Authentication system for vehicle

Abstract

The invention is in the field of authentication systems for vehicles. The present invention relates to an authentication system for a vehicle, the authentication system comprising: a transparent display attached to the vehicle; a projector positioned such that the projector can irradiate light to a person through the transparent display; a camera positioned such that the camera can receive light from a person through the transparent display; and a processor receiving an image from the camera and configured to determine whether the imaged person is an authorized person, where the processor is configured to output a signal indicating whether the imaged person is authorized.

Description

[0001] The present invention belongs to the field of authentication systems for vehicles. The invention relates to an authentication system for a vehicle, the use of the authentication system for controlling the vehicle, a vehicle comprising the authentication system, a method for authenticating a person in a vehicle, and a non-transitory computer-readable medium comprising instructions for the method for authenticating a person in a vehicle. Background Art

[0002] Traditionally, user authentication in vehicles is accomplished via keys, so any user with the correct key is considered authorized. In this way, stolen keys can allow access to the vehicle, starting the engine and using all other vehicle functions. Because keys can be easily stolen, more sophisticated methods for controlling vehicles are desirable.

[0003] WO 2021 / 218180 A1 discloses a method for controlling the unlocking of a vehicle door, which involves evaluating a person's facial image detection. CN 114120484 A discloses a facial recognition system for determining whether a person is a legitimate user. In both cases, the camera is visibly attached to the vehicle. This has the disadvantage that thieves can more easily identify the facial recognition system and can more easily find ways to circumvent such a system. Summary of the Invention

[0004] It is therefore an object of the present invention to provide an authentication system for vehicles which does not have the disadvantages of the prior art.

[0005] This object is achieved by a certification system for a vehicle, the certification system comprising:

[0006] a transparent display attached to the vehicle,

[0007] a projector positioned so that the projector can shine light through the transparent display onto a person,

[0008] a camera positioned so that the camera can receive light from a person through the transparent display, and

[0009] A processor receives an image from the camera and is configured to determine whether the imaged person is an authorized person, wherein the processor is configured to output a signal indicating whether the imaged person is authorized.

[0010] The invention further relates to the use of the authentication system according to the invention for controlling a vehicle.

[0011] The invention further relates to a vehicle comprising an authentication system according to the invention.

[0012] The invention further relates to a method for authenticating a person in a vehicle, the method comprising:

[0013] illuminating the person with light through a transparent display attached to the vehicle,

[0014] recording the image of the person through the transparent display,

[0015] Determine whether the person being imaged is an authorized person, and

[0016] A signal is output indicating whether the imaged person is authorized.

[0017] The invention further relates to a non-transitory computer-readable medium comprising instructions which, when executed by one or more processors, cause the one or more processors to perform the method according to the invention.

[0018] illuminating the person with light through a transparent display attached to the vehicle,

[0019] recording the image of the person through the transparent display,

[0020] Determine whether the person being imaged is an authorized person, and

[0021] A signal is output indicating whether the imaged person is authorized.

[0022] In another aspect, the present invention relates to a method for determining a condition of a driver, the method comprising:

[0023] - triggering to illuminate the driver with light through a transparent display attached to the vehicle;

[0024] - triggering to record the driver's image through the transparent display while the driver is illuminated by the light;

[0025] - determining a condition measure associated with the driver's condition based on the image;

[0026] - Provide status metrics.

[0027] In another aspect, the present invention relates to a method for accessing a vehicle and / or a function of the vehicle, the method comprising:

[0028] - triggering to illuminate a person with light through a transparent display attached to a vehicle;

[0029] - triggering to record an image of the driver through the transparent display while the driver is illuminated by the light;

[0030] - determining, based on the image, whether the person corresponds to an authorized person; and

[0031] - Allowing the person access to the vehicle and / or functionality of the vehicle based on determining that the person is authorized.

[0032] By placing both the projector and the camera behind a transparent display, the authentication system is invisible to the user. The projector and camera can be placed anywhere behind the display. If there is more than one display (which is increasingly common in modern vehicles), it is not even clear in which display the authentication system is placed. This makes it more difficult for thieves to manipulate the vehicle. In addition, placing the projector and camera behind the display has the advantage that the authentication system does not require additional space on the surface (for example, on the dashboard). This allows designers to use space in other ways and provides more freedom to achieve an attractive appearance. Moreover, hiding the projector and camera has the advantage that the driver is less distracted and does not feel as much under surveillance.

[0033] The certification system is applicable to various modes of transport, including cars, motorcycles, buses, trucks, trains or even airplanes.

[0034] The authentication system includes a transparent display. The term "display" may refer to a device of any shape configured to display an information item. The information item may be any information, such as at least one image, at least one chart, at least one histogram, at least one graph, text, numbers, at least one symbol, or an operation menu. The display may be or include at least one screen. The display may have any shape, such as a rectangular shape. The display may be a front-mounted display of the device.

[0035] The display may be or include at least one organic light-emitting diode (OLED) display. The term "organic light-emitting diode" may refer to a light-emitting diode (LED) in which the emissive electroluminescent layer is a film of an organic compound configured to emit light in response to an electric current. An OLED display may be configured to emit visible light. The display, in particular the display area, may be covered by glass. In particular, the display may include at least one glass cover plate.

[0036] A transparent display is at least partially transparent. The term "at least partially transparent" may refer to a property of the display that allows light, in particular light of a specific wavelength range (e.g., light in the infrared spectral region, in particular light in the near-infrared spectral region), to at least partially pass through. 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. The display may have different transparencies for other wavelength ranges. For example, the display may have a transparency of >80% for the visible spectral range, preferably >90% for the visible spectral range. A transparent display may be at least partially transparent over the entire display area or only part of it. Typically, it is sufficient as long as those parts of the display area through which light from the projector needs to pass or through which light to the camera needs to pass are at least partially transparent. In particular, a transparent display may be at least partially transparent in the case where the projector and / or camera is covered by the display.

[0037] The display includes a display area. The term "display area" may refer to an active area of ​​the display, in particular an 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 equal to or lower than 400 PPI, more preferably the second PPI value may be equal to or higher than 300 PPI. The first PPI value may be associated with at least one continuous area that is at least partially transparent.

[0038] The transparent display is attached to a vehicle. It can be placed in various locations, such as on the exterior or interior of the vehicle. When placed on the exterior of the vehicle, it can be integrated into the vehicle body, doors, windows, mirrors, or between windows, such as in a car's B-pillar. When placed inside the vehicle, it can be integrated into the steering wheel, in place of the speedometer, located in the center of the dashboard, in a mirror, or in a window.

[0039] The authentication system further comprises a projector for illuminating the person with light. The term "light" may refer to electromagnetic radiation in one or more of the infrared spectral range, the visible spectral range, and the ultraviolet spectral range. In this document, the term "ultraviolet spectral range" generally refers to electromagnetic radiation having a wavelength of 1 nm to 380 nm, preferably 100 nm to 380 nm. Further, in part in accordance with the version of standard ISO-21348 in force on the date of this document, the term "visible spectral range" generally refers to the spectral range of 380 nm to 760 nm. The term "infrared spectral range" (IR) generally refers to electromagnetic radiation in the range of 760 nm to 1000 μm, wherein the range of 760 nm to 1.5 μm is generally referred to as the "near infrared spectral range" (NIR), the range of 1.5 μm to 15 μm is referred to as the "mid infrared spectral range" (MidIR), and the range of 15 μm to 1000 μm is referred to as the "far infrared spectral range" (FIR). Preferably, the light used for the typical purposes of the present invention is light in the infrared (IR) spectral range, more preferably light in the near infrared (NIR) and / or mid-infrared spectral range (MidIR), especially light with a wavelength of 1 μm to 5 μm, preferably 1 μm to 3 μm.

[0040] The term "illuminating" may refer to the process of exposing at least one element to light. The term "projector" may refer to a device configured to generate or provide light within the meaning defined above. A projector may be a pattern projector, a flood projector, or both, or the projector may repeatedly switch from illuminating patterned light to flooding.

[0041] The term "pattern projector" may 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 refer to at least one pattern comprising a plurality of light spots. The light spots may be at least partially spatially extended. At least one light spot or any light spot may have any shape. In some cases, a circular shape of at least one light spot or any light spot may be preferred. These light spots may be arranged by taking into account the structure of the display included in the device further including an optoelectronic device. Typically, the arrangement of the OLED pixel structure of the display may be considered. The term "infrared light pattern" may refer to a light pattern comprising light spots within the infrared spectral range. The infrared light pattern may be a near-infrared light pattern. The infrared light may be coherent. The infrared light pattern may be a coherent infrared light pattern.

[0042] 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 having multiple wavelengths, for example to allow additional measurements in other wavelength channels.

[0043] The infrared light pattern may include 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 including further convex tessellations. For example, the infrared light pattern is a hexagonal pattern, preferably a hexagonal infrared light pattern, preferably a 2 / 5 hexagonal infrared light pattern.

[0044] Using a periodic 2 / 5 hexagonal pattern may allow for differentiation of artifacts from usable signals.

[0045] At least one of the infrared spots may be associated with a beam divergence of 0.2° to 0.5°, preferably 0.1° to 0.3°. The term "beam divergence" may refer to at least one measure of how at least one diameter and / or at least one diameter equivalent (such as a radius) increases with distance from the optical aperture from which the beam emerges. The measure may be an angle or an angle equivalent. In the context of the present invention, the beam divergence may typically be determined in terms of 1 / e 2 .

[0046] The pattern projector may include at least one pattern projector configured to generate an infrared light pattern. The pattern projector may include at least one emitter, in particular a plurality of emitters. The term "emitter" may 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 source and at least one non-laser light source, the at least one laser source being, for example, at least one semiconductor laser, at least one double heterostructure laser, at least one external cavity laser, at least one separated confined 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 cavity 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 pump 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 cavity surface emitting laser (VCSEL); the at least one non-laser light source being, for example, at least one LED or at least one light bulb. For example, the pattern projector includes at least one VCSEL, preferably a plurality of VCSELs. The plurality of VCSELs may be arranged in at least one array, for example, a VCSEL matrix. The VCSELs may be arranged on the same substrate or on different substrates. The term "vertical cavity surface emitting laser" may refer to a semiconductor laser diode configured to emit a laser beam vertically relative to a top surface. Examples of VCSELs may be found, for example, at en.wikipedia.org / wiki / Verticalcavity_surface-emitting_laser. VCSELs are generally known to those skilled in the art, for example from WO 2017 / 222618 A. Each of the VCSELs is configured to generate at least one light beam. The plurality of light spots generated may be associated with an infrared light pattern. The VCSEL may be configured to emit a light beam having a wavelength range of 800 nm to 1000 nm. For example, the VCSEL may be configured to emit a light beam of 808 nm, 850 nm, 940 nm, and / or 980 nm. Preferably, the VCSEL emits light at 940 nm, since terrestrial solar radiation has a local minimum of irradiance at this wavelength, as shown in CIE 085-1989. " Solar spectral irradiance ” As described in.

[0047] The pattern projector may include at least one optical element configured to increase the number of light spots generated by the pattern projector and / or replicate (e.g., double or triple replicate) the pattern. Other multiplication factors are also possible. The pattern projector, in particular the optical element, 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 (which in particular include different numbers of projection VCSELs and / or at least one different optical element configured to increase the number of light spots) may be possible. For example, one or more VCSELs may be used, and the generated laser light spot may be duplicated by using at least one DOE.

[0048] The pattern projector may comprise at least one delivery device. The term "delivery device" (also denoted "delivery system") may refer to one or more optical elements adapted to modify a light beam, in particular a light beam for generating at least a portion of an infrared light pattern, such as by modifying one or more of its beam parameters, its width or its direction. The delivery device may comprise at least one imaging optical device. The delivery device may specifically comprise one or more of the following: at least one lens, for example at least one lens selected from the group consisting of at least one adjustable focus lens, at least one aspherical lens, at least one spherical lens, at least one Fresnel lens; at least one diffractive optical element; at least one concave mirror; at least one beam deflecting element, preferably at least one reflector; at least one beam splitting element, preferably at least one of a beam splitting cube or a beam splitter; at least one multi-lens system; at least one holographic optical element; at least one meta-optical element. In particular, the delivery device comprises at least one refractive optical lens module. Thus, the delivery device may comprise a multi-lens system having refractive properties.

[0049] The pattern projector can be configured to emit modulated or non-modulated light. Where multiple emitters are used, different emitters can have different modulation frequencies, which can be used to differentiate the light beams, for example.

[0050] The one or more light beams generated by the pattern projector can 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. As an example, one or more light beams (such as laser beams) may be at an angle of less than 10°, preferably less than 5° or even less than 2° to the optical axis. However, other embodiments are also feasible. Further, one or more light beams may be located on the optical axis or outside the optical axis. As an example, one or more light beams may be parallel to the optical axis and have a distance from the optical axis of less than 10 mm, preferably a distance from the optical axis of less than 5 mm or even a distance from the optical axis of less than 1 mm, or may even coincide with the optical axis.

[0051] The term "flood projector" may refer to at least one device 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" may refer to substantially continuous spatial illumination, in particular diffuse and / or uniform illumination. The flood light has a wavelength in the infrared range, in particular in the near infrared range. The flood projector may comprise at least one VCSEL and / or at least one LED, preferably a plurality of VCSELs and / or LEDs. The term "substantially continuous spatial illumination" may refer to uniform spatial illumination, wherein non-uniform areas are possible.

[0052] The relative distance between the flood projector and the pattern projector can be less than 3.0 mm. The relative distance between the flood projector and the pattern projector can be less than 2.5 mm, preferably less than 2.0 mm. The pattern projector and the flood projector can be combined into one module. For example, the pattern projector and the flood projector can be arranged on the same substrate, in particular with a minimum relative distance. The minimum relative distance can be defined by the physical extension of the flood projector and the pattern projector. Arranging the pattern projector and the flood projector to have a relative distance less than 3.0 mm can reduce the space requirement of the two projectors. In particular, the projectors can even be combined into one module. This reduced space requirement can allow reducing the transparent area(s) necessary for the operation of the projector(s) behind the display in the display.

[0053] In an 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 next to the first platform. The optoelectronic device may include a heat sink. Above the heat sink, a first increment including the first platform may be attached. Above the heat sink, a second increment including the second platform may be attached. The second increment may be different from the first increment. Thus, the first platform may be further away from the optical element configured to increase (e.g., double replicate) the number of light spots. The second platform may be closer to the optical element. The beam emitted from the second VCSEL may be defocused and thus form overlapping light spots. This results in substantially continuous illumination and therefore flood illumination.

[0054] The projector is positioned so that it can illuminate light through the transparent display. Therefore, the light emitted by the projector passes through the transparent display before being incident on the person. From the person's perspective, the projector is placed behind the transparent display.

[0055] The authentication system further includes a camera. The term "camera" may refer to at least one unit of an optoelectronic device configured to generate at least one image. The image may be generated via a hardware and / or software interface, which may be considered a camera. The term "image generation" may refer to capturing and / or generating and / or determining and / or recording at least one image using a camera. Image generation may include performing imaging and / or recording images. Image generation may include capturing a single image and / or multiple images, such as a sequence of images. In order to generate an image via the hardware and / or software interface, the capturing and / or generating and / or determining and / or recording of the image may be caused and / or initiated by the hardware and / or software interface. For example, image generation may include continuously recording a sequence of images, such as a video or a movie. Image generation may be initiated by a user action or may be initiated automatically, for example, upon automatic detection of the presence of at least one object or user within the camera's field of view and / or within a predetermined area of ​​the field of view.

[0056] The camera may comprise at least one optical sensor, in particular at least one pixelated optical sensor. The camera may comprise at least one CMOS sensor or at least one CCD chip. For example, the camera may comprise at least one CMOS sensor, which may be sensitive in the infrared spectral range. The term "image" may refer to data recorded using an optical sensor, such as a plurality of electronic readings from a CMOS or CCD chip. The image may comprise raw image data or may be a pre-processed image. For example, pre-processing may comprise applying at least one filter and / or at least one background correction and / or at least one background subtraction to the raw image data.

[0057] For example, the camera may comprise a color camera, for example comprising at least color pixels. The camera may comprise a color CMOS camera. For example, the camera may comprise black and white pixels and color pixels. The color pixels and black and white pixels may be combined within the camera. The camera may comprise at least one color camera (e.g. RGB) and / or at least one black and white camera, such as a black and white CMOS. The camera may comprise at least one black and white CMOS chip. The camera may typically comprise a one-dimensional or two-dimensional array of image sensors (e.g. pixels). The camera may comprise an IR camera, in particular an NIR camera. The camera may comprise an IR-sensitive CMOS chip and / or a CCD chip, preferably a CMOS chip and / or a CCD chip that is sensitive in the NIR range.

[0058] The color camera may be an internal camera and / or an external camera of a device including an optoelectronic device. The internal camera and / or the external camera of the device may be accessed via a hardware and / or software interface included in the optoelectronic device for use as a camera. In the case where the device is or includes a smartphone, the image generation unit may be a front camera (such as a selfie camera) and / or a rear camera of the smartphone.

[0059] The camera may have a field of view between 10° x 10° and 75° x 75°, preferably 55° x 65°. The camera may have a resolution lower than 2 MP, preferably between 0.3 MP and 1.5 MP.

[0060] The camera may include other elements, such as one or more optical elements, for example one or more lenses. As an example, the optical sensor may be a fixed-focus camera, at least one of whose lenses is fixed relative to the camera's adjustment. Alternatively, however, the camera may also include one or more variable lenses that can be adjusted automatically or manually. However, other cameras are also possible.

[0061] The term "pattern image" may refer to an image generated by a camera when irradiating an infrared light pattern (e.g., on an object and / or a user). The pattern image may include an image showing at least a portion of the user, in particular the user's face, in particular over a corresponding region of interest included in the image, while irradiating the user with the infrared light pattern. The pattern image may be generated by imaging and / or recording light reflected by the object and / or user irradiated by the infrared light pattern. The pattern image showing the user may include at least a portion of the irradiated infrared light pattern on at least a portion of the user. For example, the irradiation of the pattern illumination source and the imaging using the optical sensor may be synchronized, for example, by using at least one control unit of the optoelectronic device.

[0062] The term "flood image" may refer to an image generated by a camera when an illumination source, such as an infrared flood light, illuminates an object and / or a user. The flood image may include an image showing a user, particularly the user's face, while the user is illuminated by the flood light. The flood image may be generated by imaging and / or recording light reflected from the object and / or user illuminated by the flood light. The flood image showing the user may include at least a portion of the flood light on at least a portion of the user. For example, the illumination by the flood light illumination source and the imaging using the optical sensor may be synchronized, such as by using at least one control unit of the optoelectronic device.

[0063] The camera may be configured to image and / or record the pattern image and the flood image simultaneously or at different times. The camera may be configured to image and / or record the pattern image and the flood image at at least partially overlapping measurement areas or equivalents of these measurement areas.

[0064] The camera is positioned so that it can receive light from a person through the transparent display. Light reflected or refracted from the person first passes through the transparent display before being incident on the camera. From the person's perspective, the camera is placed behind the transparent display.

[0065] The authentication system further includes a processor. A processor can be a logic circuit configured to perform the basic operations of a computer or system, and / or generally refers to a device configured to perform calculations or logical operations. In particular, the processor can be configured to process the basic instructions that drive the computer or system. As an example, the processor can include at least one arithmetic logic unit (ALU), at least one floating point unit (FPU), such as a math coprocessor or digital coprocessor, multiple registers, specifically registers configured to provide operands to the ALU and store operation results, and memory such as L1 and L2 cache memories. In particular, the processor can be a multi-core processor. In particular, the processor can be or include a central processing unit (CPU). Additionally or alternatively, the processor can be or include a microprocessor, and thus, specifically, the components of the processor can be contained in a single integrated circuit (IC) chip. Additionally or alternatively, the processor can be or include 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 one or more chips, such as dedicated machine learning optimization chips. The processor may be specifically configured, such as through software programming, to perform one or more evaluation operations. 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 processor may be 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.

[0066] The processor may be specifically configured, such as through software programming, to perform one or more evaluation operations. 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 processor may be 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.

[0067] The processor may be configured for identifying a user based on the floodlight image. Thus, in particular, the processor may forward the data to the remote device. Alternatively or additionally, the processor may perform identification of the user based on the floodlight image, in particular by running an appropriate computer program with corresponding functionality. The term "identification" may refer to an identity check and / or verification of the identity of a user. Identifying the user may comprise analyzing the floodlight image. Analysis of the floodlight image may comprise performing facial verification on the imaged face to confirm whether it is the face of the user. Identifying the user may comprise matching the floodlight image (e.g. showing a portion of the user, in particular an outline of a portion of the user's face) with a template. Determining whether the imaged face is the face of the user may comprise identifying the user, in particular determining whether the imaged face corresponds to at least one image of the user's face stored in, for example, at least one memory of the device.

[0068] The analysis may include one or more of the following: filtering; selecting at least one region of interest; forming a difference image between the flood image and at least one offset; inverting the flood image; background correction; decomposition into color channels; decomposition into hue, saturation, and brightness channels; frequency decomposition; singular value decomposition; applying a Canny edge detector; applying a Laplacian of Gaussian filter; applying a Difference of Gaussian filter; applying a Sobel operator; applying a Laplacian operator; applying a Scharr operator; applying a Prewitt operator; applying a Roberts operator; applying a Kirsch operator; applying a high-pass filter; applying a low-pass filter; applying a Fourier transform; applying a Radon transform; applying a Hough transform; applying a wavelet transform; thresholding; creating a binary image. The region of interest may be manually determined by a user or may be automatically determined, such as by identifying a user within the image. In particular, the analysis of the flood image may include using at least one image recognition technique, in particular a facial recognition technique. The image recognition technique includes at least one process for identifying a user within the image. Image recognition can include using at least one technique selected from the following: color-based image recognition, such as using features such as hue, saturation, and value (HSV) or red, green, blue (RGB); template matching, such as described at https: / / www.mathworks.com / help / vision / ug / pattern-matching.html; image segmentation and / or connected component (blob) analysis, such as using size, color, or shape; machine learning and / or deep learning, such as using at least one convolutional neural network. The neural network can be trained by the user, such as in a training program in which the user is instructed to take at least one or more pictures showing himself.

[0069] The analysis of the flood image may comprise determining a plurality of facial features. The analysis may comprise 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 may comprise at least one image generated during a registration process (e.g. when initializing the authentication system). The template may be an image of an authorized user. The template features and / or the facial features may comprise vectors. The matching of the features may comprise determining a distance between the vectors. Identifying the user may comprise comparing the distance of the vectors with at least one predefined limit, wherein the user is successfully identified if the distance is less than or equal to the predefined limit, at least within a tolerance. In other cases, the user is declined or rejected.

[0070] For example, image recognition may include using at least one model, in particular a trained model including at least one facial recognition model. Analysis of the flood image may be performed by using a facial recognition system such as FaceNet, as described, for example, in Florian Schroff, Dmitry Kalenichenko, and James Philbin's "FaceNet: A Unified Embedding for Face Recognition and Clustering [FaceNet]." ： Unified Embeddings for Face Recognition and Clustering] ” , as described in arXiv:1503.03832. The trained model may include at least one convolutional neural network. For example, a 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 details on convolutional neural networks for face recognition systems, see: Florian Schroff, Dmitry Kalenichenko, and James Philbin, “FaceNet: A Unified Embedding for face Recognition and Clustering [FaceNet ： Unified Embeddings for Face Recognition and Clustering] ”, as described in arXiv:1503.03832. Labeled image data from an image database can be used as training data. Specifically, labeled faces from one or more of the following documents can be used: GB Huang, M. Ramesh, T. Berg 和 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; as described in Faces Database, L. Wolf, T. Hassner, and I. Maoz, “Facerecognition in unconstrained videos with matched background similarity” ” ,IEEE International Conference on Computer Vision and Pattern Recognition, 2011; or Facial expression comparison dataset. Convolutional neural network training can be done as in Florian Schroff, Dmitry Kalenichenko, and James Philbin's "FaceNet: A Unified Embedding for face Recognition and Clustering [FaceNet ： Unified Embeddings for Face Recognition and Clustering] ” , as described in arXiv:1503.03832.

[0071] The processor can be configured to correct image artifacts caused by diffraction of light when passing through a transparent display. The term "correction" can mean partially or completely removing the artifact or marking it so that it can be excluded from further processing, in particular from determining whether the person being imaged is an authorized person. Correcting image artifacts can take into account information about the transparent display, in particular the size of the pixels or the distance between repeating features. Correcting image artifacts can include determining the artifacts before analysis and removing the determined artifacts. Image artifacts include lower intensity or irradiance compared to directly radiated light. Therefore, the intensity or irradiance can be used to determine whether the light spot is an artifact. In order to improve the accuracy of determining whether the light spot is an artifact, the intensity or irradiance of the light spot emitted from the illumination source can be increased. Further, the diffraction of a certain type of pattern (such as a hexagonal pattern) can simplify the identification of artifacts and directly radiated light.

[0072] This information can help identify artifacts, as the diffraction pattern can be calculated and compared to the image. Correcting image artifacts can include identifying reflective features, sorting these features by brightness, and selecting the locally brightest features. To determine the distance around a feature in the image that qualifies as local, information about the transparent display can be used. In particular, the distance in the image where the light beam may have been displaced due to diffraction on the transparent display can be calculated based on information about the transparent display. This approach can be particularly useful for patterned images. Further details are disclosed in WO 2021 / 105265 A1.

[0073] The processor can be configured to determine the quality of an image from a camera. Determining the image quality can involve determining the image brightness, specifically determining whether the image brightness is within a predetermined range. This predetermined range can be selected to optimize image recognition results. The processor can generate a signal indicating the image brightness level. This signal can be used, for example, by a projector controller to adjust the projector's illumination power. The camera controller can also use this signal to adjust camera settings based on the brightness signal and / or trigger the camera to generate a new image. Determining the image quality can also involve determining the position of a person's head, specifically the angle of the person's face relative to the camera. It can be determined whether the angle of the person's face relative to the camera is within a predetermined range. This predetermined range can be selected to optimize image recognition results. The processor can generate a signal indicating the person's head position. This signal can be used, for example, by the camera controller to trigger the camera to generate a new image. This signal can also be used to notify the user to turn their head, for example by displaying this information on a transparent display.

[0074] In an embodiment, the processor may determine the quality of the image based on the brightness of the image. Determining the quality based on the brightness may include determining at least one brightness value. For example, ambient light may negatively impact the quality of the image, and detecting an overexposed image may prevent erroneous authentication based on the overexposed image.

[0075] The processor may further be configured to determine material data based on the pattern image. Thus, in particular, the processor may forward the data to a remote device. Alternatively or additionally, the processor may perform material determination based on the pattern image, in particular by running a suitable computer program with corresponding functionality. In particular, by considering the material as a parameter for verifying the authentication process, the authentication process can be robust against fraud using a recorded user image.

[0076] The processor can be configured to extract material data from the pattern image by beam profile analysis of the light spot. Regarding beam profile analysis, reference is made to WO 2018 / 091649 A1, WO 2018 / 091638 A1 and WO 2018 / 091640A1, the entire contents of which are incorporated herein by reference. Beam profile analysis can allow reliable classification of scenes based on several light spots. Each light spot of the pattern image can include a beam profile. The term "beam profile" can generally refer to at least one intensity distribution of a light spot on an optical sensor as a function of a pixel. The beam profile can be selected from the group consisting of: a trapezoidal beam profile; a triangular beam profile; a conical beam profile, and a linear combination of Gaussian beam profiles.

[0077] The processor can be configured to outsource at least one step of the authentication process (such as identification of the user) and / or at least one step of the verification of the authentication process (such as consideration of material data) to a remote device, specifically a server and / or a cloud server. The authentication system and the remote device can be part of a computer network, specifically the Internet. The authentication system can transmit generated data and / or data associated with intermediate steps of the authentication process and / or its verification to the remote device. In this scenario, the processor can be and / or include a connection interface configured to transmit information to the remote device. The data generated by the remote device used in the authentication process and / or its verification can be further transmitted to the authentication system. The data can be received by a connection interface included in the authentication system. The connection interface can be specifically configured to transmit or exchange information. In particular, the connection interface can provide a data transfer connection, such as Bluetooth, NFC, or inductive coupling. As an example, the connection interface can be or can include at least one port, the at least one port including one or more of a network or Internet port, a USB port, and a disk drive.

[0078] The processor is configured to use a facial recognition authentication process operating on the pattern image and / or the extracted material data.The processor may be configured to extract the material data from the pattern image.

[0079] In an embodiment, extracting material data from a pattern image may include generating a material type and / or data derived from the material type. Preferably, extracting material data may be based on the pattern image. Material data may be extracted using at least one model. Extracting material data may include providing the pattern image to the model and / or receiving material data from the model. Providing the image to the model may include and may be followed by receiving the pattern image at the input layer of the model or via a model loss function. The model may be a data-driven model. The data-driven model may include a convolutional neural network and / or an encoder-decoder structure, such as an autoencoder. Other examples for generating representations may include FFT, wavelets, deep learning (such as CNN), energy models, normalized flows, GANs, visual transformers or transformers for natural language processing, autoregressive image modeling, normalized flows, deep autoencoders, and deep energy-based models. Supervised or unsupervised approaches may be applicable to generating representations, and may also be applicable to generating embeddings in ML languages, such as cosine or Euclidean metrics. The data-driven model may be parameterized based on 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 the image to the model and / or receiving material data from the model. In another embodiment, a data-driven model can be trained based on a training dataset comprising at least one image and material data. In another embodiment, a data-driven model can be parameterized based on a training dataset comprising at least one image and material data. The data-driven model can be parameterized based on the training dataset to receive an image and provide material data based on the received image. The data-driven model can be trained based on the training dataset to receive an image and provide material data as output based on the received image. The training dataset can include at least one image and material data (preferably material data associated with at least one image). The image can include a representation of the image. The representation can be a low-dimensional representation of the image. The representation can include at least a portion of the data or information associated with the image. The representation of the image can include a feature vector. In an embodiment, determining the representation, particularly the low-dimensional representation, can be based on a principal component analysis (PCA) map or a radial basis function (RBF) map. Determining the representation can also be referred to as generating a representation. Generating the representation based on the PCA map can include clustering based on features in the pattern image and / or portion of the image. Additionally or alternatively, generating the representation can be based on a neural network structure suitable for dimensionality reduction. The neural network structure suitable for dimensionality reduction can include an encoder and / or a decoder. In an example, the neural network structure can be an autoencoder. In an example, the neural network structure may include a convolutional neural network (CNN). The CNN may include at least one convolutional layer and / or at least one pooling layer. The CNN may reduce the dimensionality of a portion of an image and / or an image by applying convolution (e.g., based on a convolutional layer) and / or by pooling.Applying convolution may be suitable for selecting features related to material information of the pattern image.

[0080] In embodiments, a model may be adapted to determine an output based on an input. In particular, a model may be adapted to determine material data based on an image as input. The model may be a deterministic model, a data-driven model, or a hybrid model. Preferably, a deterministic model reflects physical phenomena in mathematical form, such as a first-principles model. A deterministic model may include a set of equations that describe the interaction between a material and patterned electromagnetic radiation, thereby generating a condition metric, a vital sign metric, or the like. A data-driven model may be a classification model. A hybrid model may include at least one machine learning architecture and model parameters with deterministic or statistical adjustments. Statistical or deterministic adjustments may be introduced to improve the quality of the results, as these adjustments provide a systematic relationship between empiricism and theory. In embodiments, a data-driven model may be a classification model. The classification model may include at least one machine learning architecture and model parameters. For example, the machine learning architecture may be or may include one or more of the following: linear regression, logistic regression, random forest, piecewise linear classifier, nonlinear classifier, support vector machine, naive Bayesian classification, nearest neighbor, neural network, convolutional neural network, generative adversarial network, support vector machine, or gradient boosting algorithm, among others. In the case of a neural network, the model can be a multi-scale neural network or a recurrent neural network (RNN), such as but not limited to a gated recurrent unit (GRU) recurrent neural network or a long short-term memory (LSTM) recurrent neural network. The data-driven model can be parameterized based on a training data set. The data-driven model can be trained based on a training data set. Training the model can include parameterizing the model. The term "training" can also be expressed as learning. The term can specifically refer to the process of building a classification model, in particular determining and / or updating the parameters of the classification model. Updating the parameters of the classification model can also be referred to as retraining. The training referred to herein can include retraining. In an embodiment, the training data set can include at least one image and material information.

[0081] In an embodiment, determining whether the imaged person is an authorized person may include material classification and / or blood perfusion classification. Material classification may include extracting material data from an image generated by a camera and verifying the extracted material data. In an embodiment, blood perfusion classification may include determining a blood perfusion measure based on the image generated by the camera and verifying the blood perfusion measure. Verifying the blood perfusion measure may include determining whether the determined blood perfusion measure corresponds to an expected blood perfusion measure. The expected blood perfusion measure may be a blood perfusion measure associated with an authorized user. Determining whether the determined blood perfusion measure corresponds to the expected blood perfusion measure may include comparing the determined blood perfusion measure to the expected blood perfusion measure. If the determined blood perfusion measure corresponds to the expected blood perfusion measure, authentication may be verified. If the determined blood perfusion measure is outside a range specified by the expected blood perfusion measure, authentication may be invalidated.

[0082] In an embodiment, the light may be coherent light, in particular the patterned infrared radiation may be coherent patterned infrared radiation. Determining the blood perfusion measure may include determining a speckle contrast of the pattern image and determining the blood perfusion measure based on the determined speckle contrast. The speckle contrast may represent a measure of the average contrast of the intensity distribution within the region of the speckle pattern. In particular, the speckle contrast K over the speckle pattern region may be expressed as the product of the standard deviation σ and the average speckle intensity The ratio of

[0083]

[0084] The speckle contrast may include a speckle contrast value. The speckle contrast value may be distributed between 0 and 1. The blood perfusion measure is determined based on the speckle contrast. Therefore, the vital sign measure may depend on the determined speckle contrast. If the speckle contrast changes, the blood perfusion measure derived from the speckle contrast may also change accordingly. The blood perfusion measure may be a single number or value that may indicate the likelihood that the subject is alive. Preferably, the entire pattern image may be used to determine the speckle contrast. Alternatively, a portion of the pattern image may be used to determine the speckle contrast. Preferably, the portion of the pattern image represents an area of ​​the pattern image that is smaller than the area of ​​the entire pattern image. The portion of the pattern image may be obtained by cropping the pattern image. The blood perfusion measure may indicate whether a living human being is detected.

[0085] In an 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 via 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 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 historical images and corresponding historical material data. The data-driven model may be configured to provide material data in response to receiving an image generated, for example, by a camera. An embedding may refer to a low-dimensional representation associated with the image, such as a feature vector. The feature vector may be suitable for suppressing background while maintaining a material signature indicative of material data. In this context, background may refer to information independent of the material signature and / or material data. Further, background may refer to information related to biometric features, such as facial features. Based on the embedding associated with the image, the data-driven model may determine material data. Additionally or alternatively, extracting material data from the image by providing the image to the data-driven model may include transforming the image into material data, particularly a material feature vector indicative of the material data. Therefore, the material data may further include a material characteristic vector and / or the material characteristic vector may be used to determine the material data.

[0086] In an embodiment, the authentication process may be verified based on the extracted material data.

[0087] In an embodiment, verifying based on the extracted material data may include determining whether the extracted material data corresponds to expected material data. Determining whether the extracted material data matches the expected material data may be referred to as verification. Allowing or denying the user and / or subject from performing at least one operation requiring authentication on the device based on the material data may include verifying the authentication or authentication process. Verification may be based on the material data and / or an image. Determining whether the extracted material data corresponds to the expected material data may include determining a similarity between the extracted material data and the expected material data. Determining the similarity between the extracted material data and the expected material data may include comparing the extracted material data with the expected material data. The expected material data may refer to predetermined material data. In an example, the expected material data may be skin. Determining whether the material data corresponds to the expected material data may include comparing the material data with the expected material data. Comparing the material data with the expected material data may result in allowing or denying the user and / or subject from performing the at least one operation requiring authentication. In an example, skin as the expected material data may be compared to non-skin material or silicon as the material data, and the result may be a rejection because silicon or non-skin material may differ from skin.

[0088] In an embodiment, the authentication process or verification thereof may include generating at least one feature vector from the material data and matching the material feature vector with an associated material reference template vector.

[0089] In an embodiment, a person, in particular an authorized person and / or user, may refer to a registered person and / or a registered person. A registered person may be a person who has undergone a registration process. The registration process may be a process for generating a template, in particular a template suitable for comparison with an image of a person recorded by a camera placed behind a transparent display.

[0090] In an embodiment, the illumination and / or recording may be initiated and / or triggered by an authentication request, preferably a payment request. In particular, the illumination and / or recording may be initiated and / or triggered by a payment terminal. Preferably, the illumination and / or recording may be initiated and / or triggered by at least one of a person, a device associated with the person, an application on the device associated with the person, or a combination thereof. The device associated with the person may be a mobile electronic communication device, such as a smartphone.

[0091] The authentication unit may be configured to authenticate the user if the user is recognizable and / or if the material data matches the expected material data. The device may include at least one authorization unit configured to allow the user to perform at least one operation on the device, such as unlocking the device if the user is successfully authenticated, or denying the user from performing at least one operation on the device if the user is unsuccessfully authenticated. Thus, the user can be aware of the result of the authentication.

[0092] In another aspect, the present invention discloses a method for authenticating a user of a device to perform at least one operation requiring authentication on the device.

[0093] The processor is configured to output a signal indicating whether the imaged person is authorized. The signal can be a binary signal, where zero can indicate that the person is not authorized and one can indicate that the person is authorized. The signal can also be a number, such as an integer or floating point value, indicating a probability of whether the person is authorized.

[0094] This signal can be transmitted to a control unit that controls the functions of the vehicle. Based on this signal, the control unit can, for example, unlock the vehicle, start the engine, grant access to an onboard computer system, verify an insurance policy, connect to a remote network, or authenticate an electronic payment, such as for fuel, parking, tolls, vehicle rentals, or digital services such as those found in an app store. In this manner, the authentication system of the present invention can be used to control a vehicle.

[0095] The invention further relates to a method for authenticating a person in a vehicle. Unless expressly described differently hereinafter, the description including the preferred embodiments above applies to this method.

[0096] All described method steps can be performed by hardware in the vehicle. Thus, to determine whether the person being imaged is an authorized person, the processor can be configured to exclusively execute at least one computer program, in particular at least one line of computer program code configured to execute at least one algorithm, as used in at least one of the embodiments of the method according to the present invention. In this document, a computer program executed on a single processing device may include all instructions for causing a computer to perform the method. Alternatively or additionally, at least one method step can be performed using at least one remote device, the at least one remote device being selected in particular from at least one of a server or a cloud server, in particular when the device and the remote device can be part of a computer network. In this case, the computer program may include at least one remote component to be executed by the at least one remote processing device to perform at least one method step. The remote component may have the functionality to perform user identification and / or extraction of material data. Furthermore, the computer program may include at least one interface configured to forward data to and / or receive data from at least one remote component of the computer program.

[0097] The present invention further relates to a non-transient computer-readable medium comprising instructions that, when executed by one or more processors, cause the one or more processors to perform a method according to the present invention. The term "computer-readable data medium" may refer to any suitable data storage device or computer-readable memory having one or more sets of instructions (e.g., software) stored thereon, which embody any one or more of the methods or functions described herein. The instructions may also reside entirely or at least partially in the main memory and / or processor during the execution of the instructions by the computer, main memory, and processing device that may constitute the computer-readable storage medium. These instructions may further be sent or received over a network via a network interface device. The computer-readable data medium may include, for example, a hard drive, a USB storage device, a CD, a DVD, or a Blu-ray disc on a server. The computer program may contain all the functions and data required to perform the method according to the present invention, or may provide an interface to enable portions of the method to be processed on a remote system (e.g., a cloud system).

[0098] In an embodiment, the authentication system may include one or more, preferably two or more, components. The authentication system may be a device configured to authenticate a user of the device. The component(s) may be and / or may include: a transparent display attached to a vehicle; a projector positioned such that the projector can shine light through the transparent display onto a person; a camera positioned such that the camera can receive light from the person through the transparent display; and / or a processor that receives an image from the camera and is configured to determine whether the imaged person is an authorized person, wherein the processor is configured to output a signal indicating whether the imaged person is authorized.

[0099] In an embodiment, triggering recording may include triggering recording of at least two images of the driver through the transparent display while the driver is illuminated by light. The at least two images may be generated at at least two different time points. Further, an indication of at least one interval between the at least two different time points may be provided. A condition metric associated with the driver's condition may be determined based on the at least two pattern images and the indication of the at least one interval.

[0100] In an embodiment, providing the determined condition metric may include: determining whether the determined condition metric may correspond to a target condition metric; and allowing the driver to control at least one function of the vehicle in response to determining that the determined condition metric may correspond to the target condition metric.

[0101] In an embodiment, determining a condition measure associated with the driver's condition based on the at least two pattern images and the indication of the at least one interval may include providing the at least two pattern images and the indication of the at least one interval to a condition model. The condition model may be a data-driven model, particularly based on statistical distributions between the pattern images, the indication of the intervals, and the condition measure. The condition model may be parameterized and / or trained based on historical pattern images, historical indications of the intervals, and historical condition measures. The condition model may be parameterized and / or trained to determine the condition measure in response to being provided with the at least two pattern images and the at least one indication of the intervals.

[0102] A condition metric may be a metric suitable for determining the condition of a living organism. The condition of a living organism may be physical and / or mental. Physical condition may be associated with physical stress levels, fatigue, arousal, suitability for performing a specific task of the living organism, and the like. Mental condition may be associated with mental stress levels, attention span, concentration, arousal, suitability for performing a specific task of the living organism, and the like. Such specific tasks may require the living organism to be focused, attentive, alert, calm, or similar. Examples of such tasks may include: controlling machinery, vehicles, mobile devices, etc.; operating other living creatures; sports-related activities; playing games; emergency tasks; making decisions, and the like. The condition metric indicates the condition of the living organism. The condition metric may be one or more of the following: heart rate, blood pressure, respiratory level, and the like. In some embodiments, the condition of the living organism may be a critical condition corresponding to a high value of the condition metric, and the condition of the living organism may be a non-critical condition corresponding to a low value of the condition metric. Therefore, according to these embodiments, a critical condition metric may be equal to or below a threshold, and a non-critical condition metric may be below a threshold. In other embodiments, the condition of the living organism may be a critical condition corresponding to a low value of the condition metric, and the condition of the living organism may be a non-critical condition corresponding to a high value of the condition metric. Thus, according to these embodiments, the critical condition metric may be equal to or above a threshold value, and the non-critical condition metric may be below a threshold value. The critical condition metric may be associated with a high stress level, low attention, low concentration, high fatigue, high arousal, low fitness for performing a particular task of the living organism, etc. The non-critical condition metric may be associated with a low stress level, high attention, high concentration, low fatigue, low arousal, high fitness for performing a particular task of the living organism, etc.

[0103] A condition measurement of a living organism can be determined based on the movement of bodily fluid, preferably blood, most preferably red blood cells. The movement of bodily fluid is not constant over time, but rather varies due to the activity of parts of the living organism (e.g., the heart). This change in movement can be determined based on changes in feature contrast over time. Large differences between feature contrast values ​​at different time points can be associated with rapid changes in movement. Small differences between feature contrast values ​​at different time points can be associated with slow changes in movement. Changes in the movement of bodily fluid, preferably blood, can be periodically associated with a corresponding movement frequency. Therefore, the feature contrast can vary periodically with the corresponding movement frequency. The movement frequency can correspond to the length of a period associated with the periodic change in feature contrast. In some embodiments, at least two reflection images can include half a period. In other embodiments, at least two reflection images can include one or more periods. Preferably, pattern features associated with the same part of the living organism can be used to determine the condition of the living organism. This is advantageous because different parts of the body have different blood perfusions, and therefore different feature contrasts. In some embodiments, at least one condition measure may be determined based on feature contrast. BRIEF DESCRIPTION OF THE DRAWINGS

[0104] Figure 1 Elements of an authentication system are shown.

[0105] Figure 2 A possible placement of the authentication system on the exterior of the car is shown.

[0106] Figure 3 A possible placement of the authentication system within a car is shown.

[0107] Figure 4 Authentication of a driver in a car is shown. DETAILED DESCRIPTION

[0108] Figure 1 The diagram shows elements of an authentication system 100 attached to a vehicle. The authentication system includes a transparent display 101 that allows light 120 from a projector 102 to pass to a person 110. The light can be infrared light, which is invisible to humans. Transparent display 101 can be transparent only at locations through which light 120 and 130 pass. Transparent can mean that at least 30% or at least 50% of the incident light passes through transparent display 101. Transparent display 101 further allows reflected light 130, which is reflected by person 110, to pass to camera 103. Light 120 can be incident on the person's face, but it can also be incident on the entire head including hair, the upper part of the body (including the head, neck, and shoulders), or even the entire body. Camera 103 generates an image in an optical range that matches the wavelength emitted by projector 102, for example, in the infrared range. The image can be a grayscale image (i.e., each pixel contains only total intensity information) or an RGB image (i.e., different pixels indicate the intensity of a specific wavelength). The image is passed to processor 104. Processor 104 can be a microcontroller, i.e., one that includes memory and IO controller functionality, or it can be a CPU connected to a memory and IO controller. Processor 104 determines whether the person is an authorized person. This determination can involve vectorizing the image into features. This feature vector can be compared to a stored template. If the difference between the feature vector and the stored template is below a predefined threshold, the processor can determine that the person in the vehicle is authorized. The processor can further determine whether the image truly shows a human being and not a deceptive mask. This can be achieved by evaluating the reflective properties of the reflected light to classify the material of the face in the image. If no skin is detected, the processor can determine that the person in front of the transparent display is unauthorized. The processor can generate signal 140 indicating that the person in the vehicle is authorized. Signal 140 can be forwarded to a controller, for example, via a wireless communication interface, to unlock the vehicle, start the engine, grant access to an onboard computer, or enable secure payment.

[0109] Figure 2 Indicates potential locations where a transparent display can be attached to the exterior of a vehicle, such as a car 200. The display can be placed between the windows in the B-pillar 201. Alternatively or additionally, the transparent display can be placed in the side mirror 202.

[0110] Figure 3 Potential locations where a transparent display could be attached inside a vehicle are indicated. The figure shows the dashboard 301 and windshield of a car as seen from inside the car. The transparent display could be integrated into the interior mirror 302. This could be particularly useful if the mirror function were simply mimicked by a display showing the rear view recorded by a camera. Another possibility is the space behind the steering wheel 303, where gauges such as a speedometer are typically placed. Alternatively, the transparent display could be integrated into the steering wheel 304. The center console 305 is another option, as replacing traditional controls with displays is becoming increasingly popular. In an embodiment, the space behind the steering wheel 303 and the center console could be combined into a continuous display.

[0111] Figure 4 An authentication system for a car interior is shown. A transparent display 401 is placed behind the steering wheel, in the dashboard. Light 402 is emitted onto the face of the driver 403. The light reflected by the driver 403 can pass through the transparent display 401, where it is recorded by a camera, which generates an image that is analyzed by a processor to determine whether the person is authorized.

Claims

1. A vehicle authentication system comprising: a transparent display attached to the vehicle, a projector positioned so that the projector can shine light through the transparent display onto a person, a camera positioned so that the camera can receive light from the person through the transparent display, and A processor receives the image from the camera and is configured to determine whether the imaged person is an authorized person, wherein the processor is configured to output a signal indicating whether the imaged person is authorized.

2. Authentication system according to the preceding claim, wherein The transparent display includes organic light emitting diodes.

3. An authentication system according to any one of the preceding claims, wherein: The projector irradiates infrared light onto a person through the transparent display.

4. An authentication system according to any one of the preceding claims, wherein: The projector shines patterned light and flood light onto a person through the transparent display.

5. An authentication system according to any one of the preceding claims, wherein: The projector includes an array of vertical cavity surface emitting lasers.

6. An authentication system according to any one of the preceding claims, wherein: The projector includes at least one metasurface element and / or at least one diffractive optical element.

7. An authentication system according to any one of the preceding claims, wherein: Determining whether the person being imaged is an authorized person includes: extracting material data from images generated by the camera and verifying the extracted material data, and / or • Determining a blood perfusion measure from the image generated by the camera, and validating the blood perfusion measure.

8. An authentication system according to any one of the preceding claims, wherein: Image artifacts caused by diffraction of light when passing through the transparent display are corrected.

9. An authentication system according to any one of the preceding claims, wherein: Determining whether the imaged person is an authorized person includes determining the position of the person's head.

10. Use of an authentication system as claimed in any preceding claim for controlling the vehicle.

11. Use of an authentication system according to the preceding claim, wherein: The authentication system is used to unlock the vehicle, start the engine, grant access to onboard computer systems, connect to a remote network, or verify electronic payments.

12. A vehicle comprising an authentication system according to any one of the preceding claims relating to authentication systems.

13. A method for authenticating a person in a vehicle, the method comprising: illuminating the person with light through a transparent display attached to the vehicle, recording the image of the person through the transparent display, Determine whether the person being imaged is an authorized person, and A signal is output indicating whether the imaged person is authorized.

14. The method according to the preceding claim, wherein The signal is used to control the vehicle.

15. A non-transitory computer readable medium comprising instructions which, when executed by one or more processors, cause the one or more processors to perform the method according to any one of the preceding method-related claims.

Images