution, also optional to include:
If the distance not within the scope of the pre-determined distance, prompts user to adjust face at a distance from screen;And/or
If the ambient light intensity not in the default range of light intensities, prompts user to adjust position.
If at a distance from screen farther out, i.e., face is greater than the maximum value in pre-determined distance range to face at a distance from screen,
Can then it prompt user close to screen;If face and screen are closer, i.e., face is less than pre-determined distance at a distance from screen
Minimum value in range can then prompt user far from screen.In environment detection result, if ambient light intensity is excessively high, ring
Border light will affect the light pulse for being irradiated to corresponding color on face, and user at this moment can be prompted to change to some positions of dark.
Fig. 2 is a kind of step flow chart of biopsy method provided in an embodiment of the present invention, as shown in Fig. 2, this method
May include:
Step 201, RGB sequence is generated, the RGB sequence includes at least two rgb values.
The particular content of this step is identical as the particular content of the step 101 in above-described embodiment, and which is not described herein again.
Step 202, screen is sequentially controlled according to prefixed time interval shows the corresponding face of rgb value in the RGB sequence
Color, so that the optical pulse irradiation of the RGB sequence corresponding color is to face, and using the face as target recorded video stream.
The particular content of this step is identical as the particular content of the step 102 in above-described embodiment, and which is not described herein again.
Step 203, image corresponding with the rgb value that color has been displayed in the video flowing is determined, and described in determination
The corresponding RGB detected value of human face region in image, obtains RGB detection sequence.
The particular content of this step is identical as the particular content of the step 103 in above-described embodiment, and which is not described herein again.
Step 204, the matching degree of the RGB display sequence of the RGB detection sequence and the drafting is determined.
The whole RGB detected values acquired before are carried out two points and compare calculating with the rgb value drawn in RGB sequence,
Obtain the matching degree of a 0-1.Matching degree is higher, it was demonstrated that risk of attacks is lower.Matching degree is lower, there is the risk being held as a hostage.
In the large-scale application stage, a fixed boundary matching degree can be obtained, set preset threshold for the boundary matching degree, be based on
This preset threshold is to determine whether belong to attack, to carry out subsequent user's operation.
In some embodiments of the present application, the matching of determination the RGB detection sequence and the RGB display sequence
Degree, comprising:
Calculate separately the similarity of the rgb value in the RGB detected value and RGB display sequence in the RGB detection sequence;
Matching degree to the similarity averaged, as the RGB detection sequence and the RGB display sequence.
The quantity of RGB detected value in RGB detection sequence is identical as the quantity of rgb value in RGB display sequence, Er Qiepai
Column sequence is identical, corresponding with RGB display sequence to the RGB detected value in RGB detection sequence so as in sequence
Rgb value calculates similarity and, to these similarity averageds, obtains to obtain similarity identical with detected value quantity
Average value be RGB detection sequence and RGB display sequence matching degree.
For example, when including 10 rgb values in RGB sequence, it, can be at this if a rgb value is corresponding to record 4 frame images
Last frame is chosen in 4 frame images to calculate RGB detected value, includes 10 RGB detected values in RGB detection sequence, RGB shows sequence
Column are identical as RGB sequence, corresponding with RGB display sequence so as to calculate separately the RGB detected value in RGB detection sequence
The similarity of rgb value, last averaged obtain the matching degree of RGB detection sequence Yu RGB display sequence.If a rgb value
It is corresponding to record 4 frame images, this 4 frame image can also be both participated in and calculate RGB detected value, RGB detection sequence includes 40 RGB inspections
At this moment a rgb value in corresponding RGB sequence can be copied as 4 rgb values, and continuous arrangement by measured value, then with RGB
The continuous rgb value after the duplication of other rgb values in sequence arranges in sequence, obtains RGB display sequence, i.e. RGB display sequence
Including 40 rgb values, so as to calculate separately the similarity of analog value in two sequences in sequence, finally seek average
Value, obtains the matching degree of two sequences.
Step 205, judge whether the matching degree is greater than or equal to preset threshold, if so, 206 are thened follow the steps, if it is not,
Then follow the steps 207.
Step 206, determine that In vivo detection result passes through for detection.
Step 207, determine that In vivo detection result is that there are living body attacks.
Wherein, living body attack includes virtual video attack.
Biopsy method provided in this embodiment when determining In vivo detection result, leads on the basis of the above embodiments
Whether the matching degree for crossing RGB detected value and rgb value is greater than or equal to preset threshold to determine whether there is living body attack, from
And further increase the accuracy of In vivo detection.
It on the basis of the above embodiments, is to be gone back there are after living body attack in the determining In vivo detection result
Include:
Prompt user re-starts In vivo detection.
If In vivo detection result be there are living body attacks, prompting user, there are living body attacks, and again into
Row detection, that is, re-execute the operation of above-mentioned In vivo detection, ensure that the accuracy of testing result.
It should be noted that for simple description, therefore, it is stated as a series of action groups for embodiment of the method
It closes, but those skilled in the art should understand that, embodiment of that present invention are not limited by the describe sequence of actions, because according to
According to the embodiment of the present invention, some steps may be performed in other sequences or simultaneously.Secondly, those skilled in the art also should
Know, the embodiments described in the specification are all preferred embodiments, and the related movement not necessarily present invention is implemented
Necessary to example.
Fig. 3 is a kind of structural block diagram of living body detection device provided in an embodiment of the present invention, as shown in figure 3, the living body is examined
Surveying device may include:
RGB sequence generating module 301, for generating RGB sequence, the RGB sequence includes at least two rgb values;
Light pulse control module 302 shows RGB in the RGB sequence for sequentially controlling screen according to prefixed time interval
It is worth corresponding color, so that the optical pulse irradiation of the RGB sequence corresponding color is recorded to face, and by target of the face
Video flowing;
Color value detection module 303, for determining image corresponding with the rgb value that color has been displayed in the video flowing, and
It determines the corresponding RGB detected value of human face region in described image, obtains RGB detection sequence;
Judgment module 304 is attacked in light pulse, for being formed according to the RGB detection sequence and the rgb value that color has been displayed
RGB display sequence, determine In vivo detection result.
Optionally, the light pulse attack judgment module includes:
Matching unit, for determining the matching degree of the RGB detection sequence and the RGB display sequence;
Detection is by determination unit, if being greater than or equal to preset threshold for the matching degree, it is determined that In vivo detection result is
Detection passes through;
Living body attacks determination unit, if being less than the preset threshold for the matching degree, it is determined that In vivo detection result is to deposit
In living body attack.
Optionally, the matching unit is specifically used for:
Calculate separately the similarity of the rgb value in the RGB detected value and RGB display sequence in the RGB detection sequence;
Matching degree to the similarity averaged, as the RGB detection sequence and the RGB display sequence.
Optionally, described device further include:
Screen intensity adjusts module, for being turned up screen intensity to preset range.
Optionally, described device further include:
Apart from determining module, for obtaining face at a distance from screen, and determine the distance within the scope of pre-determined distance;
Luminous intensity determining module for obtaining the ambient light intensity of ambient enviroment, and determines the ambient light intensity in default light
In strength range.
Optionally, described device further include:
First cue module, if prompting user to adjust face and screen for the distance not within the scope of the pre-determined distance
The distance of curtain;And/or
Second cue module, if prompting user to adjust not in the default range of light intensities for the ambient light intensity
Position.
Optionally, the In vivo detection interface in the screen includes background area and Face datection frame region;
The light pulse control module includes:
Screen display control unit shows the RGB sequence for sequentially controlling the background area according to prefixed time interval
In the corresponding color of rgb value;And/or the first of the Face datection frame region is sequentially controlled according to prefixed time interval and is drawn
Cloth shows the corresponding color of rgb value in the RGB sequence, and the second painting canvas of the Face datection frame region shows face preview
Image;First painting canvas is superimposed upon on second painting canvas with default transparency.
Optionally, the light pulse control module includes:
Video record control unit for using the face as target recorded video stream, and controls in the video flowing of recording with one
The corresponding continuous frame number of a rgb value is default frame number.
Optionally, the light pulse attack judgment module is specifically used for:
When the quantity for the rgb value that color has been displayed in the RGB sequence reaches specified number, according to the RGB detection sequence
With the RGB display sequence, In vivo detection result is determined.
Optionally, the color value detection module is specifically used for:
According to sequence of the rgb value of color in RGB sequence has been displayed, current rgb value is determined, and will be with the current rgb value
Corresponding image is as currently processed image;
It determines the human face region in the currently processed image, and obtains the pixel value of each pixel in the human face region;
The average value for determining the pixel value in the human face region, the RGB detected value as the currently processed image;
It continues to execute the currently processed image of above-mentioned determination and determines the operation of the RGB detected value of currently processed image, until obtaining
The RGB detected value of each rgb value correspondence image of color has been displayed, the RGB detected value forms RGB detection sequence.
Optionally, two neighboring rgb value is different in the RGB sequence.
Living body detection device provided in this embodiment generates RGB sequence, light pulse control by RGB sequence generating module
Module sequentially controls the corresponding color of rgb value in screen display RGB sequence according to prefixed time interval, so that the RGB sequence
For the optical pulse irradiation of column corresponding color to face, and using the face as target recorded video stream, color value detection module determines institute
Image corresponding with the rgb value that color has been displayed in video flowing is stated, and determines that the human face region in described image is corresponding
RGB detected value, obtains RGB detection sequence, and light pulse attacks judgment module according to RGB detection sequence and the RGB that color has been displayed
It is worth the RGB display sequence of composition, determines In vivo detection as a result, due to being detected by light pulse, there are living body attacks
The RGB detected value obtained when behavior is different from the rgb value that color has been displayed, and so as to detect the behavior in time, improves
The accuracy of In vivo detection, and do not need the video of recording being sent to server and detect, offline inspection is realized, is contracted
Short detection time, the user experience is improved.
For device embodiment, since it is basically similar to the method embodiment, related so being described relatively simple
Place illustrates referring to the part of embodiment of the method.
Further, according to one embodiment of present invention, a kind of electronic equipment is provided, the electronic equipment can be
The terminals such as mobile phone, the electronic equipment include: processor, memory and are stored on the memory and can be in the processor
The computer program of upper operation realizes the In vivo detection side of previous embodiment when the computer program is executed by the processor
Method.
According to one embodiment of present invention, a kind of computer readable storage medium is additionally provided, it is described computer-readable
Storage medium includes but is not limited to magnetic disk storage, CD-ROM, optical memory etc., is deposited on the computer readable storage medium
Computer program is contained, the biopsy method of previous embodiment is realized when the computer program is executed by processor.
All the embodiments in this specification are described in a progressive manner, the highlights of each of the examples are with
The difference of other embodiments, the same or similar parts between the embodiments can be referred to each other.
It should be understood by those skilled in the art that, the embodiment of the embodiment of the present invention can provide as method, apparatus or calculate
Machine program product.Therefore, the embodiment of the present invention can be used complete hardware embodiment, complete software embodiment or combine software and
The form of the embodiment of hardware aspect.Moreover, the embodiment of the present invention can be used one or more wherein include computer can
With in the computer-usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) of program code
The form of the computer program product of implementation.
The embodiment of the present invention be referring to according to the method for the embodiment of the present invention, terminal device (system) and computer program
The flowchart and/or the block diagram of product describes.It should be understood that flowchart and/or the block diagram can be realized by computer program instructions
In each flow and/or block and flowchart and/or the block diagram in process and/or box combination.It can provide these
Computer program instructions are set to general purpose computer, special purpose computer, Embedded Processor or other programmable data processing terminals
Standby processor is to generate a machine, so that being held by the processor of computer or other programmable data processing terminal devices
Capable instruction generates for realizing in one or more flows of the flowchart and/or one or more blocks of the block diagram
The device of specified function.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing terminal devices
In computer-readable memory operate in a specific manner, so that instruction stored in the computer readable memory generates packet
The manufacture of command device is included, which realizes in one side of one or more flows of the flowchart and/or block diagram
The function of being specified in frame or multiple boxes.
These computer program instructions can also be loaded into computer or other programmable data processing terminal devices, so that
Series of operation steps are executed on computer or other programmable terminal equipments to generate computer implemented processing, thus
The instruction executed on computer or other programmable terminal equipments is provided for realizing in one or more flows of the flowchart
And/or in one or more blocks of the block diagram specify function the step of.
Although the preferred embodiment of the embodiment of the present invention has been described, once a person skilled in the art knows bases
This creative concept, then additional changes and modifications can be made to these embodiments.So the following claims are intended to be interpreted as
Including preferred embodiment and fall into all change and modification of range of embodiment of the invention.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that process, method, article or terminal device including a series of elements not only wrap
Those elements are included, but also including other elements that are not explicitly listed, or further includes for this process, method, article
Or the element that terminal device is intrinsic.In the absence of more restrictions, being wanted by what sentence "including a ..." limited
Element, it is not excluded that there is also other identical elements in process, method, article or the terminal device for including the element.
Above to a kind of biopsy method provided by the present invention, device, electronic equipment and storage medium, carry out in detail
Thin to introduce, used herein a specific example illustrates the principle and implementation of the invention, and above embodiments are said
It is bright to be merely used to help understand method and its core concept of the invention;At the same time, for those skilled in the art, foundation
Thought of the invention, there will be changes in the specific implementation manner and application range, in conclusion the content of the present specification is not
It is interpreted as limitation of the present invention.
Claims (14)
1. a kind of biopsy method characterized by comprising
RGB sequence is generated, the RGB sequence includes at least two rgb values;
Screen is sequentially controlled according to prefixed time interval and shows the corresponding color of rgb value in the RGB sequence, so that described
The optical pulse irradiation of RGB sequence corresponding color is to face, and using the face as target recorded video stream;
It determines image corresponding with the rgb value that color has been displayed in the video flowing, and determines the face in described image
The corresponding RGB detected value in region, obtains RGB detection sequence;
According to the RGB display sequence of the RGB detection sequence and the rgb value composition that color has been displayed, In vivo detection result is determined.
2. the method according to claim 1, wherein described according to the RGB detection sequence and the RGB having been displayed
It is worth the RGB display sequence of composition, determines In vivo detection result, comprising:
Determine the matching degree of the RGB detection sequence and the RGB display sequence;
If the matching degree is greater than or equal to preset threshold, it is determined that In vivo detection result is that detection passes through;
If the matching degree is less than the preset threshold, it is determined that In vivo detection result is that there are living body attacks.
3. according to the method described in claim 2, it is characterized in that, the determination RGB detection sequence and the RGB are shown
The matching degree of sequence, comprising:
Calculate separately the similarity of the rgb value in the RGB detected value and RGB display sequence in the RGB detection sequence;
Matching degree to the similarity averaged, as the RGB detection sequence and the RGB display sequence.
4. the method according to claim 1, wherein sequentially to control according to prefixed time interval screen aobvious described
Before showing the corresponding color of rgb value in the RGB sequence, further includes:
Screen intensity is turned up to preset range.
5. the method according to claim 1, wherein sequentially to control according to prefixed time interval screen aobvious described
Before showing the corresponding color of rgb value in the RGB sequence, further includes:
Face is obtained at a distance from screen, and determines the distance within the scope of pre-determined distance;And/or
The ambient light intensity of ambient enviroment is obtained, and determines the ambient light intensity in default range of light intensities.
6. according to the method described in claim 5, it is characterized by further comprising:
If the distance not within the scope of the pre-determined distance, prompts user to adjust face at a distance from screen;And/or
If the ambient light intensity not in the default range of light intensities, prompts user to adjust position.
7. the method according to claim 1, wherein the In vivo detection interface in the screen includes background area
With Face datection frame region;
The screen that sequentially controls according to prefixed time interval shows the corresponding color of rgb value in the RGB sequence, comprising:
The background area is sequentially controlled according to prefixed time interval shows the corresponding color of rgb value in the RGB sequence;
And/or
The first painting canvas that the Face datection frame region is sequentially controlled according to prefixed time interval is shown in the RGB sequence
Second painting canvas of the corresponding color of rgb value, the Face datection frame region shows face preview image;First painting canvas is with pre-
If transparency is superimposed upon on second painting canvas.
8. the method according to claim 1, wherein using the face as target recorded video stream, comprising:
Using the face as target recorded video stream, and control continuous frame number corresponding with a rgb value in the video flowing of recording
To preset frame number.
9. the method according to claim 1, wherein described according to the RGB detection sequence and color having been displayed
Rgb value composition RGB display sequence, determine In vivo detection result, comprising:
When the quantity for the rgb value that color has been displayed in the RGB sequence reaches specified number, according to the RGB detection sequence
With the RGB display sequence, In vivo detection result is determined.
10. -9 described in any item methods according to claim 1, which is characterized in that the face area in the determining described image
The corresponding RGB detected value in domain, obtains RGB detection sequence, comprising:
According to sequence of the rgb value of color in RGB sequence has been displayed, current rgb value is determined, and will be with the current rgb value
Corresponding image is as currently processed image;
It determines the human face region in the currently processed image, and obtains the pixel value of each pixel in the human face region;
The average value for determining the pixel value in the human face region, the RGB detected value as the currently processed image;
It continues to execute the currently processed image of above-mentioned determination and determines the operation of the RGB detected value of currently processed image, until obtaining
The RGB detected value of each rgb value correspondence image of color has been displayed, the RGB detected value forms RGB detection sequence.
11. the method according to claim 1, wherein two neighboring rgb value is different in the RGB sequence.
12. a kind of living body detection device characterized by comprising
RGB sequence generating module, for generating RGB sequence, the RGB sequence includes at least two rgb values;
Light pulse control module shows rgb value pair in the RGB sequence for sequentially controlling screen according to prefixed time interval
The color answered, so that the optical pulse irradiation of the RGB sequence corresponding color is to face, and using the face as target recorded video
Stream;
Color value detection module, for determining image corresponding with the rgb value that color has been displayed in the video flowing, and sequentially
It determines the corresponding RGB detected value of human face region in described image, obtains RGB detection sequence;
Judgment module is attacked in light pulse, for what is formed according to the RGB detection sequence and the rgb value that color has been displayed
RGB display sequence determines In vivo detection result.
13. a kind of electronic equipment characterized by comprising processor, memory and be stored on the memory and can be in institute
The computer program run on processor is stated, such as claim 1-11 is realized when the computer program is executed by the processor
Described in any item biopsy methods.
14. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program realizes such as claim 1-11 described in any item biopsy methods when the computer program is executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910557266.9A CN110414346A (en) | 2019-06-25 | 2019-06-25 | Biopsy method, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910557266.9A CN110414346A (en) | 2019-06-25 | 2019-06-25 | Biopsy method, device, electronic equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110414346A true CN110414346A (en) | 2019-11-05 |
Family
ID=68359879
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910557266.9A Pending CN110414346A (en) | 2019-06-25 | 2019-06-25 | Biopsy method, device, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110414346A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111144365A (en) * | 2019-12-31 | 2020-05-12 | 北京三快在线科技有限公司 | Living body detection method, living body detection device, computer equipment and storage medium |
CN111597938A (en) * | 2020-05-07 | 2020-08-28 | 马上消费金融股份有限公司 | Living body detection and model training method and device |
CN111914763A (en) * | 2020-08-04 | 2020-11-10 | 网易(杭州)网络有限公司 | Living body detection method and device and terminal equipment |
WO2020259128A1 (en) * | 2019-06-28 | 2020-12-30 | 北京旷视科技有限公司 | Liveness detection method and apparatus, electronic device, and computer readable storage medium |
WO2023221996A1 (en) * | 2022-05-16 | 2023-11-23 | 北京旷视科技有限公司 | Living body detection method, electronic device, storage medium, and program product |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107832712A (en) * | 2017-11-13 | 2018-03-23 | 深圳前海微众银行股份有限公司 | Biopsy method, device and computer-readable recording medium |
CN107992794A (en) * | 2016-12-30 | 2018-05-04 | 腾讯科技(深圳)有限公司 | A kind of biopsy method, device and storage medium |
CN108197279A (en) * | 2018-01-09 | 2018-06-22 | 北京旷视科技有限公司 | Attack data creation method, device, system and computer readable storage medium |
CN108460266A (en) * | 2018-03-22 | 2018-08-28 | 百度在线网络技术(北京)有限公司 | Method and apparatus for authenticating identity |
CN108876757A (en) * | 2017-06-14 | 2018-11-23 | 北京旷视科技有限公司 | Environment light detection method, device and equipment and storage medium |
CN109063588A (en) * | 2018-07-11 | 2018-12-21 | 深圳合纵视界技术有限公司 | A method of the face colour of skin in image is extracted based on face frame |
JP2019001226A (en) * | 2017-06-13 | 2019-01-10 | アルパイン株式会社 | Electronic mirror device |
CN109376592A (en) * | 2018-09-10 | 2019-02-22 | 阿里巴巴集团控股有限公司 | Biopsy method, device and computer readable storage medium |
CN109660745A (en) * | 2018-12-21 | 2019-04-19 | 深圳前海微众银行股份有限公司 | Video recording method, device, terminal and computer readable storage medium |
-
2019
- 2019-06-25 CN CN201910557266.9A patent/CN110414346A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107992794A (en) * | 2016-12-30 | 2018-05-04 | 腾讯科技(深圳)有限公司 | A kind of biopsy method, device and storage medium |
JP2019001226A (en) * | 2017-06-13 | 2019-01-10 | アルパイン株式会社 | Electronic mirror device |
CN108876757A (en) * | 2017-06-14 | 2018-11-23 | 北京旷视科技有限公司 | Environment light detection method, device and equipment and storage medium |
CN107832712A (en) * | 2017-11-13 | 2018-03-23 | 深圳前海微众银行股份有限公司 | Biopsy method, device and computer-readable recording medium |
CN108197279A (en) * | 2018-01-09 | 2018-06-22 | 北京旷视科技有限公司 | Attack data creation method, device, system and computer readable storage medium |
CN108460266A (en) * | 2018-03-22 | 2018-08-28 | 百度在线网络技术(北京)有限公司 | Method and apparatus for authenticating identity |
CN109063588A (en) * | 2018-07-11 | 2018-12-21 | 深圳合纵视界技术有限公司 | A method of the face colour of skin in image is extracted based on face frame |
CN109376592A (en) * | 2018-09-10 | 2019-02-22 | 阿里巴巴集团控股有限公司 | Biopsy method, device and computer readable storage medium |
CN109660745A (en) * | 2018-12-21 | 2019-04-19 | 深圳前海微众银行股份有限公司 | Video recording method, device, terminal and computer readable storage medium |
Non-Patent Citations (2)
Title |
---|
YOULIAN ZHU ET AL: "Face Detection Method Based on Multi-feature Fusion in YCbCr Color Space", 《2012 5TH INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING (CISP 2012)》 * |
郑欣洋: "面向人脸认证的活体检测方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020259128A1 (en) * | 2019-06-28 | 2020-12-30 | 北京旷视科技有限公司 | Liveness detection method and apparatus, electronic device, and computer readable storage medium |
CN111144365A (en) * | 2019-12-31 | 2020-05-12 | 北京三快在线科技有限公司 | Living body detection method, living body detection device, computer equipment and storage medium |
CN111597938A (en) * | 2020-05-07 | 2020-08-28 | 马上消费金融股份有限公司 | Living body detection and model training method and device |
CN111597938B (en) * | 2020-05-07 | 2022-02-22 | 马上消费金融股份有限公司 | Living body detection and model training method and device |
CN111914763A (en) * | 2020-08-04 | 2020-11-10 | 网易(杭州)网络有限公司 | Living body detection method and device and terminal equipment |
CN111914763B (en) * | 2020-08-04 | 2023-11-28 | 网易(杭州)网络有限公司 | Living body detection method, living body detection device and terminal equipment |
WO2023221996A1 (en) * | 2022-05-16 | 2023-11-23 | 北京旷视科技有限公司 | Living body detection method, electronic device, storage medium, and program product |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110414346A (en) | Biopsy method, device, electronic equipment and storage medium | |
CN108337433B (en) | Photographing method, mobile terminal and computer readable storage medium | |
CN104113688B (en) | A kind of image processing method and its electronic equipment | |
US10204432B2 (en) | Methods and systems for color processing of digital images | |
CN109376592A (en) | Biopsy method, device and computer readable storage medium | |
CN107566747A (en) | A kind of brightness of image Enhancement Method and device | |
CN105069812B (en) | Image processing apparatus, the setting devices and methods therefor for image processing apparatus | |
CN108418920B (en) | Intelligent terminal and control method thereof | |
CN109345485A (en) | A kind of image enchancing method, device, electronic equipment and storage medium | |
CN108351960A (en) | Electronic equipment with improved iris recognition and its method | |
CN107862653A (en) | Method for displaying image, device, storage medium and electronic equipment | |
AU2019309552B2 (en) | Method and data-processing system for synthesizing images | |
CN108419028A (en) | Image processing method, device, computer readable storage medium and electronic equipment | |
US20220400221A1 (en) | A system for performing ambient light image correction | |
CN108717691A (en) | A kind of image interfusion method, device, electronic equipment and medium | |
CN107404628A (en) | Image processing apparatus and method and monitoring system | |
CN110113526A (en) | Processing method, processing unit and electronic equipment | |
CN106600556A (en) | Image processing method and apparatus | |
CN113205057A (en) | Face living body detection method, device, equipment and storage medium | |
CN107454315A (en) | The human face region treating method and apparatus of backlight scene | |
CN106331460A (en) | Image processing method and device, and terminal | |
EP2958073A1 (en) | Image processing device, image processing method, and recording medium | |
KR20190080732A (en) | Estimation of illumination chromaticity in automatic white balancing | |
CN111275648B (en) | Face image processing method, device, equipment and computer readable storage medium | |
EP2469450B1 (en) | Face detection |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191105 |
|
RJ01 | Rejection of invention patent application after publication |