Interactive living body detection method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to an interactive living body detection method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: in response to a living body detection request, randomly generating a dynamic detection image; displaying the dynamic detection image through a display screen, and projecting light according to the dynamic detection image; obtaining a first facial feature image after the face of the detection object reflects light and a second facial feature image when the detection object watches the dynamic detection image; and determining whether the detection object is a living body or not according to the first facial feature image and the second facial feature image. By adopting the method, the accuracy of living body detection can be improved.

Description

Technical Field

[0001] The present application relates to the field of information security technology, and in particular to an interactive liveness detection method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] With the development of digital technology, identity authentication technology has emerged. Only after authenticating the user's identity and authorizing the user to access system resources.

[0003] Traditional identity authentication methods, such as passwords and tokens, are easy to forget and easy to be stolen. With the development of facial recognition, identity authentication has replaced traditional passwords or tokens.

[0004] However, current facial recognition systems are vulnerable to prosthetic attacks. For example, when using prosthetics such as photos, masks, and videos to attack facial recognition systems, there is a certain probability that identity authentication will be passed, which leads to the problem of low accuracy in current facial recognition. Summary of the invention

[0005] Based on this, it is necessary to provide an interactive liveness detection method, apparatus, computer device, computer-readable storage medium and computer program product that can improve detection accuracy in response to the above technical problems.

[0006] In a first aspect, the present application provides an interactive living body detection method, the method comprising:

[0007] In response to a liveness detection request, randomly generating a dynamic detection image;

[0008] Displaying the dynamic detection image through a display screen, and projecting light according to the dynamic detection image;

[0009] Acquire a first facial feature image after the detection object's face reflects the light and a second facial feature image of the detection object gazing at the dynamic detection image;

[0010] Determine whether the detection object is a living body according to the first facial feature image and the second facial feature image.

[0011] In one embodiment, determining whether the detected object is alive according to the first facial feature image and the second facial feature image includes:

[0012] Performing light reflection analysis on the first facial feature image to obtain a light reflection analysis result;

[0013] extracting eye feature data from the second facial feature image;

[0014] Determining gaze information of the detection object fixating on the dynamic detection image according to the eye feature data;

[0015] If the light reflection analysis result meets the living body detection feature, and the gaze information matches the change information of the dynamic detection image, it is determined that the detection object is a living body.

[0016] In one embodiment, the eye feature data includes pupil position information, eye movement trajectory information and iris morphology change information; the gaze information includes gaze duration information and gaze direction information; and determining the gaze information of the detection object on the dynamic detection image based on the eye feature data includes:

[0017] Determining the gaze duration information and gaze direction information of the detection object staring at the dynamic detection image according to the pupil position information, the eyeball movement trajectory information and the iris morphology change information;

[0018] The change information includes position change information and change information of the duration of the dynamic detection image; if the light reflection analysis result meets the liveness detection feature, and the gaze information matches the change information of the dynamic detection image, then determining that the detection object is a live body includes:

[0019] If the light reflection analysis result meets the liveness detection feature, and the gaze direction information matches the position change information of the dynamic detection image, and the gaze duration information matches the stay duration change information of the dynamic detection image, then it is determined that the detection object is a live body.

[0020] In one embodiment, the gaze information further includes gaze stability, and the gaze stability represents the ability to maintain a stable gaze direction; if the light reflection analysis result meets the liveness detection feature, and the gaze information matches the change information of the dynamic detection image, then determining that the detection object is a live body includes:

[0021] If the light reflection analysis result meets the liveness detection characteristics, the gaze information matches the change information of the dynamic detection image, and the gaze stability is greater than the stability threshold, then the detection object is determined to be a live body, wherein the stability threshold is determined based on pupil position information, eye movement trajectory information and iris morphology change information.

[0022] In one embodiment, performing light reflection analysis on the first facial feature image to obtain a light reflection analysis result includes:

[0023] extracting reflection information of light from the first facial feature image, wherein the reflection information includes at least one of reflection intensity, reflection distribution and reflection color;

[0024] Determine a light reflection analysis result according to the reflection information, wherein the light reflection analysis result includes at least one of a reflection intensity analysis result, a reflection distribution analysis result and a reflection color analysis result;

[0025] The liveness detection feature includes at least one of a first feature of uneven and dynamically changing reflection intensity, a second feature of uneven reflection distribution, and a third feature of dynamically changing reflection color; if the light reflection analysis result meets the liveness detection feature, and the gaze information matches the change information of the dynamic detection image, determining that the detection object is a live body includes:

[0026] If at least one of the reflection intensity analysis result conforms to the first feature, the reflection distribution analysis result conforms to the second feature, and the reflection color analysis result conforms to the third feature, and the gaze information matches the change information of the dynamic detection image, it is determined that the detection object is a living body.

[0027] In one embodiment, the dynamic detection image carries color information, location information and stay time information; the method further includes:

[0028] Prompt information is generated for use in conjunction with the color information, location information, and dwell time information, wherein the prompt information includes at least one of a voice prompt and a text prompt, and the prompt information is used to guide the detection object to gaze at the dynamic detection image.

[0029] An interactive living body detection device, comprising:

[0030] A generating module, used for randomly generating a dynamic detection image in response to a liveness detection request;

[0031] A display projection module, used for displaying the dynamic detection image through a display screen and projecting light according to the dynamic detection image;

[0032] An acquisition module, used for acquiring a first facial feature image after the detection object's face reflects the light and a second facial feature image of the detection object gazing at the dynamic detection image;

[0033] A determination module is used to determine whether the detection object is a living body according to the first facial feature image and the second facial feature image.

[0034] In a second aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0035] In a third aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0036] In a fourth aspect, the present application also provides a computer program product, including a computer program, which implements the steps of the above method when executed by a processor.

[0037] The above-mentioned interactive liveness detection method, apparatus, computer device, computer-readable storage medium and computer program product, on the one hand, verify whether the detected object is a live object by collecting the first facial feature image after the light projected from the dynamic detection image is reflected on the face of the detected object, that is, by the feature image of the light projected from the dynamic detection image reflected on the face of the detected object (reflected light detection); on the other hand, verify whether the detected object is a live object by collecting the second facial feature image of the detected object gazing at the dynamic detection image, that is, by the feature image of the gaze detection of the detected object (gaze detection). Through the reflected light detection and gaze detection, it is judged and verified whether the detected object is a live object together, thereby improving the accuracy of liveness detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0039] FIG1 is a diagram of an application environment of an interactive living body detection method according to an embodiment;

[0040] FIG2 is a schematic diagram of a flow chart of an interactive living body detection method in one embodiment;

[0041] FIG3 is a schematic diagram of a process for determining whether a detection object is a living body in one embodiment;

[0042] FIG4 is a schematic diagram of a process for determining whether a detection object is a living body in another embodiment;

[0043] FIG5 is a schematic diagram of a process for determining whether a detection object is a living body in another embodiment;

[0044] FIG6 is a structural block diagram of an interactive living body detection device in one embodiment;

[0045] FIG. 7 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0047] The interactive liveness detection method provided in the embodiment of the present application can be applied in the application environment shown in FIG. 1. The terminal 102 communicates with the server 104 through a network. The data storage system can store data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed on a cloud or other network server. The server can randomly generate a dynamic detection image in response to a liveness detection request sent by the terminal; display the dynamic detection image through a display screen, and project light according to the dynamic detection image; obtain a first facial feature image after the face of the detection object reflects the light and a second facial feature image of the detection object looking at the dynamic detection image; determine whether the detection object is alive according to the first facial feature image and the second facial feature image. The terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices, and portable wearable devices, and any terminal device with a display screen can be used, and the terminal projects light through the display screen. The server 104 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0048] Optionally, a processor is provided in the terminal 102. The terminal 102 receives a user's instruction and generates a liveness detection request. The terminal 102 responds to the liveness detection request through the processor and randomly generates a dynamic detection image; displays the dynamic detection image through a display screen and projects light according to the dynamic detection image; obtains a first facial feature image after the detection object's face reflects the light and a second facial feature image of the detection object looking at the dynamic detection image; determines whether the detection object is alive based on the first facial feature image and the second facial feature image.

[0049] In an exemplary embodiment, as shown in FIG2 , an interactive liveness detection method is provided, which is described by taking the method applied to the terminal in FIG1 as an example, and includes the following steps S202 to S206 . Among them:

[0050] Step S202: randomly generate a dynamic detection image in response to a liveness detection request.

[0051] Among them, liveness detection requests use liveness detection technology to detect the authenticity and survival status of organisms in scenarios where identity authentication is required to ensure that the collected biometric information comes from a real, living individual, and to request identity authentication based on this. Among them, liveness detection is a technical means in a biometric recognition system, which is used to ensure that the collected biometric information does come from a real, living person, rather than a forgery or a copy. Scenarios that require identity authentication include, for example, face unlocking scenarios on mobile phones; payment scenarios, payment is allowed after liveness detection; and remote identity authentication, such as verification in the fields of banking, securities, finance, insurance, and people's livelihood and social security.

[0052] Motion detection images represent patterns formed by a combination of multiple vivid, bright, and constantly changing colors.

[0053] Optionally, the terminal may include a mobile phone. In a mobile phone face recognition unlocking scenario, before the detection object unlocks the mobile phone, the detection object will send a liveness detection request to the mobile phone, for example, pressing the power of the mobile phone will send the liveness detection request. The mobile phone will generate a dynamic detection image randomly based on the liveness detection request, for example, a dynamically changing detection image composed of red, yellow and other colors.

[0054] Step S204, displaying the dynamic detection image through the display screen, and projecting light according to the dynamic detection image.

[0055] Optionally, the mobile phone displays a dynamic detection image through the display screen, for example, generates a dynamically changing detection image composed of red, yellow and other colors, and projects light toward the outside of the screen through the processor according to the dynamic detection image, and the colors of the projected light include red light and yellow light.

[0056] Optionally, the terminal may also include a computer device. For example, when the user presses the power button to start the computer device and sends a liveness detection request to the computer device, the computer device generates a dynamic detection image according to the liveness detection request, displays the dynamic detection image through a display screen, and projects light according to the dynamic detection image.

[0057] Step S206, obtaining a first facial feature image after the detection object's face reflects the light and a second facial feature image of the detection object gazing at the dynamic detection image.

[0058] The first facial feature image may be one facial feature image or a plurality of facial feature images, and the second facial feature image may be a plurality of consecutive facial feature images.

[0059] Optionally, the terminal may project light according to the dynamic detection image, and the detection object moves to the optimal facial feature image sampling point. The terminal may also project light according to the dynamic detection image, and the object moves to the optimal facial feature image sampling point. The terminal obtains the first facial feature image after the detection object's face reflects the light through the processor, and the terminal also obtains the second facial feature image of the detection object looking at the dynamic detection image.

[0060] Optionally, the terminal uses a high-definition camera to collect an initial first facial feature image after the detection object's face reflects light and an initial second facial feature image of the detection object looking at the dynamic detection image. The terminal processes the initial first facial feature image through a processor to obtain a first facial feature image; and preprocesses the initial second facial feature image to obtain a second facial feature image. The preprocessing includes operations such as image enhancement and denoising.

[0061] Step S208: determining whether the detected object is a living body according to the first facial feature image and the second facial feature image.

[0062] Optionally, the terminal determines whether the detected object is alive based on the acquired first facial feature image and second facial feature image. If the detected object is alive, the verification is successful and the detected object is authorized with corresponding permissions; if the detected object is not alive, the verification fails. For example, in the scenario of unlocking the mobile phone by face recognition, if the detected object is alive, the verification is successful, and the detected object can operate the mobile phone after unlocking. In the payment scenario, payment is allowed after liveness detection. If the detected object is alive, the verification is successful and payment can be made; if the detected object is not alive, the verification fails and payment is rejected.

[0063] Optionally, when the detection object is a living body, the identity information of the detection object is verified based on the first facial feature image and the second facial feature image. Including: when the detection object is a living body, a quick match is performed from a database based on the first facial feature image and the second facial feature image, and if the match with the image in the database is successful, it indicates that the identity information of the detection object has passed the verification. It should be noted that, when the detection object is a living body, the verification of the identity of the detection object does not require re-collection of image information, and the identity information verification is time-saving. For users, through one data facial feature collection, both liveness detection and identity information verification can be completed, and users will not perceive that the terminal device performs multiple processing.

[0064] Optionally, in the face recognition unlocking scenario of a mobile phone, if the detected object is alive, the identity information of the detected object is verified based on the first facial feature image and the second facial feature image, and the unlocking can be successful only if the alive condition and the identity information are met. If only the alive condition is met but the identity information is not met, the unlocking cannot be completed.

[0065] Optionally, in a payment scenario, after liveness detection, the identity information of the detected object is verified based on the first facial feature image and the second facial feature image, and payment can be made only if both the liveness condition and the identity information are met. If only the liveness condition is met but the identity information is not met, payment cannot be made.

[0066] In practical applications, detection methods based on physiological characteristics often require expensive special equipment, such as integrating iris collection equipment into the terminal. By reflecting the projected light of the dynamic detection pattern in this embodiment on the face of the detection object and the gaze information of the detection object's gaze on the dynamic detection pattern, accurate detection can be achieved without the need for additional expensive hardware equipment, reducing system cost and deployment difficulty.

[0067] In the above-mentioned interactive liveness detection method, on the one hand, by collecting the first facial feature image after the light projected from the dynamic detection image is reflected on the face of the detection object, that is, by the feature image of the light projected from the dynamic detection image reflected on the face of the detection object (reflected light detection), it is verified whether the detection object is alive; on the other hand, by collecting the second facial feature image of the detection object gazing at the dynamic detection image, that is, by the feature image of the gaze detection of the detection object (gaze detection), it is verified whether the detection object is alive. Through reflected light detection and gaze detection, it is judged and verified whether the detection object is alive, thereby improving the accuracy of liveness detection.

[0068] In an exemplary embodiment, as shown in FIG3 , determining whether the detected object is a living body according to the first facial feature image and the second facial feature image includes steps S302 to S306 . Among them:

[0069] Step S302, performing light reflection analysis on the first facial feature image to obtain a light reflection analysis result.

[0070] Optionally, the server or terminal performs light reflection analysis on the first facial feature image through a processor to obtain a light reflection analysis result, such as the light reflection analysis result is the natural scattering and absorption of the facial skin of the detection object, or the reflection intensity of the facial skin of the detection object is uneven and changes dynamically, or the reflection color of the facial skin of the detection object changes dynamically.

[0071] Step S304: extract eye feature data from the second facial feature image.

[0072] Optionally, the server or terminal uses at least one of advanced image processing and machine learning algorithms through a processor to extract eye feature data, where the eye feature data includes pupil position information, iris morphology change information, eye movement trajectory information, etc.

[0073] Step S306: determining the gaze information of the gaze dynamic detection image of the detection object according to the eye feature data.

[0074] Optionally, the server or the terminal analyzes the eye feature data through a processor to determine gaze information of the gaze dynamic detection image of the detection object, where the gaze information includes gaze direction, gaze duration, gaze stability, and the like.

[0075] Step S308: If the light reflection analysis result meets the liveness detection feature, and the gaze information matches the change information of the dynamic detection image, it is determined that the detection object is a live body.

[0076] Optionally, the light reflection analysis result meets the characteristics of liveness detection, such as the natural scattering and absorption of the facial skin of the test object meets the characteristics of liveness, and the reflection intensity of the facial skin of the test object meets the characteristics of liveness, for example, the characteristics of liveness require that the reflection intensity is uneven and changes dynamically. And the gaze information such as gaze direction, gaze duration and gaze stability matches the change information of the dynamic detection image. For example, if the dynamic detection image is presented in a clockwise direction, red images are displayed at the four corners of the image respectively, and the gaze direction of the test object should be consistent with the clockwise direction.

[0077] Optionally, when the light reflection analysis result meets the liveness detection feature, and the gaze information matches the change information of the dynamic detection image, the detection object is determined to be a live body. If the light reflection analysis result does not meet the liveness detection feature, or the gaze information does not match the change information of the dynamic detection image, the detection object is determined not to be a live body.

[0078] In this embodiment, under the two conditions that the light reflection analysis result meets the liveness detection characteristics and the gaze information matches the change information of the dynamic detection image, when both conditions are met, it is determined that the detection object is a live body, which can improve the accuracy of liveness detection.

[0079] In an exemplary embodiment, as shown in FIG4 , the method for determining whether the detected object is a living body includes step S402 and step S404. In which:

[0080] The eye feature data includes pupil position information, eye movement trajectory information and iris morphology change information; the gaze information includes gaze duration information and gaze direction information; based on the eye feature data, the gaze information of the gaze dynamic detection image of the detection object is determined, including step S402, based on the pupil position information, eye movement trajectory information and iris morphology change information, the gaze duration information and gaze direction information of the detection object's gaze dynamic detection image are determined.

[0081] Among them, pupil position information refers to the relative position or coordinates of the pupil in the eyeball. The pupil is a small circular hole in the center of the iris and is the channel for light to enter the eye. The pupil position information can reflect the direction of sight, because the direction of sight is usually associated with the center position of the pupil. By capturing the pupil position information, the gaze direction of the detected object can be inferred. Pupil position information is usually extracted from the eye image through image processing technology and used to calculate the direction of sight or the position of the gaze point.

[0082] Eye movement trajectory information refers to the path or trajectory of the eye movement over a period of time. Eye movements include gaze, saccade, and tracking. These movement trajectories can reflect the visual attention and information processing methods of the test subject. By capturing and analyzing eye movement trajectory information, we can understand the test subject's gaze path, gaze point dwell time, and transfer between gaze points when observing dynamic test images.

[0083] Iris morphological change information refers to changes in the iris' morphology, such as size. The iris is a flat, circular, thin membrane in the middle layer of the eyeball wall, located between the cornea and the lens. When the subject looks at a certain position, the iris will become smaller, otherwise the iris will become larger.

[0084] Gaze duration refers to the length of time a subject keeps their gaze on a specific area or object.

[0085] Gaze direction refers to the direction or orientation of the detected object's gaze.

[0086] Optionally, the terminal analyzes pupil position information, eye movement trajectory information, and iris morphology change information through a processor, and determines gaze duration information and gaze direction information of the detection object's gaze on the dynamic detection image based on the three types of information.

[0087] The change information includes position change information and change information of the duration of stay of the dynamic detection image; if the light reflection analysis result meets the liveness detection characteristics, and the gaze information matches the change information of the dynamic detection image, then the detection object is determined to be a living body, including step S404, if the light reflection analysis result meets the liveness detection characteristics, and the gaze direction information matches the position change information of the dynamic detection image, and the gaze duration information matches the change information of the duration of stay of the dynamic detection image, then the detection object is determined to be a living body.

[0088] Optionally, if the light reflection analysis result meets the liveness detection characteristics, and the gaze direction information matches the position change information of the dynamic detection image, and the gaze duration information matches the stay duration change information of the dynamic detection image, then the detection object is determined to be a live body.

[0089] For example, the dynamic detection image is divided into several areas, such as a 3*3 area, and the 9 areas are numbered clockwise from the upper right corner. The upper right corner area is numbered 1, the lower right corner area is numbered 3, the lower left corner area is numbered 5, the upper left corner area is numbered 7, and the middle area is 9. Assume that the dynamic detection image is filled with red in areas 1, 3, 5, and 7 clockwise, and the red stay time in each area is x milliseconds. The terminal extracts eye data based on the collected second facial feature image, and determines the gaze direction information and gaze duration information based on the eye information. If the gaze direction information is the direction information of the clockwise gaze area 1, 3, 5, and 7; and the detection object gazes at areas 1, 3, 5, and 7 for x milliseconds respectively. At this time, if the light reflection analysis result meets the liveness detection characteristics, it is determined that the detection object is alive.

[0090] In this embodiment, the gaze duration information and gaze direction information of the detection object staring at the dynamic detection image are determined through eye data, and it is judged whether the gaze duration information and gaze direction information match the dynamic detection image change information, so as to more accurately judge whether the detection object is alive.

[0091] In the previous embodiment, the gaze information further includes gaze stability. If the light reflection analysis result meets the liveness detection feature, and the gaze information matches the change information of the dynamic detection image, then the detection object is determined to be a live body, including: if the light reflection analysis result meets the liveness detection feature, the gaze information matches the change information of the dynamic detection image, and the gaze stability is greater than the stability threshold, then the detection object is determined to be a live body, wherein the stability threshold is determined based on the pupil position information, the eyeball movement trajectory information, and the iris morphology change information.

[0092] Among them, gaze stability represents the ability of the detected object to maintain a stable gaze direction. The stability threshold is calculated based on pupil position information, eye movement trajectory information, and iris morphology change information.

[0093] Optionally, the terminal extracts eye data based on the collected second facial feature image, determines gaze direction information and gaze duration information based on the eye information, and also determines gaze stability. If the gaze direction information is clockwise gaze direction information of areas 1, 3, 5, and 7; the detection object gazes at areas 1, 3, 5, and 7 for x milliseconds respectively, and the gaze stability is greater than the stability threshold, then if the light reflection analysis result meets the liveness detection feature, the detection object is determined to be a live body.

[0094] In this embodiment, by increasing gaze stability, the accuracy of determining whether the detected object is a living body can be improved.

[0095] In an exemplary embodiment, as shown in FIG5 , the method for determining whether the detected object is a living body includes steps S502 to S506. In which:

[0096] Performing light reflection analysis on the first facial feature image to obtain a light reflection analysis result includes: step S502, extracting light reflection information from the first facial feature image, the reflection information including at least one of reflection intensity, reflection distribution and reflection color.

[0097] Optionally, the terminal extracts light reflection information from the first facial feature image through a processor, and the reflection information includes at least one of reflection intensity, reflection distribution, and reflection color. For example, the terminal extracts the light reflection intensity; for example, the terminal extracts two of the information, such as the light reflection intensity and the light reflection distribution; for example, the terminal extracts three of the information, such as the reflection intensity, the reflection distribution, and the reflection color.

[0098] Step S504: determining a light reflection analysis result according to the reflection information, where the light reflection analysis result includes at least one of a reflection intensity analysis result, a reflection distribution analysis result and a reflection color analysis result.

[0099] Optionally, the terminal determines the light reflection analysis result according to the extracted reflection information through the processor. For example, if the terminal extracts the reflection intensity of the light, the reflection intensity analysis result is determined according to the reflection intensity of the light; if the terminal extracts two of the information, such as the reflection intensity of the light and the reflection distribution of the light, the reflection intensity analysis result and the reflection distribution analysis result are determined according to the reflection intensity of the light and the reflection distribution of the light; if the terminal extracts three of the information, reflection intensity, reflection distribution and reflection color, the reflection intensity analysis result, reflection distribution analysis result and reflection color analysis result are determined according to the reflection intensity of the light, the reflection distribution of the light and the reflection color of the light.

[0100] The liveness detection feature includes at least one of a first feature of uneven and dynamically changing reflection intensity, a second feature of uneven reflection distribution, and a third feature of dynamically changing reflection color; if the light reflection analysis result meets the liveness detection feature, and the gaze information matches the change information of the dynamic detection image, then the detection object is determined to be a live body, including step S506, if there is a reflection intensity analysis result that meets the first feature, the reflection distribution analysis result that meets the second feature, and the reflection color analysis result that meets the third feature, and the gaze information matches the change information of the dynamic detection image, then the detection object is determined to be a live body.

[0101] The living body detection feature includes at least one of a first feature of uneven and dynamically changing reflection intensity, a second feature of uneven reflection distribution, and a third feature of dynamically changing reflection color.

[0102] The reason for selecting the first feature: When light shines on a living face, the skin of the living face will produce tiny changes in reflection intensity due to physiological activities such as blood flow and micro-expressions. This change is continuous and natural. In contrast, if the detection object is a non-living object such as a photo or an image displayed on a screen, its reflection intensity is often more uniform and lacks dynamic changes.

[0103] Reason for selecting the second feature: The facial skin of a living person has complex texture and uneven surface structure, which causes uneven distribution of light when reflected. Specifically, light will be diffusely reflected at the tiny bumps on the skin, forming a unique reflection pattern. Non-living faces (such as photos) tend to have a relatively flat surface, and the distribution of reflected light is relatively uniform and lacks details. The texture and uneven structural features of the facial skin of a living person are detected. These features are usually difficult to replicate in photos or images displayed on the screen.

[0104] Reasons for selecting the third feature: Living skin will produce complex color changes under different light exposure, which is mainly due to the absorption and reflection of blood, pigments and other substances in the skin. In contrast, non-living faces (such as photos or screens) often lack such color changes. When different colors of light sources are used to illuminate the face, living skin will show different color reactions. By analyzing these color reactions, the authenticity of the detected object can be further confirmed. In addition, color features in color space can be used to distinguish between living and non-living objects.

[0105] Optionally, the terminal determines a light reflection analysis result according to at least one of the reflection information through a processor, where the light reflection analysis result includes at least one of a reflection intensity analysis result, a reflection distribution analysis result and a reflection color analysis result.

[0106] Optionally, the terminal extracts the reflection intensity, reflection distribution and reflection color from the second facial feature image, and determines the reflection intensity analysis result according to the reflection intensity of the light; determines the reflection distribution analysis result according to the reflection distribution of the light; and determines the reflection color analysis result according to the reflection color of the light. If there is a reflection intensity analysis result that meets the first feature, a reflection distribution analysis result that meets the second feature, and a reflection color analysis result that meets the third feature, and the gaze direction information matches the position change information of the dynamic detection image, the gaze duration information matches the stay duration change information of the dynamic detection image, and the gaze stability is greater than the stability threshold, then it is determined that the detected object is alive.

[0107] In this embodiment, the detection object is determined to be a living body by determining whether the reflection result meets the live body detection feature and whether the gaze information matches the change information of the dynamic detection image, thereby improving the detection accuracy.

[0108] In an exemplary embodiment, the dynamic detection image carries color information, position information and stay duration information; the method also includes: generating prompt information for use in conjunction with the color information, position information and stay duration information, the prompt information including at least one of a voice prompt and a text prompt, and the prompt information is used to guide the detection object to look at the dynamic detection image.

[0109] Optionally, the dynamic detection image is divided into several areas, for example, a 3*3 area, and 9 areas are numbered clockwise from the upper right corner. The upper right corner area is numbered 1, the lower right corner area is numbered 3, the lower left corner area is numbered 5, the upper left corner area is numbered 7, and the middle area is 9. Assume that the dynamic detection image is filled with red in areas 1, 3, 5, and 7 clockwise, and the red stay time in each area is x milliseconds; the dynamic detection image is filled with yellow in areas 2, 4, 6, and 8 clockwise, and the red stay time in each area is y milliseconds. Green is filled in the middle area 9, and the stay time is z milliseconds.

[0110] It should be noted that in all embodiments of the present application, the division of the area is not limited to 3*3, but can also be 4*4, or other uneven divisions, and can be divided according to actual conditions. The color, position, and duration of stay are not specifically limited.

[0111] Optionally, the terminal generates prompt information used in conjunction with the color information, position information and stay duration information carried by the dynamic detection image, and the detection object looks at the dynamic detection image according to the prompt information.

[0112] In scenarios where sound can be played out loud, the subject can choose voice prompts or text prompts. In scenarios where sound cannot be played out loud, the subject can choose text prompts. Examples of prompts: "Please look at the yellow area", "After looking at the yellow area, please look at the red area", etc.

[0113] In this embodiment, by cooperating with the prompt information and analyzing the facial data generated after the interaction with the detection object, the accuracy of detecting whether the object is alive can be improved.

[0114] In an exemplary embodiment, the face unlocking scenario of a mobile phone is used as an example for explanation. Before the detection object unlocks the mobile phone, the detection object will send a liveness detection request to the mobile phone, for example, pressing the power of the mobile phone to send a liveness detection request. The mobile phone generates a dynamic detection image according to the liveness detection request, and the dynamic detection image carries color information, location information and stay time information. If the dynamic detection image is divided into several areas, such as a 3*3 area, 9 areas are numbered clockwise from the upper right corner. Then the upper right corner area is numbered 1, the lower right corner area is numbered 3, the lower left corner area is numbered 5, the upper left corner area is numbered 7, and the middle area is 9. Assume that the dynamic detection image is filled with red in areas 1, 3, 5, and 7 clockwise, and the red stay time in each area is x milliseconds; the dynamic detection image is filled with yellow in areas 2, 4, 6, and 8 clockwise, and the red stay time in each area is y milliseconds. Fill green in the middle area 9, and the stay time is z milliseconds.

[0115] The mobile phone displays the dynamic detection image through a display screen and projects light according to the dynamic detection image.

[0116] The mobile phone generates a dynamic detection image randomly through a processor, and generates prompt information used in conjunction with the color information, location information, and dwell time information. The prompt information includes a voice prompt, and the prompt information is used to guide the detection object to look at the dynamic detection image. Examples of prompt information: "Please look at the yellow area" and "After looking at the yellow area, please look at the red area." The detection object looks at the dynamic detection image according to the prompt information.

[0117] The mobile phone obtains a first facial feature image after the detection object's face reflects the light and a second facial feature image of the detection object looking at the dynamic detection image through a processor. The mobile phone extracts the reflection information of the light from the first facial feature image through a processor, and the reflection information includes reflection intensity, reflection distribution and reflection color; determines the reflection intensity analysis result according to the reflection intensity of the light; determines the reflection distribution analysis result according to the reflection distribution of the light; and determines the reflection color analysis result according to the reflection color of the light.

[0118] The mobile phone uses at least one of advanced image processing and machine learning algorithms through a processor to extract eye feature data, which includes pupil position information, iris morphological change information, eye movement trajectory information, etc. The terminal determines the gaze duration information and gaze direction information of the detection object gazing at the dynamic detection image through a processor based on the pupil position information, the eye movement trajectory information, and the iris morphological change information.

[0119] The liveness detection features include a first feature of uneven and dynamically changing reflection intensity, a second feature of uneven reflection distribution, and a third feature of dynamically changing reflection color; and when the gaze direction information matches the position change information of the dynamic detection image, the gaze duration information matches the dwell time change information of the dynamic detection image, and the gaze stability is greater than a stability threshold, it is determined that the detection object is a live body, wherein the stability threshold is determined based on pupil position information, eye movement trajectory information, and iris morphology change information.

[0120] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0121] Based on the same inventive concept, the embodiment of the present application also provides an interactive liveness detection device for implementing the interactive liveness detection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more interactive liveness detection device embodiments provided below can refer to the limitations of the interactive liveness detection method above, and will not be repeated here.

[0122] In an exemplary embodiment, as shown in FIG6 , an interactive living body detection device is provided, including: a generating module 601, a display projection module 602, an acquiring module 603 and a determining module 604, wherein:

[0123] The generating module 601 is used to randomly generate a dynamic detection image in response to a living body detection request.

[0124] The display projection module 602 is used to display the dynamic detection image through the display screen and project light according to the dynamic detection image.

[0125] The acquisition module 603 is used to acquire a first facial feature image after the detection object's face reflects the light and a second facial feature image of the detection object staring at the dynamic detection image.

[0126] The determination module 604 is used to determine whether the detected object is a living body according to the first facial feature image and the second facial feature image.

[0127] In an exemplary embodiment, the determination module 604 includes:

[0128] The analysis unit is used to perform light reflection analysis on the first facial feature image to obtain a light reflection analysis result.

[0129] The extraction unit is used to extract eye feature data from the second facial feature image.

[0130] The gaze information determining unit is used to determine the gaze information of the gaze dynamic detection image of the detection object according to the eye feature data.

[0131] The living body determination unit is used to determine that the detection object is a living body if the light reflection analysis result meets the living body detection characteristics and the gaze information matches the change information of the dynamic detection image.

[0132] In an exemplary embodiment, the eye feature data includes pupil position information, eyeball movement trajectory information, and iris morphology change information; the gaze information includes gaze duration information and gaze direction information; the gaze information determination unit includes:

[0133] The gaze information determination subunit is used to determine the gaze duration information and gaze direction information of the detection object's gaze on the dynamic detection image according to the pupil position information, the eye movement trajectory information and the iris morphology change information.

[0134] The change information includes position change information and dynamic detection image retention time change information; the living body determination unit includes:

[0135] The first living body determination subunit is used to determine that the detection object is a living body if the light reflection analysis result meets the living body detection characteristics, and the gaze direction information matches the position change information of the dynamic detection image, and the gaze duration information matches the stay duration change information of the dynamic detection image.

[0136] In an exemplary embodiment, the gaze information further includes gaze stability, where the gaze stability represents the ability to maintain a stable gaze direction; the living body determination unit includes:

[0137] The second living body determination subunit is used to determine that the detection object is a living body if the light reflection analysis result meets the living body detection characteristics, the gaze information matches the change information of the dynamic detection image, and the gaze stability is greater than the stability threshold, wherein the stability threshold is determined based on the pupil position information, the eye movement trajectory information and the iris morphology change information.

[0138] In an embodiment of an embodiment, the analysis unit includes:

[0139] The extraction subunit is used to extract the reflection information of the light from the first facial feature image, where the reflection information includes at least one of reflection intensity, reflection distribution and reflection color.

[0140] The analysis subunit is used to determine the light reflection analysis result according to the reflection information, and the light reflection analysis result includes at least one of the reflection intensity analysis result, the reflection distribution analysis result and the reflection color analysis result.

[0141] The liveness detection feature includes at least one of a first feature of uneven and dynamically changing reflection intensity, a second feature of uneven reflection distribution, and a third feature of dynamically changing reflection color; and a liveness determination unit, including:

[0142] The third living body determination subunit is used to determine that the detection object is a living body if there is at least one of the reflection intensity analysis result conforming to the first feature, the reflection distribution analysis result conforming to the second feature and the reflection color analysis result conforming to the third feature, and the gaze information matches the change information of the dynamic detection image.

[0143] In an embodiment of an embodiment, the dynamic detection image carries color information, position information and stay time information; the interactive living body detection device also includes:

[0144] The prompt information generation module is used to generate prompt information used in conjunction with color information, location information and stay duration information. The prompt information includes at least one of voice prompt and text prompt. The prompt information is used to guide the detection object to look at the dynamic detection image.

[0145] Each module in the above-mentioned interactive liveness detection device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0146] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG7. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store interactive liveness detection related data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an interactive liveness detection method is implemented.

[0147] Those skilled in the art will understand that the structure shown in FIG. 7 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0148] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0149] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0150] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0151] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0152] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0153] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An interactive liveness detection method, characterized in that: The method comprises: In response to a liveness detection request, randomly generating a dynamic detection image; Displaying the dynamic detection image through a display screen, and projecting light according to the dynamic detection image; Acquire a first facial feature image after the detection object's face reflects the light and a second facial feature image of the detection object gazing at the dynamic detection image; Determine whether the detection object is a living body according to the first facial feature image and the second facial feature image.

2. The method according to claim 1, characterized in that The step of determining whether the detected object is a living body according to the first facial feature image and the second facial feature image includes: Performing light reflection analysis on the first facial feature image to obtain a light reflection analysis result; extracting eye feature data from the second facial feature image; Determining gaze information of the detection object fixating on the dynamic detection image according to the eye feature data; If the light reflection analysis result meets the living body detection feature, and the gaze information matches the change information of the dynamic detection image, it is determined that the detection object is a living body.

3. The method according to claim 2, characterized in that The eye feature data includes pupil position information, eyeball movement trajectory information and iris morphology change information; the gaze information includes gaze duration information and gaze direction information; the determination of the gaze information of the detection object on the dynamic detection image based on the eye feature data includes: Determining the gaze duration information and gaze direction information of the detection object gazing at the dynamic detection image according to the pupil position information, the eyeball movement trajectory information and the iris morphology change information; The change information includes position change information and change information of the duration of the dynamic detection image; if the light reflection analysis result meets the liveness detection feature, and the gaze information matches the change information of the dynamic detection image, then determining that the detection object is a live body includes: If the light reflection analysis result meets the liveness detection feature, and the gaze direction information matches the position change information of the dynamic detection image, and the gaze duration information matches the stay duration change information of the dynamic detection image, then it is determined that the detection object is a live body.

4. The method according to claim 2, characterized in that: The gaze information also includes gaze stability, and the gaze stability represents the ability to maintain a stable gaze direction; if the light reflection analysis result meets the liveness detection feature, and the gaze information matches the change information of the dynamic detection image, then determining that the detection object is a live body includes: If the light reflection analysis result meets the liveness detection characteristics, the gaze information matches the change information of the dynamic detection image, and the gaze stability is greater than the stability threshold, then the detection object is determined to be a live body, wherein the stability threshold is determined based on pupil position information, eye movement trajectory information and iris morphology change information.

5. The method according to claim 2, characterized in that: The performing light reflection analysis on the first facial feature image to obtain a light reflection analysis result includes: extracting reflection information of light from the first facial feature image, wherein the reflection information includes at least one of reflection intensity, reflection distribution and reflection color; Determine a light reflection analysis result according to the reflection information, wherein the light reflection analysis result includes at least one of a reflection intensity analysis result, a reflection distribution analysis result and a reflection color analysis result; The liveness detection feature includes at least one of a first feature of uneven and dynamically changing reflection intensity, a second feature of uneven reflection distribution, and a third feature of dynamically changing reflection color; if the light reflection analysis result meets the liveness detection feature, and the gaze information matches the change information of the dynamic detection image, determining that the detection object is a live body includes: If at least one of the reflection intensity analysis result conforms to the first feature, the reflection distribution analysis result conforms to the second feature, and the reflection color analysis result conforms to the third feature, and the gaze information matches the change information of the dynamic detection image, it is determined that the detection object is a living body.

6. The method according to any one of claims 1 to 5, characterized in that The dynamic detection image carries color information, location information and stay time information; the method further includes: Prompt information is generated for use in conjunction with the color information, location information, and dwell time information, wherein the prompt information includes at least one of a voice prompt and a text prompt, and the prompt information is used to guide the detection object to gaze at the dynamic detection image.

7. An interactive living body detection device, characterized in that: The device comprises: A generating module, used for randomly generating a dynamic detection image in response to a liveness detection request; A display projection module, used for displaying the dynamic detection image through a display screen and projecting light according to the dynamic detection image; An acquisition module, used for acquiring a first facial feature image after the detection object's face reflects the light and a second facial feature image of the detection object gazing at the dynamic detection image; A determination module is used to determine whether the detection object is a living body according to the first facial feature image and the second facial feature image.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images