Vehicle authentication system

Abstract

This invention belongs to the field of vehicle authentication systems. A transparent display mounted on the vehicle, A projector positioned to project light onto a person through the aforementioned transparent display, A camera positioned to receive light from a person through a transparent display, A processor configured to receive an image from the camera and determine whether the person captured in the image is an authenticated person, and configured to output a signal indicating whether the person captured in the image is an authenticated person, This relates to a vehicle authentication system equipped with the following features.

Description

Technical Field

[0001] The present invention relates to a vehicle authentication system. It relates to a vehicle authentication system, the use of an authentication system for controlling a vehicle, a vehicle including the authentication system, a method for authenticating a person inside the vehicle, and a non-temporary computer-readable medium including instructions for a method for authenticating a person inside the vehicle.

Background Art

[0002] Conventionally, user authentication in a vehicle is performed via a key, so any user with the correct key is considered authenticated. In this method, theft of the key allows access to the vehicle, starting the engine, and using all other functions of the vehicle. Since the key can be easily stolen, a more sophisticated method for controlling the vehicle is desired.

[0003] Patent Document 1 (WO 2021 / 218180 A1) discloses a method for controlling the unlocking of a vehicle door, including evaluating the detection of a person's face image. Patent Document 2 (CN 114120484 A) discloses a face recognition system for determining whether a person is a legitimate user. In both cases, the camera is visibly attached to the automobile. For this reason, there is a drawback that the face authentication system can be more easily recognized and a method for avoiding such a system can be more easily found.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0005] Therefore, the object of the present invention is to provide a vehicle authentication system that does not have the drawbacks of the prior art. [Means for solving the problem]

[0006] The purpose is as follows: A transparent display mounted on the vehicle, A projector positioned to project light onto a person through the aforementioned transparent display, A camera positioned to receive light from a person through the aforementioned transparent display, A processor configured to receive an image from the camera and determine whether the person captured in the image is an authenticated person, and further configured to output a signal indicating whether the person captured in the image is an authenticated person, This was achieved through a vehicle authentication system that included [unclear / vehicle-specific features].

[0007] The present invention further relates to the use of the authentication system of the present invention for controlling a vehicle.

[0008] The present invention further relates to a vehicle equipped with the authentication system according to the present invention.

[0009] The present invention further includes the following steps: The process involves shining light onto a person through a transparent display mounted on the vehicle, The steps include recording a person's image through a transparent display, A step to determine whether the person being photographed is the person who has been authenticated, A step of outputting a signal indicating whether the person captured in the image is a person who has been authenticated, This concerns methods for authenticating individuals inside a vehicle, including [specific details omitted].

[0010] The present invention further relates to a non-temporary computer-readable medium that, when executed by one or more processors, includes instructions causing one or more processors to perform a method according to the present invention.

[0011] Steps that illuminate people with light through a transparent display mounted on the vehicle, Steps to record a person's image through a transparent display, A step to determine whether the person being photographed is a verified person, and A step of outputting a signal indicating whether the person captured in the image is a person who has been authenticated.

[0012] In another embodiment, the present invention relates to a method for determining the state of a driver, the method comprising the following steps: - A step that triggers the illumination of the driver with light through a transparent display mounted on the vehicle. - A step that triggers the recording of the driver's image through a transparent display while the driver is illuminated by light. - A step of determining a condition indicator related to the driver's condition based on the image, - A step of providing a status indicator, Includes.

[0013] In another embodiment, the present invention relates to a method for accessing a vehicle and / or a vehicle function, the method comprising the following steps: - A step that triggers the projection of light onto a person through a transparent display mounted on the vehicle. - A step that triggers the recording of a person's image through a transparent display while the driver is illuminated by light. - A step of determining whether the person is a verified person based on the image. - A step of granting access to the vehicle and / or the vehicle's functions based on the determination that the person is an authenticated person, Includes.

[0014] By arranging a projector and a camera behind a transparent display, the authentication system is not visible to the user. The projector and the camera can be installed anywhere behind the display. In the case of multiple displays that are common in recent automobiles, it becomes unclear even which display the authentication system is arranged on. Therefore, it becomes difficult to operate the vehicle in a stolen vehicle. Furthermore, by arranging the projector and the camera behind the display, there is also an advantage that the authentication system does not require extra space on the surface such as a dashboard. As a result, designers can use other spaces and the degree of freedom for an attractive appearance increases. Also, by hiding the projector and the camera, there is an advantage that the driver's attention is not distracted and it is difficult to feel being monitored.

[0015] This authentication system is suitable for various vehicles such as automobiles, motorcycles, buses, trucks, trains, or airplanes.

[0016] The authentication system includes a transparent display. The term "display" may represent a device of any shape configured to display items of information. The items of information may be any information such as at least one image, at least one diagram, at least one histogram, at least one graphic, text, numbers, at least one symbol, or an operation menu. The display may be at least one screen or may include at least one screen. The display may have any shape, for example, a rectangular shape. The display may be a front display of the device.

[0017] The display may be at least one organic light emitting diode (OLED) display or may include at least one organic light emitting diode (OLED) display. The term "organic light emitting diode" may represent a light emitting diode (LED) that is a film of an organic compound configured to emit light in response to an electric current. The organic OLED display may be configured to emit visible light. The display, particularly the display area, may be covered with glass. In particular, the display may include at least one glass cover.

[0018] The transparent display is at least partially transparent. The term "at least partially transparent" may particularly represent the characteristic of a display that at least partially transmits light in a certain wavelength range, for example, in the infrared spectrum region, particularly in the near-infrared spectrum region. For example, the display may be translucent in the near-infrared region. For example, the display may have a transparency of 20% to 50% in the near-infrared region. Also, it may have different transparencies in other wavelength ranges. For example, the display may have a transparency of more than 80%, preferably more than 90%, with respect to the visible spectrum region. The transparent display may be at least partially transparent throughout the display area or may be only partially transparent. Generally, it is sufficient if only a part of the display area through which light needs to pass from a projector or a camera is at least partially transparent. In particular, the transparent display may be at least partially transparent in the part where the projector and / or the camera are covered by the display.

[0019] A display includes a display area. The term “display area” may also refer to the active area of ​​the display, particularly the activatable area. The display may have additional areas such as recesses or cutouts. The display may have a first area associated with a first pixel per inch (PPI) value and a second area associated with a second PPI value. The first PPI value may be lower than the second PPI value, preferably the first PPI value is 400 PPI or less, and more preferably the second PPI value is 300 PPI or more. The first PPI value may also be associated with at least one continuous area being at least partially transparent.

[0020] The transparent display can be mounted in a vehicle. It can be installed in various locations, such as on the outside or inside of the vehicle. When installed on the outside, it can be integrated into the vehicle body, doors, windows, mirrors, between windows, for example, in the B-pillar of the car. When installed inside the vehicle, it can be integrated into the steering wheel, in place of the speedometer, in the center of the dashboard, inside the mirror, inside the window, etc.

[0021] The authentication system further includes a projector for shining light onto the person. The term “light” may refer to one or more electromagnetic radiation from the spectral ranges of infrared, visible light, and ultraviolet. Here, the term “ultraviolet spectral range” generally refers to electromagnetic radiation having wavelengths of 1 nm to 380 nm, preferably 100 nm to 380 nm. Furthermore, according to a portion of the ISO-21348 standard in effect as of the date of this document, the term “visible spectral range” generally refers to the spectral range from 380 nm to 760 nm. The term “infrared spectral range” (IR) generally refers to electromagnetic radiation from 760 nm to 1000 μm, with the range from 760 nm to 1.5 μm usually denoted as the “near-infrared spectral range” (NIR), the range from 1.5 μm to 15 μm as the “mid-infrared spectral range” (MidIR), and the range from 15 μm to 1000 μm as the “far-infrared spectral range” (FIR). Preferably, the light used for a typical purpose of the present invention is light in the infrared (IR) spectral range, more preferably light in the near-infrared (NIR) and / or mid-infrared (MidIR) spectral range, and in particular light having wavelengths of 1 μm to 5 μm, preferably 1 μm to 3 μm.

[0022] The term “illuminate” may also refer to the process of illuminating at least one element with light. The term “projector” may also refer to a device configured to generate or provide light, in the sense defined above. A projector may be a pattern projector, a flood projector, or both, or it may repeatedly switch between patterned light and flood light.

[0023] The term “pattern projector” may also refer to a device configured to generate or provide at least one light pattern, in particular at least one infrared light pattern. The term “light pattern” may also refer to at least one pattern comprising multiple light spots. The light spots may be at least partially spatially extended. At least one spot or any spot may have any shape. In some cases, a circular shape of at least one spot or any spot may be preferred. The spots may be arranged considering the structure of a display comprising a device further comprising optoelectronic devices. Typically, the arrangement of an OLED-pixel structure of a display may be considered. The term “infrared light pattern” may also refer to a light pattern comprising spots in the infrared spectral region. The infrared light pattern may also be a near-infrared light pattern. The infrared light may be coherent. The infrared light pattern may also be a coherent infrared light pattern.

[0024] The pattern projector may be configured to emit light of a single wavelength, for example, in the near-infrared region. In other embodiments, the pattern projector may be adapted to emit light of multiple wavelengths, for example, to enable additional measurements in other wavelength channels.

[0025] The infrared light pattern may consist of at least one regular and / or constant and / or periodic pattern, such as a triangular pattern, a rectangular pattern, a hexagonal pattern, or a pattern that further includes a convex slope. For example, the infrared light pattern may be a hexagonal pattern, preferably a hexagonal infrared light pattern, and more preferably a 2 / 5 hexagonal infrared light pattern.

[0026] By using a periodic 2 / 5 hexagonal pattern, artifacts can be distinguished from usable signals.

[0027] At least one of the infrared light spots may have a beam divergence of 0.2° to 0.5°, preferably 0.1° to 0.3°. The term "beam divergence" may represent at least one measure (index) of the increase of at least one diameter and / or at least one diameter equivalent, such as radius, with respect to the distance from the optical aperture from which the beam is emitted. This index may be an angle or an angle equivalent. In the context of the present invention, typically, beam divergence is 1 / e 2 It's fine if the decision is made that way.

[0028] A pattern projector may include at least one pattern projector configured to generate an infrared light pattern. A pattern projector may include at least one emitter, in particular multiple emitters. The term “emitter” may also refer to at least one arbitrary device configured to provide at least one light beam. The light beam may generate an infrared light pattern. The emitter may include at least one element selected from the group consisting of at least one laser light source such as at least one semiconductor laser, at least one double heterostructure laser, at least one external resonator laser, at least one isolated confinement heterostructure laser, at least one quantum cascade laser, at least one distributed Bragg reflector laser, at least one polariton laser, at least one hybrid silicon laser, at least one extended resonator diode laser, at least one quantum dot laser, at least one volume Bragg grating laser, at least one indium arsenide laser, at least one gallium arsenide laser, at least one transistor laser, at least one diode-excited laser, at least one distributed feedback laser, at least one quantum well laser, at least one interband cascade laser, at least one semiconductor ring laser, at least one vertical resonator surface-emitting laser (VCSEL); and at least one non-laser light source such as at least one LED or at least one light bulb. For example, a pattern projector includes at least one VCSEL, preferably multiple VCSELs. Multiple VCSELs may be arranged, for example, in at least one array containing a matrix of VCSELs. VCSELs may be arranged on the same substrate or on different substrates. The term "vertical cavity surface-emitting laser" may also refer to a semiconductor laser diode configured to emit a laser beam perpendicular to the upper surface. Examples of VCSELs can be found, for example, at ja.wikipedia.org / wiki / Verticalcavity_surface-emitting_laser.VCSELs are generally known to those skilled in the art from WO 2017 / 222618 A, etc., and each VCSEL is configured to produce at least one light beam. Multiple produced spots may be associated with an infrared light pattern. VCSELs may be configured to emit light beams in the wavelength range of 800–1000 nm. For example, a VCSEL may be configured to emit light beams at 808 nm, 850 nm, 940 nm, and / or 980 nm. Preferably, a VCSEL emits light at 940 nm, as terrestrial solar radiation has locally minimum irradiance at this wavelength, as described in CIE 085-1989 "Solar spectral Irradiance".

[0029] The pattern projector may include at least one optical element configured to increase the number of spots generated by the pattern projector and / or to duplicate the pattern, for example, to make it double or triple. Other multiplication factors are also possible. The pattern projector, in particular the optical elements, may include at least one diffractive optical element (DOE) and / or at least one metasurface element. The DOE and / or metasurface element may be configured to generate multiple light beams from a single incident light beam. Further arrangements are possible, in particular, including a different number of projection VCSELs and / or at least one different optical element configured to increase the number of spots. For example, the generated laser spots may be duplicated by using a VCSEL or multiple VCSELs and at least one DOE.

[0030] A pattern projector may include at least one transfer device. The term “transfer device” may also be written as “transfer system” and may refer to one or more optical elements adapted to modify a light beam, particularly a light beam used to generate at least a portion of an infrared light pattern, by changing one or more of the beam parameters of the light beam, the width of the light beam, or the direction of the light beam. A transfer device may include at least one imaging optical device. Specifically, a transfer device may include one or more of the following: at least one lens, e.g., at least one lens selected from the group consisting of at least one adjustable lens, at least one aspherical lens, at least one spherical lens, and at least one Fresnel lens; at least one diffractive optical element; at least one concave mirror; at least one beam deflection element, preferably at least one mirror; at least one beam splitting element, preferably at least one beam splitting cube or beam splitting mirror; at least one multi-lens system; at least one holographic optical element; at least one meta-optical element. Specifically, a transfer device may include at least one refractive optical lens stack. Therefore, the transfer device may include a multi-lens system having refractive properties.

[0031] The pattern projector may be configured to emit modulated or unmodulated light. If multiple emitters are used, different emitters may have different modulation frequencies, which can be used, for example, to distinguish between light beams.

[0032] The light beam or beam beam generated by the pattern projector may propagate parallel to the optical axis. The pattern projector may include at least one reflective element, preferably at least one prism, for deflecting the illumination light beam onto the optical axis. For example, the angle between the light beam or beam beam, such as a laser light beam, and the optical axis may be less than 10°, preferably less than 5°, and even less than 2°. However, other embodiments are also possible. Furthermore, the light beam or beam beam may be on the optical axis or off-axis. For example, the light beam or beam beam may be parallel to the optical axis at a distance of less than 10 mm from the optical axis, preferably less than 5 mm from the optical axis, or even less than 1 mm from the optical axis, or it may coincide with the optical axis.

[0033] The term “flood projector” may also refer to at least one device (apparatus) configured to provide substantially continuous spatial illumination. The flood projector may illuminate a measurement area, such as a user, a part of a user, and / or the user’s face, with a spatially constant or substantially constant illumination intensity. The term “flood light” may also refer to substantially continuous spatial illumination, particularly diffuse illumination and / or uniform illumination. Flood light has wavelengths in the infrared region, particularly the near-infrared region. The flood projector may include at least one VCSEL and / or at least one LED, preferably multiple VCSELs and / or LEDs. The term “substantially continuous spatial illumination” may also refer to uniform spatial illumination, where non-uniform areas are also possible.

[0034] The relative distance between the flood projector and the pattern projector may be less than 3.0 mm. The relative distance between the flood projector and the pattern projector may be less than 2.5 mm, preferably less than 2.0 mm. The pattern projector and the flood projector may be combined into a single module. For example, the pattern projector and the flood projector may be placed on the same substrate (particularly having a minimum relative distance). The minimum relative distance can be defined by the physical extension of the flood projector and the pattern projector. By arranging the pattern projector and the flood projector with a relative distance of 3.0 mm or less, the space requirements for the two projectors can be reduced. In particular, the projectors can be combined into a single module. Such reduction in space requirements can reduce the transparent area of ​​the display required for the operation of the projector behind the display.

[0035] In one embodiment, the pattern projector and the flood projector may include at least one VCSEL, preferably a plurality of VCSELs. The pattern projector may include a plurality of first VCSELs mounted on a first platform. The flood projector may include a plurality of second VCSELs mounted on a second platform. The second platform may be located next to the first platform. The optoelectronic device may include a heat sink. A first increment including the first platform may be mounted on the heat sink. A second increment including the second platform may be mounted on the heat sink. The second increment may be different from the first increment. Thus, the first platform may be further away from optical elements configured to increase the number of spots, for example, to duplicate them. The second platform may be located closer to the optical elements. The beams emitted from the second VCSELs may be defocused, resulting in overlapping spots. This results in substantially continuous illumination, and therefore flood illumination.

[0036] The projector is positioned to project light through a transparent display. Therefore, the light emitted from the projector crosses the transparent display before hitting the person. From the person's perspective, the projector is positioned behind the transparent display. The authentication system further comprises a camera. The term “camera” may also refer to at least one unit of an optoelectronic device configured to generate at least one image. Images may be generated via hardware and / or software interfaces, which may also be considered cameras. The term “image generation” may refer to capturing and / or generating and / or determining and / or recording at least one image using the camera. Image generation may include capturing and / or recording an image. Image generation may include capturing multiple images, such as a single image and / or a sequence of images. If images are generated via hardware and / or software interfaces, the capturing and / or generating and / or determining and / or recording of images may be triggered and / or initiated by the hardware and / or software interfaces. For example, image generation may include sequentially recording a series of images, such as a video or movie. Image generation may be initiated by user action, or it may be initiated automatically, for example, when the presence of at least one object or user in the field of view and / or within a given sector of the camera's field of view is automatically detected.

[0037] The camera may include at least one optical sensor, in particular at least one pixelated optical sensor. The camera may include at least one CMOS sensor or at least one CCD chip. For example, the camera may include at least one CMOS sensor that is sensitive to the infrared spectral range. The term “image” may also refer to data recorded using the optical sensor, such as multiple electronic readings from a CMOS or CCD chip. The image may include raw image data or a pre-processed image. For example, pre-processing may include applying at least one filter to the raw image data and / or applying at least one background correction and / or at least one background subtraction.

[0038] For example, the camera may include a color camera consisting of at least color pixels. The camera may include a color CMOS camera. For example, the camera may include monochrome pixels and color pixels. The color pixels and monochrome pixels may be combined within the camera. The camera may include at least one color camera (e.g., RGB) and / or at least one monochrome camera (e.g., monochrome CMOS). The camera may include at least one monochrome CMOS chip. The camera may generally include a one-dimensional or two-dimensional array of image sensors such as pixels. The camera may include an IR camera, in particular an NIR camera. The camera may include an IR-sensitive CMOS chip and / or CCD chip, preferably a CMOS chip and / or CCD chip sensitive to the NIR range.

[0039] The color camera may be an internal and / or external camera of the device constituting the optoelectronic device. The internal and / or external camera of the device may be accessed via a hardware and / or software interface included in the optoelectronic device used as a camera. If the device is a smartphone or includes a smartphone, the image generation unit may be a front camera such as a selfie camera and / or the smartphone's back camera.

[0040] The camera may have a field of view between 10°x10° and 75°x75°, preferably between 55°x65°. The camera resolution is less than 2MP, preferably between 0.3MP and 1.5MP.

[0041] The camera may include one or more optical elements, such as one or more lenses. For example, the optical sensor may be a fixed-focus camera having at least one lens fixedly adjusted relative to the camera. Alternatively, the camera may include one or more variable lenses that are automatically or manually adjusted. However, other cameras are also possible.

[0042] The term “pattern image” may also refer to an image generated by a camera while an infrared light pattern is being irradiated, for example, an image on an object and / or a user. The pattern image may include an image showing the user, in particular at least a portion of the user’s face, and in particular images on each region of interest composed of the image, while the user is being illuminated by the infrared light pattern. The pattern image may be generated by capturing and / or recording light reflected by the object and / or user being illuminated by the infrared light pattern. A pattern image showing a user may include at least a portion of the illuminated infrared light pattern on at least a portion of the user. For example, illumination by a pattern illumination light source and imaging using a photosensor may be synchronized, for example, using at least one control unit of an optoelectronic device.

[0043] The term "flood image" may also refer to an image generated by a camera while an illumination source is illuminating, for example, an object and / or a user with infrared flood light. The flood image may include an image of the user, particularly an image of the user's face, while the user is illuminated by the flood light. The flood image may also be generated by capturing and / or recording the light reflected by the object and / or user that is illuminated by the flood light. A flood image of a user may include at least a portion of the flood light that illuminates at least a portion of the user. For example, illumination by a flood illumination source and imaging using a photosensor may be synchronized, for example, using at least one control unit of an optoelectronic device.

[0044] The camera may be configured to capture and / or record pattern images and flood images simultaneously or at different times. The camera may be configured to capture and / or record pattern images and flood images in at least partially overlapping measurement areas or areas corresponding to measurement areas.

[0045] The camera is positioned to receive light from the person through a transparent display. Light reflected or refracted from the person first passes through the transparent display before entering the camera. From the person's perspective, the camera is positioned behind the transparent display.

[0046] The authentication system further comprises a processor. The processor may be a logic circuit configured to perform basic operations of a computer or system, and / or, generally, a device configured to perform calculations or logical operations. In particular, the processor may be configured to process basic instructions that drive the computer or system. As an example, the processor may include at least one arithmetic logic unit (ALU), at least one floating-point unit (FPU), such as a mathematical coprocessor or a numerical coprocessor, a plurality of registers, specifically registers configured to supply operands to the ALU and store the results of calculations, and memory such as L1 cache memory and L2 cache memory. In particular, the processor may be a multi-core processor. Specifically, the processor may be a central processing unit (CPU) or include a central processing unit (CPU). In addition or alternatively, the processor may be a microprocessor or include a microprocessor, and therefore, specifically, the elements of the processor may be contained in a single integrated circuit (IC) chip. In addition or alternatively, the processor may be one or more chips, such as one or more application-specific integrated circuits (ASICs) and / or one or more field-programmable gate arrays (FPGAs) and / or one or more tensor processing units (TPUs) and / or dedicated machine learning optimization chips. The processor may be configured to perform one or more evaluation operations, specifically by software programming or the like. At least one or any component of the computer program configured to perform the authentication process may be executed by the processing device. Alternatively or additionally, the processing device may be a connection interface or include a connection interface. The connection interface may be configured to transfer data from the device to a remote device, or vice versa. At least one or any component of the computer program configured to perform the authentication process may be executed by the remote device.

[0047] The processor may be configured to perform one or more evaluation operations, specifically through software programming or the like. At least one or any component of a computer program configured to perform the authentication process may be executed by the processing unit. Alternatively or additionally, the processing unit may be a connection interface or include a connection interface. The connection interface may be configured to transfer data from a device to a remote device, or vice versa. At least one or any component of a computer program configured to perform the authentication process may be executed by a remote device.

[0048] The processor may be configured to identify a user based on the flood images. Thus, in particular, the processor may transfer data to a remote device. Alternatively or additionally, the processor may perform user identification based on the flood images, in particular by executing appropriate computer programs having their respective functions. The term “identify” may also mean identity verification and / or verifying the identity of a user. User identification may include analyzing the flood images. Analyzing the flood images may include performing face verification to determine that the captured face is the face of a user. User identification may include, for example, matching a flood image showing the contours of a part of the user, in particular a part of the user’s face, to a template. Determining whether the captured face is the face of a user may include identifying the user, in particular, determining whether the captured face corresponds to at least one image of the user’s face stored, for example, in at least one memory of the device.

[0049] The analysis may include one or more of the following: filtering; selection of at least one region of interest; formation of a difference image between the flood image and at least one offset; inversion of the flood image; background correction; decomposition into color channels; decomposition into hue, saturation, and brightness channels; frequency decomposition; singular value decomposition; application of a Canney edge detector; application of the Laplacian of a Gaussian filter; application of a difference Gaussian filter; application of the Sobel operator; application of the Laplace operator; application of the Shah operator; application of the Priwitt operator; application of the Roberts operator; application of the Kirsch operator; application of a high-pass filter; application of a low-pass filter; application of the Fourier transform; application of the Radon transform; application of the Hough transform; application of the wavelet transform; thresholding; and creation of a binary image. The region of interest may be determined manually by the user or automatically by recognizing the user in the image, for example. In particular, the analysis of the flood image may include the use of at least one image recognition technique, in particular a face recognition technique. The image recognition technique includes at least one process for identifying a user in the image. Image recognition may include using at least one technique selected from techniques such as color-based image recognition using features like hue, saturation, and lightness (HSV) or red, green, and blue (RGB); template matching as exemplified at https: / / www.mathworks.com / help / vision / ug / pattern-matching.html; image segment and / or blob analysis using size, color, or shape; and machine learning and / or deep learning using at least one convolutional neural network. The neural network may be trained by a user in a training procedure in which the user is instructed to take at least one or more photographs showing themselves.

[0050] The analysis of the flood image may include determining multiple facial features. The analysis may include comparing the determined facial features with template features, in particular matching them. The template features may be features extracted from at least one template. The template may be, or include, at least one image generated in a registration process, such as when initializing an authentication system. The template may also be an image of an authenticated user. The template features and / or facial features may include vectors. Feature matching may include determining the distance between vectors. User identification may include comparing the distance between vectors to at least one predefined threshold value, where the user is successfully identified if the distance is at least within an acceptable range and equal to or less than the predefined threshold value. Otherwise, the user is rejected or denied.

[0051] For example, image recognition involves using a trained model that includes at least one model, particularly at least one face recognition model. Analysis of flooded images is described, for example, in Florian Schroff, Dmitry Kalenichenko, and James Philbin, "FaceNet: A Unified Embedding for Face Recognition and Clustering," arXiv:1503.03832. The trained model may include at least one convolutional neural network. For example, the convolutional neural network may be designed as described in MD Zeiler and R. Fergus, "Visualizing and understanding convolutional networks," CoRR, abs / 1311.2901, 2013, or C. Szegedy et al., "Going deeper with convolutions," CoRR, abs / 1409.4842, 2014. For more information on convolutional neural networks for face recognition systems, see Florian Schroff, Dmitry Kalenichenko, James Philbin, "FaceNet: A Unified Embedding for Face Recognition and Clustering", arXiv:1503.03832. Labeled image data from an image database may be used as training data.Specifically, labeled faces may be taken from one or more of the following datasets: GB Huang, M. Ramesh, T. Berg, and E. Learned-Miller, “Labeled faces in the wild: A database for studying face recognition in unconstrained environments”, Technical Report 07-49, University of Massachusetts, Amherst, October 2007, the YouTube(R) Faces Database as described in L. Wolf, T. Hassner, and I. Maoz, “Face recognition in unconstrained videos with matched background similarity”, in IEEE Conf. on CVPR, 2011, or the Google(R) Facial Expression Comparison dataset. The convolutional neural network can be trained using the method described in Florian Schroff, Dmitry Kalenichenko, and James Philbin, “FaceNet: A Unified Embedding for Face Recognition and Clustering”, arXiv:1503.03832.

[0052] The processor may be configured to correct image artifacts caused by the diffraction of light as it passes through a transparent display. The term “correction” may mean partially or completely removing the artifact, or tagging the artifact so that it can be excluded from further processing, particularly from determining whether the person being photographed is an authorized person. Correction of image artifacts may take into account information about the transparent display, particularly the dimensions of the pixels and the distances between repeating features. Correcting image artifacts may include determining the artifacts and removing artifacts that were determined before analysis. Image artifacts include lower intensity or irradiance compared to directly emitted light. Therefore, intensity or irradiance may be used to determine whether a light spot is an artifact. To improve the accuracy of determining whether a light spot is an artifact, the intensity or irradiance of the spot emitted from the illuminating source may be increased. Furthermore, diffracting certain patterns, such as hexagonal patterns, can make it easier to distinguish between artifacts and directly emitted light.

[0053] This information allows for the calculation of diffraction patterns and comparison with the image, thereby facilitating the identification of artifacts. Correction of image artifacts may include identifying reflective features, sorting them by brightness, and selecting the locally brightest features. To determine the distance around features in the image that are conditioned as local, in particular, the distance in the image at which the light beam is displaced by diffraction on a transparent display can be calculated based on information from the transparent display. This method is particularly useful for patterned images. Further details are disclosed in WO 2021 / 105265 A1.

[0054] The processor may be configured to determine the image quality of the image from the camera. Determining the image quality may mean determining the brightness of the image, in particular whether the brightness of the image is within a predetermined range. This predetermined range may be selected so that image recognition yields optimal results. The processor may generate a signal indicating the brightness level of the image. Such a signal may be used, for example, by a projector controller to adjust the lighting power of the projector. This signal may also be used by a camera controller to adjust the camera settings in accordance with the signal indicating the brightness level, and / or to trigger the camera to generate a new image. Determining the image quality may also mean determining the position of a person's head, in particular the angle of the person's face relative to the camera. It may also mean determining whether the angle of the person's face relative to the camera is within a predetermined range. This predetermined range may be selected so that image recognition yields optimal results. The processor may generate a signal indicating the position of a person's head. Such a signal may be used, for example, by a camera controller to trigger the camera to generate a new image. Furthermore, this signal can also be used, for example, to inform a user to change the direction of their head by displaying such information on a transparent display.

[0055] In one embodiment, the processor may determine the image quality based on the brightness of the image. Determining quality based on brightness may include at least determining the brightness value. For example, ambient light can negatively affect image quality, and detecting overexposed images can prevent misrecognition based on overexposed images.

[0056] The processor may be further configured to determine material data based on the pattern image. Therefore, in particular, the processor may transfer the data to a remote device. Alternatively or additionally, the processor may perform material determination based on the pattern image, in particular by executing appropriate computer programs having their respective functions. In particular, by considering the material as a parameter for verifying the authentication process, the authentication process can be made more robust against being circumvented by using the user's recorded images.

[0057] The processor may be configured to extract material data from the pattern image by beam profile analysis of the light spots. For beam profile analysis, see WO 2018 / 091649 A1, WO 2018 / 091638 A1, and WO 2018 / 091640 A1, the full contents of which are incorporated herein by reference. Beam profile analysis can enable reliable classification of scenes based on a small number of light spots. Each of the light spots in the pattern image may include a beam profile. The term "beam profile" may generally represent at least one intensity distribution of a light spot on an optical sensor as a function of pixels. The beam profile may be selected from the group consisting of trapezoidal beam profiles, triangular beam profiles, conical beam profiles, and linear combinations of Gaussian beam profiles.

[0058] The processor may be configured to outsource at least one step of the authentication process, such as user identification, and / or at least one step of the verification process, such as reviewing data, to a remote device, specifically a server and / or a cloud server. The authentication system and the remote device may be part of a computer network (particularly the Internet). The authentication system may transmit generated data and / or data related to intermediate steps of the authentication process and / or its verification to the remote device. In such a scenario, the processor may be, and / or include, a connection interface configured to transmit information to the remote device. Data generated by the remote device used in the authentication process and / or its verification may be further transmitted to the authentication system. This data may be received by a connection interface configured by the authentication system. The connection interface may be configured in particular for transmitting or exchanging information. In particular, the connection interface can provide data transfer connections such as Bluetooth, NFC, and inductive coupling. As an example, the connection interface may be, or include, at least one port, including one or more of a network or Internet port, a USB port, and a disk drive.

[0059] The processor is configured to use a facial recognition authentication process that operates on pattern images and / or extracted material data. The processor may also be configured to extract material data from pattern images.

[0060] In one embodiment, extracting material data from a pattern image may include generating material types and / or data derived from material types. Preferably, the extraction of material data may be based on a pattern image. The material data may be extracted by using at least one model. The extraction of material data may include providing a pattern image to a model and / or receiving material data from a model. Providing an image to a model may include, and may follow, receiving a pattern image at the input layer of the model or receiving a pattern image via the loss function of the model. The model may be a data-driven model. The data-driven model may include an encoder-decoder structure such as a convolutional neural network and / or an autoencoder. Other examples for generating representations may be FFT, wavelets, deep learning such as CNNs, energy models, normalization flows, GANs, visual transformers, or transformers used in natural language processing, autoregressive image modeling, normalization flows, deep autoencoders, and deep energy-based models. Supervised or unsupervised schemes are applicable to generating representations, and embeddings such as cosine or Euclidean metrics in ML languages ​​are also possible. A data-driven model can be parametricized according to a training dataset comprising at least one image and material data, preferably at least one pattern image and material data. In another embodiment, extracting material data may include providing images to the model and / or receiving material data from the model. In another embodiment, the data-driven model may be trained according to a training dataset comprising at least one image and material data. In another embodiment, the data-driven model may be parametricized according to a training dataset comprising at least one image and material data. The data-driven model may be parametricized according to a training dataset for receiving images and providing material data based on the received images.A data-driven model may be trained according to a training dataset to receive an image and provide material data as output based on the received image. The training dataset may include at least one image and material data, preferably material data associated with at least one image. The image may include a representation of the image. The representation may be a low-dimensional representation of the image. The representation may include at least some of the data or information associated with the image. The image representation may include feature vectors. In one embodiment, determining the representation, in particular a low-dimensional representation, may be based on principal component analysis (PCA) mapping or radial basis function (RBF) mapping. Determining the representation may also be expressed as generating the representation. Generating a representation based on PCA mapping may include clustering based on features of pattern images and / or subimages. In addition or alternatively, generating the representation may be based on a neural network structure suitable for dimensionality reduction. A neural network structure suitable for dimensionality reduction may include an encoder and / or decoder. In one example, the neural network structure may be an autoencoder. In one example, the neural network structure may include a convolutional neural network (CNN). A CNN may include at least one convolutional layer and / or at least one pooling layer. A CNN can reduce the dimensionality of a subimage and / or an image, for example, by applying convolution based on the convolutional layer and / or by pooling. Applying convolution may be suitable for selecting features related to material information in a pattern image.

[0061] In one embodiment, the model may be suitable for determining output based on input. In particular, the model may be suitable for determining material data based on an image as input. The model may be a deterministic model, a data-driven model, or a hybrid model. A deterministic model preferably reflects a physical phenomenon in mathematical form, including, for example, a first-principles model. A deterministic model may include a set of equations that describe the interaction between matter and patterned electromagnetic radiation, thereby yielding state index values, vital sign measurements, etc. A data-driven model may be a classification model. A hybrid model may be a classification model that includes at least one machine learning architecture having deterministic or statistical adaptations and model parameters. Statistical or deterministic adaptations may be introduced to improve the quality of results, as they provide a systematic relationship between empiricism and theory. In one embodiment, the data-driven model may be a classification model. A classification model may include at least one machine learning architecture and model parameters. For example, a machine learning architecture may be one or more of the following: linear regression, logistic regression, random forest, piecewise linear, nonlinear classifier, support vector machine, naive Bayes classification, nearest neighbor classification, neural network, convolutional neural network, generative adversarial network, support vector machine, or gradient boosting algorithm, or include them. In the case of a neural network, the model may be, but is not limited to, a multiscale neural network or a recurrent neural network (RNN) such as a gated recurrent unit (GRU) recurrent neural network or a long-short-slow-memory (LSTM) recurrent neural network. A data-driven model may be parameterized according to a training dataset. A data-driven model may be trained based on a training dataset. Training a model may include parametricating the model. The term training may also be written as learning.This term may specifically refer to the process of building a classification model, in particular the process of determining and / or updating the parameters of the classification model. Updating the parameters of a classification model may be referred to as retraining. Retraining may be included wherever training is referred to herein. In one embodiment, the training dataset may include at least one image and material information.

[0062] In one embodiment, determining whether an imaged person may be an authenticated person may include material classification and / or hemoperfusion classification. Material classification may include extracting material data from an image generated by the camera and verifying the extracted material data. In one embodiment, hemoperfusion classification may include determining a hemoperfusion scale based on an image generated by the camera and verifying the hemoperfusion scale. Verifying the hemoperfusion scale may include determining whether the determined hemoperfusion scale corresponds to a desired hemoperfusion scale. The desired hemoperfusion measurement may be a hemoperfusion measurement associated with an authenticated user. Determining whether the determined hemoperfusion measurement corresponds to a desired hemoperfusion measurement may include comparing the determined hemoperfusion measurement with the desired hemoperfusion measurement. If the determined hemoperfusion measurement matches the desired hemoperfusion measurement, authentication may be activated. If the determined hemoperfusion measurement is outside the range specified by the desired hemoperfusion measurement, authentication may be deactivated.

[0063] In one embodiment, the light may be coherent light, and in particular the patterned infrared illumination may be coherent patterned infrared illumination. Determining the blood perfusion measurement may include determining the speckle contrast of the pattern image and determining the blood perfusion measurement based on the determined speckle contrast. The speckle contrast may represent an index of the average contrast of the intensity distribution within the region of the speckle pattern. In particular, the speckle contrast K across the region of the speckle pattern is the average speckle intensity The ratio of the standard deviation σ to, i.e.,

number

[0064] The speckle contrast may include a speckle contrast value. The speckle contrast value may be distributed between 0 and 1. The hemoperfusion measurement is determined based on the speckle contrast. Therefore, the vital sign measurement may depend on the determined speckle contrast. If the speckle contrast changes, the hemoperfusion measurement derived from the speckle contrast may change accordingly. The hemoperfusion measurement may be a single numerical value or value representing the likelihood that the subject is a living subject. Preferably, a complete pattern image can be used to determine the speckle contrast. Alternatively, a portion of the pattern image may be used to determine the speckle contrast. The portion of the pattern image preferably represents a smaller area of ​​the pattern image than the area of ​​the complete pattern image. A cross-section of the pattern image may be obtained by cropping the pattern image. The hemoperfusion measurement may indicate whether a living human being has been detected.

[0065] In one embodiment, extracting material data may include providing an image to a data-driven model. Additionally or alternatively, extracting material data may include generating a numerical representation associated with the image by the data-driven model and / or mapping the numerical representation associated with the image to material data. The numerical representation associated with the image may be a feature vector. Extracting material data may also include generating an embedding associated with the image based on the data-driven model. The data-driven model may be parameterized and / or trained based on past images and corresponding past material data. The data-driven model may be configured to provide material data in response to the reception of an image generated by a camera, for example. The embedding may represent a low-dimensional representation associated with the image, such as a feature vector. The feature vector may be suitable for suppressing the background while preserving a material signature indicating the material data. In this context, the background may represent information independent of the material signature and / or the material data. Furthermore, the background may represent information related to biometric features, such as facial features. The material data may be determined by the data-driven model based on the embedding associated with the image. Additionally or alternatively, extracting material data from an image by providing the image to a data-driven model may include converting the image into material data, particularly material feature vectors that represent the material data. Thus, the material data may further include material feature vectors, and / or material feature vectors may be used to determine the material data.

[0066] In one embodiment, the authentication process can be verified based on the extracted material data.

[0067] In one embodiment, verification based on extracted material data may include determining whether the extracted material data matches desired material data. Determining whether the extracted material data matches desired material data may be referred to as verification. Allowing or denying a user and / or object to perform at least one operation on the device that requires authentication based on the material data may include verifying authentication or an authentication process. Verification may be performed based on material data and / or images. Determining whether the extracted material data corresponds to desired material data may include determining the similarity between the extracted material data and the desired material data. Determining the similarity between the extracted material data and the desired material data may include comparing the extracted material data and the desired material data. The desired material data may represent predetermined material data. For example, the desired material data may be skin. It may be determined whether the material data corresponds to desired material data. For example, the material data may be a non-skin material or silicone. Determining whether the material data corresponds to desired material data includes comparing the material data with the desired material data. The comparison between material data and desired material data may allow and / or deny the user and / or object the execution of at least one operation requiring authentication. In this example, skin as the desired material data is compared with non-skin material or silicone as material data, and since silicone or non-skin material may differ from skin, the result may be rejection.

[0068] In one embodiment, the authentication process or verification thereof may include generating at least one feature vector from material data and matching the material feature vector with the associated reference template vector of the material.

[0069] In one embodiment, a person, in particular an authorized person and / or user, may represent a registered person and / or a person who has been registered. A registrant may be a person who has gone through a registration process. The registration process may be a process of generating a template, in particular a template suitable for comparison with recorded images of a person taken by a camera placed behind a transparent display.

[0070] In one embodiment, illumination and / or recording may be initiated and / or triggered by an authentication request, preferably a payment request. In particular, illumination and / or recording may be initiated and / or triggered by a payment terminal. Preferably, illumination and / or recording may be initiated and / or triggered by the person, a device associated with the person, an application on the device associated with the person, or at least one of these. A device associated with a person may represent a mobile electronic communication device such as a smartphone.

[0071] The authentication unit may be configured to authenticate a user if it can identify the user and / or if the material data matches the desired material data. The device may include at least one authentication unit configured to allow the user to perform at least one operation on the device, for example, unlock the device, if authentication is successful, or to deny the user to perform at least one operation on the device if authentication is unsuccessful. This allows the user to know the result of authentication.

[0072] In a further embodiment, the present invention discloses a method for authenticating a user of a device in order to perform at least one operation on the device that requires authentication.

[0073] The processor is configured to output a signal indicating whether the captured person is authenticated. This signal may be a binary signal, where 0 indicates the person is not authenticated and 1 indicates the person is authenticated. Alternatively, this signal may be a numerical value, such as an integer or floating-point value, that indicates the probability that the person is authenticated.

[0074] The signal may be transmitted to a control unit that controls the vehicle's functions. Based on the signal, the control unit may, for example, unlock the vehicle, start the engine, grant access to the onboard computer system, verify insurance policies, connect to a remote network, or verify electronic payments in an app store. Thus, the authentication system of the present invention may be used for vehicle control.

[0075] The present invention further relates to a method for authenticating a person inside a vehicle. Unless otherwise clearly stated below, the description including the preferred embodiments described above applies to this method.

[0076] All method steps described may be performed by hardware within the vehicle. Therefore, the processor that determines whether an imaged person is an authenticated person may be configured to exclusively execute at least one computer program used in at least one embodiment of the method according to the present invention, in particular at least one line of computer program code configured to execute at least one algorithm. Here, the computer program executed on a single processing device may contain all instructions that cause the computer to execute the method. Alternatively, or additionally, at least one method step may be executed using at least one remote device, selected from at least one server or cloud server, in particular, where the apparatus and remote device may be part of a computer network. In this case, the computer program may include at least one remote component executed by at least one remote processing device to execute at least one method step. The remote component may have the function of performing user identification and / or material data extraction. Furthermore, the computer program may include at least one interface configured to transfer data to and / or receive data from at least one remote component of the computer program.

[0077] The present invention further relates to a non-temporary computer-readable medium containing instructions that, when executed by one or more processors, cause one or more processors to perform the method according to the present invention. The term “computer-readable data medium” may also mean any suitable data storage device or computer-readable memory that stores one or more instruction sets (e.g., software) that embody one or more of the methodologies or functions described herein. Instructions may also reside, all or at least partially, in the main memory and / or processing device during their execution by the computer, main memory, and processing device (these may constitute a computer-readable storage medium). Instructions may also be transmitted or received over a network via a network interface device. Computer-readable data media include, for example, hard drives on servers, USB storage devices, CDs, DVDs, or Blu-ray discs. A computer program may contain all the functions and data necessary to perform the method according to the present invention, or it may provide an interface for processing parts of the method on a remote system, such as a cloud system.

[0078] In one embodiment, the authentication system may include one or more components, preferably two or more. The authentication system may also be a device configured to authenticate the user of the device. The components may include, and / or include, a transparent display mounted on a vehicle, a projector positioned to illuminate a person through the transparent display, a camera positioned to receive light from a person through the transparent display, and / or a processor configured to receive an image from the camera and determine whether the person being photographed is an authenticated person, and to output a signal indicating whether the person being photographed is an authenticated person.

[0079] In one embodiment, the recording trigger may include a trigger that records at least two images of the driver through a transparent display while the driver is illuminated by light. The at least two images may be generated at least two different time points in time. Furthermore, a display of at least one interval between at least two different time points may be provided. A state index related to the driver's state may be determined based on the at least two pattern images and the display of at least one interval.

[0080] In one embodiment, providing a determined state index may include determining whether the determined state index may correspond to a target state index, and enabling the driver to control at least one function of the vehicle in response to determining that the determined state index may correspond to a target state index.

[0081] In one embodiment, determining a state index related to a driver's state based on at least two pattern images and at least one interval instruction may include providing at least two pattern images and at least one interval instruction to a state model. The state model may be a data-driven model based in particular on a statistical distribution between pattern images, interval instructions, and state indexes. The state model may be parametric and / or trained based on past pattern images, past interval instructions, and past state index values. The state model may be parametric and / or trained to determine a state index in response to being provided with at least two pattern images and at least one interval instruction.

[0082] The state index may be an index suitable for determining the state of an organism. The state of an organism may be a physical state and / or a mental state. The physical state may relate to physical stress levels, fatigue levels, agitation levels, the organism's suitability for performing a specific task, etc. The mental state may relate to mental stress levels, attention, concentration, agitation levels, the organism's suitability for performing a specific task, etc. Such specific tasks may require the organism's concentration, attention, alertness, calmness, or similar characteristics. Examples of such tasks include controlling machinery, vehicles, mobile devices, etc., manipulating other species, sports activities, games, emergency tasks, decision-making, etc. The state index indicates the state of an organism. The state index may be one or more of the following: heart rate, blood pressure, suction level, etc. In some embodiments, the state of an organism may be a critical state corresponding to a high value of the state index, and the state of an organism may be a non-critical state corresponding to a low value of the state index. Next, the critical state index in these embodiments may be equal to or lower than the threshold, and the non-critical state index may be lower than the threshold. In other embodiments, the state of the organism may be a critical state corresponding to a low value of the state index, and the state of the organism may be a non-critical state corresponding to a high value of the state index. Next, the critical state index in these embodiments may be equal to or higher than the threshold, and the non-critical state index may be lower than the threshold. The critical state index may be associated with a high stress level, low attention, low concentration level, high fatigue, high excitement, low aptitude of the organism to perform a specific task, etc. The non-critical state index may be associated with a low stress level, high attention, high concentration, low fatigue, low excitement, high aptitude of the organism to perform a specific task, etc.

[0083] The index of a biological state may be determined based on the movement of body fluids, preferably blood, most preferably red blood cells. The movement of body fluids is not constant over time and changes due to the activity of parts of the body, such as the heart. Such changes in movement can be determined based on changes in feature contrast over time. A large difference in feature contrast values ​​at different time points may be associated with a rapid change in movement. A small difference between feature contrast values ​​at different time points may be associated with a slow change in movement. Changes in the movement of body fluids, preferably blood, may be periodically associated with a corresponding motion frequency. Thus, the feature contrast may change periodically along with the corresponding motion frequency. The motion frequency may correspond to the length of the period associated with the periodic change in feature contrast. In some embodiments, at least two reflected images may contain half of the period. In other embodiments, at least two reflected images may contain one or more periods. Preferably, pattern features associated with the same part of the body may be used to determine the state of the body. This is advantageous due to the fact that blood perfusion, and therefore feature contrast, changes across different parts of the body. In some embodiments, at least one state index may be determined based on the feature contrast. [Brief explanation of the drawing]

[0084] [Figure 1] Figure 1 shows the elements of the authentication system. [Figure 2] Figure 2 shows possible configurations of the authentication system on the outside of a vehicle. [Figure 3] Figure 3 shows possible configurations for an authentication system within a vehicle. [Figure 4] Figure 4 shows the authentication of a driver inside a vehicle. [Modes for carrying out the invention]

[0085] Figure 1 shows the elements of an authentication system 100 to be installed in a vehicle. This includes a transparent display 101 that transmits light 120 from a projector 102 to a person 110. The light may be infrared, which is invisible to humans. The transparent display 101 may be transparent only at the points through which the light 120, 130 passes. Transparent may mean that at least 30% or at least 50% of the incident light passes through the transparent display 101. The transparent display 101 further allows reflected light 130 reflected by the person 110 to pass through to the camera 103. The light 120 may be incident on the person's face, the entire head including the hair, the upper body including the head, neck, and shoulders, or the entire body. The camera 103 generates an image in an optical range that matches the wavelength emitted by the projector 102, for example, in the infrared range. The image may be a grayscale image, i.e., an image in which each pixel contains only total intensity information, or an RGB image, i.e., an image in which different pixels show intensity at a specific wavelength. The image is passed to processor 104. Processor 104 may be a microcontroller including memory and I / O controller functions, or a CPU connected to memory and I / O controllers. Processor 104 determines whether the person is an authenticated person. Such determination may include vectorizing the image into features. Such feature vectors may be compared to a stored template. If the difference between the feature vectors and the stored template is less than a predefined threshold, the processor may determine that the person in the vehicle is an authenticated person. The processor may further determine whether the image truly shows a human and not a fake mask. This may be achieved by classifying the material of the face in the image by evaluating the reflective properties of the reflected light. If no skin is detected, the processor may determine that the person in front of the transparent display is not authenticated. The processor may generate a signal 140 indicating that the person in the vehicle is authenticated. Signal 140 may be transcribed (transferred) to a controller, for example, via a wireless communication interface, for unlocking the vehicle, starting the engine, granting access to the board computer, or for secure payment.

[0086] Figure 2 shows possible locations where the transparent display may be mounted on the exterior of the vehicle, such as in automobile 200. The display may be positioned between the windows of the B-pillar 201. Alternatively or additionally, the transparent display may be positioned on the side mirror 202.

[0087] Figure 3 shows possible locations where a transparent display may be mounted inside a vehicle. The figure shows the dashboard 301 and the car's windshield as seen from inside the vehicle. The transparent display may be integrated into the interior mirror 302. This may be particularly useful if the mirror's function is only replicated by a display showing the rear view recorded by a camera. Another possibility is the space behind the steering wheel 303 where instruments such as a speedometer are typically located. Furthermore, the transparent display may be incorporated into the steering wheel 304. The center console 305 is also an option, as it is becoming increasingly common to replace conventional control devices with displays. In one embodiment, the space behind the steering wheel 303 and the center console may be combined to form a continuous display.

[0088] Figure 4 shows the in-vehicle authentication system. The transparent display 401 is installed behind the steering wheel, inside the dashboard. A light ray 402 is shone onto the face of the driver 403. The light reflected by the person 403 passes through the transparent display 401 and is recorded by a camera. The camera generates an image, which is analyzed by a processing unit to determine whether or not the person is an authenticated individual.

Claims

1. A vehicle authentication system, A transparent display mounted on the vehicle, A projector positioned to project light onto a person through the aforementioned transparent display, A camera positioned to receive light from a person through the aforementioned transparent display, A processor configured to receive an image from the camera and determine whether the person captured in the image is an authenticated person, and configured to output a signal indicating whether the person captured in the image is an authenticated person, A vehicle authentication system characterized by having the following features.

2. The authentication system according to claim 1, characterized in that the transparent display includes an organic light-emitting diode.

3. The authentication system according to claim 1 or 2, characterized in that the projector irradiates infrared light onto a person through the transparent display.

4. The authentication system according to claim 1 or 2, characterized in that the projector irradiates a person with patterned light and flood light through the transparent display.

5. The authentication system according to claim 1 or 2, characterized in that the projector includes an array of vertical cavity surface-emitting lasers.

6. The authentication system according to claim 1 or 2, characterized in that the projector comprises at least one metasurface element and / or at least one diffractive optical element.

7. Determining whether the person captured in the image is the authenticated person is: - Extracting material data from images generated by a camera, verifying the extracted material data, and / or - To determine blood perfusion measurements from images generated by a camera, and to verify the blood perfusion measurements. The authentication system according to claim 1 or 2, characterized by including the following:

8. The authentication system according to claim 1 or 2, characterized in that image artifacts caused by the diffraction of light as it passes through the transparent display are corrected.

9. The authentication system according to claim 1 or 2, characterized in that determining whether the person captured in the image is an authenticated person includes determining the position of the person's head.

10. Use of the authentication system according to claim 1 or 2 for controlling a vehicle.

11. Use of the authentication system according to claim 10, wherein the authentication system is used for unlocking a vehicle, starting the engine, granting access to a board computer system, connecting to a remote network, or verifying electronic payments.

12. A vehicle comprising the authentication system according to claim 1 or 2 relating to the authentication system.

13. A method for authenticating a person riding in a vehicle, The process involves shining light onto a person through a transparent display mounted on the vehicle, The steps include recording an image of a person through the aforementioned transparent display, A step to determine whether the person captured in the image is the person who has been authenticated, A step of outputting a signal indicating whether the person captured in the image is a person who has been authenticated, A method that includes this.

14. The method according to 13, characterized in that the signal is used to control a vehicle.

15. A non-temporary computer-readable medium, when executed by one or more processors, containing instructions that cause one or more processors to perform the method according to claim 13 or 14, which references the method.

Images