Material authentication system

Abstract

The disclosure is in the field of material authentication systems. The disclosure relates to a material authentication system for authenticating an object comprising: a. a camera configured to capture image data of the object under illumination, b. a processor configured to determine if the object is of an expected material using the image data as input to a material model and authenticate the object based on the material determination, wherein the material model comprises an encoder which uses the image data as input and outputs a feature vector representing features in the image data and a material classifier which uses a feature vector as input and outputs a predicted class label, wherein the material model is trained with training data comprising image data captured from objects of the expected material, labelled with the expected material, image data captured from objects of a material other than the expected material, labelled with other material, and random image data labelled with other material, wherein the random image data comprises feature vectors comprising random values for training the material classifier.

Description

[0001] Material Authentication System

[0002] The disclosure is in the field of material authentication systems. The disclosure relates to a material authentication system for authenticating an object, a computer-implemented method for generating datasets for training a material authentication system, a use of the datasets obtained by the method for training a material authentication system, a system for generating datasets for training a material authentication system, and a non-transient computer-readable medium including instructions that, when executed by one or more processors, cause the one or more processors to perform a method for generating datasets for training a material authentication system.

[0003] Background

[0004] Face authentication is a powerful security feature for access control, for example to a device such as a smartphone or building, or for authentication of a person, for example for online payments. To make face authentication even more secure, the material from the characteristic reflection of patterned light can be detected. Such patterned light images are classified with a trained material model, for example as described in WO 2023 / 156315 A1. In this way, it is possible to distinguish between a real face and a spoofing mask. The identity of a person can be identified from a floodlight image with a 2D image recognition algorithm. Subsequently, a material model can verify if the presented face is a real face or a spoofing mask.

[0005] The material model needs to be trained with labelled data. Both real persons and spoofing masks need to be recorded. However, there are quite a lot of materials for spoofing masks conceivable and it is unfeasible to record all such materials. However, the material model may be unreliable for materials which it has not been trained for, so it may erroneously classify an unknown material as skin. Such errors make the system vulnerable and need to be avoided.

[0006] Anuj Rai et al. disclose in their article "An Open Patch Generator based Fingerprint Presentation Attack Detection using Generative Adversarial Network” on arXiv.org (arXiv:2306.03577v1) a fingerprint recognition system which has been trained with synthetic samples. However, no details of this method are provided.

[0007] Summary

[0008] The objective of the present disclosure was to provide a material authentication system with material classification functionality which is more robust against spoofing attacks.

[0009] In one aspect the disclosure relates to a material authentication system for authenticating an object comprising: a. a camera configured to record image data of the object under illumination, b. a processor configured to determine whether the object is made of an expected material by using the image data as input to a material model and authenticate the object based on the material determination, wherein the material model is trained with training data comprising image data recorded from objects of the expected material, labelled with the expected material, image data recorded from objects of a material other than the expected material, labelled with other material, and random image data labelled with other material.

[0010] In another aspect the disclosure relates to a material authentication system for authenticating an object comprising: a. a camera configured to capture image data of the object under illumination, b. a processor configured to determine whether the object is made of an expected material by using the image data as input to a material model and authenticate the object based on the material determination, wherein the material model comprises an encoder which uses the image data as input and outputs a feature vector representing features in the image data and a material classifier which uses a feature vector as input and outputs a predicted class label, wherein the material model is trained with training data comprising image data captured from objects of the expected material, labelled with the expected material, image data captured from objects of a material other than the expected material, labelled with other material, and random image data labelled with other material, wherein the random image data comprises feature vectors comprising random values for training the material classifier.

[0011] In another aspect the disclosure relates to a computer-implemented method for generating training data for training a material authentication system comprising: a. receiving a set of image data with a label indicating whether the image data is associate with an expected material or not, b. generating training data for training a material authentication system using the received image data and random image data with a label indicating that the image data is not associated with the expected material, and c. outputting the training data.

[0012] In another aspect the disclosure relates to a computer-implemented method for generating training data for training a material authentication system comprising: a. receiving a set of image data with a label indicating whether the image data is associate with an expected material or not, b. generating training data for training a material authentication system comprising a material model comprising an encoder which uses the image data as input and outputs a feature vector representing features in the image data and a material classifier which uses a feature vector as input and outputs a predicted class label, wherein generating training data uses the received image data and random image data with a label indicating that the image data is not associated with the expected material and wherein the random image data comprises feature vectors comprising random values for training the material classifier, and c. outputting the training data.

[0013] In another aspect the disclosure relates to a use of the training data obtained by the method for training a material authentication system.

[0014] In another aspect the disclosure relates to a system for generating training data for training a material authentication system comprising: a. an input for receiving a set of image data with a binary label indicating whether the image data is associate with an expected material or not, b. a processor for generating training data for training a material authentication system comprising the received image data and random image data with a label indicating that the image data is not associated with the expected material, and c. outputting the training data.

[0015] In another aspect the disclosure relates to a system for generating training data for training a material authentication system comprising: a. an input for receiving a set of image data with a binary label indicating whether the image data is associate with an expected material or not, b. a processor for generating training data for training a material authentication system comprising a material model comprises an encoder which uses the image data as input and outputs a feature vector representing features in the image data and a material classifier which uses a feature vector as input and outputs a predicted class label, wherein generating training data uses the received image data and random image data with a label indicating that the image data is not associated with the expected material, and c. outputting the training data.

[0016] In another aspect the disclosure relates to a non-transient computer-readable medium including instructions that, when executed by one or more processors, cause the one or more processors to perform a method comprising: a. receiving image data with a label indicating whether the image data is associate with an expected material or not, b. generating training data for training a material authentication system comprising the received image data and random image data with a label indicating that the image data is not associated with the expected material, and c. outputting the training data. In another aspect the disclosure relates to a non-transient computer-readable medium including instructions that, when executed by one or more processors, cause the one or more processors to perform a method comprising: a. an input for receiving a set of image data with a binary label indicating whether the image data is associate with an expected material or not, b. a processor for generating training data for training a material authentication system comprising a material model comprises an encoder which uses the image data as input and outputs a feature vector representing features in the image data and a material classifier which uses a feature vector as input and outputs a predicted class label, wherein generating training data uses the received image data and random image data with a label indicating that the image data is not associated with the expected material, and c. outputting the training data.

[0017] The addition of random image data to the training data for a material model makes the model more robust against spoofing attacks. This is in particular the case for attacks with spoofing masks with materials which have not been represented in the training dataset. The random image data helps the material model in the training process to more specifically identify features which are characteristic for the expected material in comparison to any other material. In this way, the expected material can be detected more reliably. The disclosure further helps to reduce the required effort in providing image data for training the material model. In particular if randomized feature vectors rather than randomized images are used, the material determination for materials which are not part of the training material is enhanced, presumably as such randomized feature vectors more closely resemble those obtained from other materials other than in randomized images.

[0018] The term "material authentication system” may refer to a device, part of a device or device assembly which can be used to authenticate a material of an object, i.e. determine if the object is made of an expected material. Examples for material authentication may be in the context of apparel, such as authenticating if a suit is of silk or if a jacket is of real leather. Material authentication may be in the context of quality control such as ensuring the correct material composition of a good, such as chocolate or medical implants. Material authentication may be used for biometric authentication, i.e. the material authentication system may be a biometric authentication system. The material authentication system may be integrated into a mobile computing device, for example a smartphone, a tablet, a smartwatch or a laptop, into a vehicle, for example a car, a truck, a motorcycle, a train, an airplane, into a access system for a building or a gate.

[0019] The term "object” may refer to any object which can be measured with light. An object can be a living body, for example a human, or a non-living object. An object may refer to a complete object or a small piece thereof, for example a sample extracted from the object. In case of a living body, the object may refer to a body part, for example face or hand. The term "biometric authentication” may refer to any procedure which uses a characteristic of a human to identify if a real human is present, i.e. in front of the biometric authentication system, or not. In the context of the present disclosure, the characteristic of the human is a material. The material may be any material which is found in a human body, for example skin, hair, or cornea tissue. Biometric authentication may be combined with biometric recognition, i.e. the determination which person is present. Biometric recognition may include optical biometric recognition like face recognition, iris scan, palm scan or fingerprint scan; or acoustic recognition like voice recognition. Optical biometric recognition may be passive, i.e. an image is captured of the user or part of the user to be recognized, wherein the user is only under irradiation of ambient light. Optical biometric recognition may be active, i.e. an image is captured of the user or part of the user to be recognized, wherein the user is only under irradiation of light emitted by a projector.

[0020] The term "light” may refer to electromagnetic radiation in one or more of the infrared, the visible and the ultraviolet spectral range. Herein, the term "ultraviolet spectral range”, generally, refers to electromagnetic radiation having a wavelength of 1 nm to 380 nm, preferably of 100 nm to 380 nm. Further, in partial accordance with standard ISO- 21348 in a valid version at the date of this document, the term "visible spectral range”, generally, refers to a spectral range of 380 nm to 760 nm. The term "infrared spectral range” (IR) generally refers to electromagnetic radiation of 760 nm to 1000 m, wherein the range of 760 nm to 1.5 pm is usually denominated as "near infrared spectral range” (NIR) while the range from 1.5 p to 15 pm is denoted as "mid infrared spectral range” (MidlR) and the range from 15 pm to 1000 pm as "far infrared spectral range” (FIR). Preferably, light used for the typical purposes of the present disclosure is light in the infrared (IR) spectral range, more preferred, in the near infrared (NIR) and / or the mid infrared spectral range (MidlR), especially the light having a wavelength of 1 pm to 5 pm, preferably of 1 pm to 3 pm.

[0021] The material authentication system may comprise a projector. The term "projector” may refer to a device configured to generat or provid light in the sense of the above-mentioned definition. The projector may be a pattern projector, a floodlight projector or both either simultaneously or the projector may repeatedly switch from illuminating patterned light to floodlight.

[0022] The term "pattern projector” may refer to a device configured to generate or providing 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 spot may be at least partially spatially extended. At least one spot or any spot may have an arbitrary shape. In some cases, a circular shape of at least one spot or any spot may be preferred. The spots may be arranged by considering a structure of a display comprised by a device that is further comprising the optoelectronic apparatus. Typically, an arrangement of an OLED-pixel-structure of the display may be considered. The term "infrared light pattern” may refer to a light pattern comprising spots in 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. The pattern projector may be configured to emit monochromatic light, e.g. in the near infrared region. The term "monochromatic” may refer to light with a wavelength accuracy of less or equal to ± 2 % or less or equal to ± 1 %. The wavelength accuracy may be the maximum difference of emitted wavelength relative to the mean wavelength. In other embodiments, the pattern projector may be adapted to emit light with a plurality of wavelengths, e.g. for allowing additional measurements in other wavelengths channels.

[0023] The infrared light pattern may comprise 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 comprising further convex tilings. For example, the infrared light pattern is a hexagonal pattern, preferably a hexagonal infrared light pattern. The illumination pattern may comprise a number of rows on which the illumination features are arranged in equidistant positions with distance d. The rows may be orthogonal with respect to the epipolar lines. A distance between the rows may be constant. A different offset may be applied to each of the rows in the same direction. The offset may result in that the illumination features of a row are shifted. The offset 5 may be 5= a / b, wherein a and b are positive integer numbers such that the illumination pattern is a periodic pattern. For example, 5 may be 1 / 3 or 2 / 5. Using a periodical pattern with said offset can allow distinguishing between artefacts and usable signal.

[0024] The light pattern may comprise less than 4000 spots, for example less than 3000 spots or less than 2000 spots or less than 1500 spots or less than 1000 spots. The light pattern may comprise patterned coherent infrared light of less than 4000 spots or less than 3000 spots or less than 2000 spots or less than 1500 spots or less than 1000 spots.

[0025] At least one of the infrared light 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 an increase in at least one diameter and / or at least one diameter equivalent, such as a radius, with a distance from an optical aperture from which the beam emerges. The measure may be an angle or an angle equivalent. In the context of the present disclosure, typically, a beam divergence may be determined at 1 / e2.

[0026] The pattern projector may comprise at least one pattern projector configured to generate the infrared light pattern. The pattern projector may comprise 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 the infrared light pattern. The emitter may comprise at least one element selected from the group consisting of at least one laser source such as at least one semi-conductor laser, at least one double heterostructure laser, at least one external cavity laser, at least one separate 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 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 50 one diode pumped laser, at least one distributed feedback lasers, 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); at least one non-laser light source such as at least one LED or at least one light bulb. For example, the pattern projector comprises at least one least one VCSEL, preferably a plurality of VCSELs. The plurality of VCSELs may be arranged in at least one array, e.g. comprising a matrix of VCSELs. 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 laser beam emission perpendicular with respect to a top surface. Examples for VCSELs can be found e.g. in en.wikipedia.org / wiki / Verticalcavity_surface-emitting_laser. VCSELs are generally known to the skilled user such as from WO 2017 / 222618 A. Each of the VCSELs is configured to generate at least one light beam. The plurality of generated spots may be associated with the infrared light pattern. The VCSELs may be configured to emit light beams at a wavelength range from 800 to 1000 nm. For example, the VCSELs may be configured to emit light beams at 808 nm, 850 nm, 940 nm, and / or 980 nm. Preferably the VCSELs emit light 940 nm, since terrestrial sun radiation has a local minimum in irradiance at this wavelength, e.g. as described in CIE 085-1989 „Solar spectral Irradiance”.

[0027] The pattern projector may comprise at least one optical element configured to increase, e.g. duplicating, the number of spots generated by the pattern projector. The pattern projector, particularly the optical element, may comprises at least one diffractive optical element (DOE) and / or at least one meta surface element. The DOE and / or the meta surface element may be configured to generate multiple light beams from a single incoming light beam. Further arrangements, particularly comprising a different number of projecting VCSEL and / or at least one different optical element configured to increase the number of spots may be possible. Other multiplication factors are possible. For example, a VCSEL or a plurality of VCSELs may be used and the generated laser spots may be duplicated by using at least one DOE.

[0028] The pattern projector may comprise at least one transfer device. The term "transfer device”, also denoted as "transfer system” may refer to one or more optical elements which are adapted to modify the light beam, particularly the light beam used for generating at least a portion of the infrared light pattern, such as by modifying one or more of a beam parameter of the light beam, a width of the light beam or a direction of the light beam. The transfer device may comprise at least one imaging optical device .The transfer device specifically may comprise one or more of: at least one lens, for example at least one lens selected from the group consisting of at least one focus-tunable lens, at least one aspheric 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 deflection element, preferably at least one mirror; at least one beam splitting element, preferably at least one of a beam splitting cube or a beam splitting mirror; at least one multi lens system; at least one holographic optical element; at least one meta optical element. Specifically, the transfer device comprises at least one refractive optical lens stack. Thus, the transfer device may comprise a multi-lens system having refractive properties. The pattern projector may be configured to emit modulated or non-modulated light. In case a plurality of emitters is used, the different emitters may have different modulation frequencies, e.g. which can be used for distinguishing the light beams.

[0029] The light beam or light beams generated by the pattern projector may propagate parallel to an optical axis. The pattern projector may comprise at least one reflective element, preferably at least one prism, for deflecting the illuminating light beam onto the optical axis. As an example, the light beam or light beams, such as the laser light beam, and the optical axis may include an angle of less than 10°, preferably less than 5° or even less than 2°. Other embodiments, however, are feasible. Further, the light beam or light beams may be on the optical axis or off the optical axis. As an example, the light beam or light beams may be parallel to the optical axis having a distance of less 10 than 10 mm to the optical axis, preferably less than 5 mm to the optical axis or even less than 1 mm to the optical axis or may even coincide with the optical axis.

[0030] 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 portion of the user and / or a face of the user, with a spatially constant or essentially constant illumination intensity. The term "flood light” 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 least one VCSEL, preferably a plurality of VCSELs, for example an array of VCSELs. The term "substantially continuous spatial illumination” may refer to uniform spatial illumination, wherein areas of non-uniform are possible.

[0031] A relative distance between the flood projector and the pattern projector may be below 3.0 mm. The relative distance between the flood projector and the pattern projector may be below 2.5 mm, preferably below 2.0 mm. The pattern projector and the flood projector may be combined into one module. For example, the pattern projector and the flood projector may be arranged on the same substrate, in particular having a minimum relative distance. The minimum relative distance may be defined by a physical extension of the flood projector and the pattern projector. Arranging the pattern projector and the flood projector having a relative distance below 3.0 mm can result in decreased space requirement of the two projectors. In particular, said projectors can even be combined into one module. Such a reduced space requirement can allow reducing the transparent area(s) in a display necessary for operation of the projector(s) behind the display.

[0032] In an embodiment, the pattern projector and the flood projector may comprise at least one VCSEL, preferably a plurality of VCSELs, for example an array of VCSELs. The pattern projector may comprise a plurality of first VCSELs mounted on a first platform. The flood projector may comprise a plurality of second VCSELs mounted on a second platform. The second platform may be beside the first platform. The optoelectronic apparatus may comprise a heat sink. Above the heat sink a first increment comprising the first platform may be attached. Above the heat sink a second increment comprising the second platform may be attached. The second increment may be different from the first increment. Thus, the first platform may be more distant to the optical element configured to increase, e.g. duplicating, the number of 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 spots. This leads to a substantially continuous illumination and, thus, to flood illumination.

[0033] The projector may be positioned such that it can illuminate light through the transparent display. Hence, light emitted by the projector may cross the transparent display before it impinges on the user. From the user's view, the projector may be placed behind the transparent display.

[0034] The material authentication system comprises a camera. The term "camera” may refer to at least one unit of the optoelectronic apparatus configured to generate at least one image. The image may be generated via a hardware and / or a software interface, which may be considered as the camera. The term "image generation” may refer to capturing and / or generating and / or determining and / or recording at least one image by using the camera. The image generation may comprise imaging and / or recording the image. The image generation may comprise capturing a single image and / or a plurality of images such as a sequence of images. For generating an image via a hardware and / or a 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 the software interface. For example, the image generation may comprise recording continuously a sequence of images such as a video or a movie. The image generation may be initiated by a user action or may automatically be initiated, e.g. once the presence of at least one object or user within a field of view and / or within a predetermined sector of the field of view of the camera is automatically detected.

[0035] 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 captured by using the optical sensor, such as a plurality of electronic readings from the CMOS or CCD chip. The image may comprise raw image data or may be a pre-processed image. For example, the pre-processing may comprise applying at least one filter to the raw image data and / or at least one background correction and / or at least one background subtraction.

[0036] For example, the camera may comprise a color camera, e.g. 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 the black and white pixels may be combined internally in the camera. The camera may comprise a color camera (e.g. RGB) or a black and white camera, such as a black and white CMOS. The camera may comprise a black and white CMOS chip. The camera generally may comprise a one-dimensional or two-dimensional array of image sensors, such as pixels. The color camera may be an internal and / or external camera of a device comprising the optoelectronic apparatus. The internal and / or external camera of the device may be accessed via a hardware and / or a software interface comprised by the optoelectronic apparatus, which is used as the camera. In case, the device is or comprises a smartphone the image generating unit may be a front camera, such as a selfie camera, and / or back camera of the smartphone.

[0037] The camera may have a field of view between 10°x10° and 75°x75°, preferably 55°x65°. The camera may have a resolution below 2 megapixel (MP), for example 0.3 to 1 .8 MP, such as 0.5 MP and 1 .6 MP or 1 .0 to 1 .5 MP.

[0038] The camera may comprise further elements, such as one or more optical elements, e.g. one or more lenses. As an example, the optical sensor may be a fix-focus camera, having at least one lens which is fixedly adjusted with respect to the camera. Alternatively, however, the camera may also comprise one or more variable lenses which may be adjusted, automatically or manually. Other cameras, however, are feasible.

[0039] The term "pattern image” may refer to an image generated by the camera while illuminating the infrared light pattern, e.g. on an object and / or a user. The pattern image may comprise an image showing a user, in particular at least parts of the face of the user, while the user is being illuminated with the infrared light pattern, particularly on a respective area of interest comprised by the image. The pattern image may be generated by imaging and / or recording light reflected by an object and / or user which is illuminated by the infrared light pattern. The pattern image showing the user may comprise at least a portion of the illuminated infrared light pattern on at least a portion the user. For example, the illumination by the pattern illumination source and the imaging by using the optical sensor may be synchronized, e.g. by using at least one control unit of the optoelectronic apparatus.

[0040] The term "flood image” may refer to an image generated by the camera while illumination source is illuminating infrared flood light, e.g. on an object and / or a user. The flood image may comprise an image showing a user, in particular the face of the user, while the user is being illuminated with the flood light. The flood image may be generated by imaging and / or recording light reflected by an object and / or user which is illuminated by the flood light. The flood image showing the user may comprise at least a portion of the flood light on at least a portion the user. For example, the illumination by the flood illumination source and the imaging by using the optical sensor may be synchronized, e.g. by using at least one control unit of the optoelectronic apparatus.

[0041] The camera may be configured to capture and / or image and / or record the pattern image and the flood image at the same time or at different times. The camera may be configured to capture and / or image and / or record the pattern image and the flood image at at least partially overlapping measurement areas or equivalents of the measurement areas. The material authentication system may comprise a transparent display. The camera or the projector may be placed behind the transparent display in order maximize the display area of a device. The term "display” may refer to an arbitrary shaped device configured to display an item of information. The item of information may be arbitrary information such as at least one image, at least one diagram, at least one histogram, at least one graphic, text, numbers, at least one sign, or an operating menu. The display may be or may comprise at least one screen. The display may have an arbitrary shape, e.g. a rectangular shape. The display may be a front display of the device.

[0042] The display may be or may comprise 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 an emissive electroluminescent layer is a film of organic compound configured to emit light in response to an electric current. The OLED display may be configured to emit visible light. The display, particularly a display area, may be covered by glass. In particular, the display may comprise at least one glass cover.

[0043] The transparent display may be at least partially transparent. The term "at least partially transparent” may refer to a property of the display to allow light, in particular of a certain wavelength range, e.g. in the infrared spectral region, in particular in the near infrared spectral region, to pass at least partially through. For example, the display may be semitransparent 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 a different transparency 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. The transparent display may be at least partially transparent over the entire display area or only parts thereof. Typically, it is sufficient if only those parts of the display area are at least partially transparent trough which light needs to pass from the projector or to the camera.

[0044] The display comprises a display area. The term "display area” may refer to an active area of the display, in particular an area which is activatable. 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 first PPI value is equal to or below 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 the at least one continuous area being at least partially transparent.

[0045] Biometric authentication may comprise identifying the object based on the flood image. The term "identifying” may refer to identity check and / or verifying an identity of the object. The identifying of the object may comprise analyzing the flood image. The analyzing of the flood image may comprise performing a face verification of the imaged face to be the user's face. The identifying the object may comprise matching the flood image, e.g. showing a contour of parts of the user, in particular parts of the user's face, with a template. Determining if the imaged face is the face of the user may comprise identifying the user, in particular determining if the imaged face corresponds to at least one image of the user's face stored in at least one memory, e.g. of the device. The analyzing may comprise one or more of the following: a filtering; a selection of at least one region of interest; a formation of a difference image between the flood image and at least one offset; an inversion of flood image; a background correction; a decomposition into color channels; a decomposition into hue; saturation; and brightness channels; a frequency decomposition; a 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 Laplace 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 transformation; applying a Radon- transformation; applying a Hough-transformation; applying a wavelet-transformation; a thresholding; creating a binary image. The region of interest may be determined manually by a user or may be determined automatically, such as by recognizing the user within the image. In particular, the analyzing of the flood image may comprise using at least one image recognition technique, in particular a face recognition technique. An image recognition technique comprises at least one process of identifying the user in an image. The image recognition may comprise using at least one technique selected from the technique consisting of: color-based image recognition, e.g. using features such as hue, saturation, and value (HSV) or red, green, blue (RGB); template matching, for example as illustrated on https: / / www.mathworks.com / help / vision / ug / pattern-matching.html; image segment and / or blob analysis e.g. using size, color, or shape; machine learning and / or deep learning e.g. using at least one convolutional neural network.

[0046] The neural network may be trained by the user, such as in a training procedure, in which the user is indicated to take at least one or a plurality of pictures showing himself.

[0047] The analyzing of the flood image may comprise determining a plurality of facial features. The analyzing may comprise comparing, in particular matching, the determined facial features with template features. The template features may be features extracted from at least one template. The template may be or may comprise at least one image generated in an enrollment process, e.g. when initializing the authentication system. Template may be an image of an authorized user. The template features and / or the facial feature may comprise a vector. Matching of the features may comprise determining a distance between the vectors. The identifying of the user may comprise comparing the distance of the vectors to a least one predefined limit, wherein the user is successfully identified in case the distance is smaller than or equal to the predefined limit at least within tolerances. The user declining and / or rejected otherwise.

[0048] For example, the image recognition may comprise using at least one model, in particular a trained model comprising at least one face recognition model. The analyzing of the flood image may be performed by using a face recognition system, such as FaceNet, e.g. as described in Florian Schroff, Dmitry Kalenichenko, James Philbin, "FaceNet: A Unified Embedding for Face Recognition and Clustering”, arXiv: 1503.03832. The trained model may comprises at least one convolutional neural network. For example, the convolutional neural network may be designed as described in M. D. Zeller 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 with respect to convolutional neural network for the face recognition system reference is made to Florian Schroff, Dmitry Kalenichenko, James Philbin, "FaceNet: A Unified Embedding for Face Recognition and Clustering”, arXiv: 1503.03832. As training data labelled image data from an image database may be used. Specifically, labeled faces may be used from one or more of G. B. 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® 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 Google® Facial Expression Comparison dataset. The training of the convolutional neural network may be performed as described in Florian Schroff, Dmitry Kalenichenko, James Philbin, "FaceNet: A Unified Embedding for Face Recognition and Clustering”, arXiv: 1503.03832.

[0049] Image artifacts caused by diffraction of the light when passing the transparent display may be corrected. The term "correct” may mean partially or fully remove the artifacts or tag them so they can be excluded from further processing, in particular from determine if the imaged user is an authorized user. Correcting image artifacts may take into account the information about the transparent display, in particular the dimensions of the pixels or the distance of repeating features to each other. This information can facilitate identifying artifacts as diffraction patterns can be calculated and compared to the image. Correcting image artifacts may comprise identifying reflection features, sorting them by brightness and selecting the locally brightest features. For determining a distance around a feature in the image which qualifies as local, the information of the transparent display may be used, in particular a distance in the image by which a light beam may be displaced by diffraction on the transparent display may be calculated based on the information about the transparent display. This method can be particularly useful for pattern images. Further details are disclosed in WO 2021 / 105265 A1.

[0050] The term "image data” may refer to data associated with one or more images recorded with a camera. The image data may comprise one or more images as received from a camera, or it may comprise data derived from one or more images, for example from images received from a camera. The term "derived” may mean adjustments to the image, for example change of contrast or brightness, cropping, for example removal of background sections, division into multiple partial images, transformation into a different format, for example into a feature vector. Image data may comprise one or more pattern images and / or one or more flood images. Image data may comprise multiple partial images derived from an image, for example from a pattern image. In particular, image data may comprise multiple partial images, where a partial image obtained from a pattern image by cropping around a pattern feature. A partial image may comprise one pattern feature or a subset of image features of the pattern image, for example one pattern features and at least parts of its nearest neighboring pattern features.

[0051] The image data may be augmented by adding further image data labelled with the expected material. The further image data may be generated by variations of the image data labelled with the expected material. Such augmentation may reduce the tendency of generating skewed training data, i.e. training data with too little data labelled with the expected material. For example, further image data may be generated by adding a small amount of noise to the image data. Alternatively, or additionally, further image data may be generated by linear or non-linear combinations of the image data labelled with the expected material. The image data may comprise feature vectors obtained by encoding images. The further image data may be obtained by adding a small amount of noise to the feature vectors or by adding random values to the feature vectors according to a distribution of the value of the feature vectors in the image data labelled with the expected material.

[0052] The material authentication comprises determining whether the object is made of an expected material by using the image data as input to a material model. In other words, a material model is used to determine the material of the object. The material model may receive the image data as input and output an indicator indicating if the object is of the expected material.

[0053] The term "expected material” may refer to a material to be expected for an object. For example, in face authentication a human face is expected to be of skin while spoofing masks may be made of a broad variety of materials, for example silicone, latex, fiberglass, plastic or a resin. The expected material can be one material or more than one, for example two, such as skin or hair. The determination whether the object is of an expected material may yield a predicted class label indicating whether the object is of the expected material. The predicted class label may be zero-dimensional, for example a categorial value, like a Boolean, or a numerical value, such as a float value, representing the probability that the object if of the expected material. For the case that there is more than one expected material, the predicted class label may be one-dimensional, for example a vector comprising an entry for each expected material and one for any other material, for example a vector with three values, wherein the first value indicates if the object is of the first expected material, the second value indicates if the object is of a second expected material and the third values indicates if the object is of any other material, i.e. a material which is neither the first expected material nor the second expected material. The values of the one-dimensional predicted class label may be a categorial value, like a Boolean, or a numerical value, such as a float value representing a probability that the object if of the material associated with the value.

[0054] The term "material model” may refer to a model which uses image data as input and outputs a predicted class label indicating the material of the object. The material model may be or may comprise an artificial neural network, in particular a convolutional neural network (CNN), a support vector machine (SVM), a random forest, a Gaussian mixture model (GMM), a hidden Markov model (HMM) or a conditional random field (CRF).

[0055] The material model may comprise an encoder and a material classifier. The term "encoder” may refer to an algorithm which uses the image data as input and output a feature vector representing features in the image data. The encoder may be or may comprise a convolutional neural network (CNN), an autoencoder, a histogram of oriented gradients (HOG), a scale-invariant feature transform (SIFT), speeded-up robust features (SURF) or bag-of-visual-words (BoVW). The image data may comprise multiple images, for example a set of partial images, wherein each partial image is obtained by cropping a pattern image around a pattern feature. The encoder may encode each partial image into a corresponding feature vector, so multiple feature vectors are obtained.

[0056] The term "material classifier” may refer to an algorithm which uses a feature vector as input and outputs a predicted class label. The material classifier may be or may comprise a support vector machine (SVM), a random forest, a K- nearest neighbors (KNN), naive Bayes, decision tree, a gradient boosting model. The encoder may have generated multiple feature vectors. The material classifier may determine a predicted class label for each feature vector. Hence, the material classifier may determine multiple predicted class labels. The material classifier may aggregate the multiple predicted class labels into one aggregated predicted class label, for example by averaging or by weighted averaging. The weights of the weighted averaging may be variable parameters of the material model which are adjusted during training the material model.

[0057] The material model is trained with a training dataset comprising labelled image data. The training dataset may comprise:

[0058] I. image data recorded from objects of the expected material, labelled with the expected material,

[0059] II. image data recorded from objects of a material other than the expected material, labelled with other material, ill. random image data labelled with other material.

[0060] The term "random image data” may refer to data having the same format as image data, but containing random or pseudo-random values, for example values generated by a random generator. The random generator may use a uniform distribution algorithm, a normal or Gaussian distribution algorithm, for example the Box-Muller transform or Ziggurat algorithm, a Bernoulli distribution algorithm, a multinomial distribution algorithm, a permutation algorithm, i.e. an algorithm for shuffling or randomly reordering elements in a dataset, or a pseudorandom number generators, such as the Mersenne Twister algorithm. Random image data may also refer to image data generated by adding random or pseudo-random values to real image data. Random image data may correlate with real image data. For example, random image data may be generated such that it has the same or essentially the same value distribution. For example, random image data may be generated with an algorithm which generates random number of the same or a similar distribution as the corresponding values in the real image data.

[0061] Random image data may comprise a feature vector comprising random values. The feature vector may have the same format as the output of an encoder which encodes images. A material model comprising an encoder and a material classifier may first be trained with images recorded from objects of the expected material labelled with the expected material, and images recorded from objects of a material other than the expected material labelled with other material. Subsequently, the material classifier may be retrained with training data including random feature vectors. Random feature vectors may comprise random values, i.e. freely determined with a random generator. Random feature vectors may be derived from feature vectors obtained from real images, for example random feature vectors may be obtained by adding random values to feature vectors obtained from the received image data. The arithmetic mean of the added random values may smaller than the arithmetic mean of the values of the feature vectors obtained from the received image data, for example 0.01 to 0.9 times or 0.05 to 0.5 times. Random feature vectors may comprise feature vectors having the same or a similar distribution of values as the feature vectors obtained from real images, for example as the feature vectors obtained from the received image data. The same distribution may mean that the values have the same arithmetic mean and the same standard deviation. Similar may mean that the arithmetic mean and standard deviation of the values of the random feature vectors differ from those of the feature vectors obtained from real images by less than 10 %, by less than 3 % or by less than 1 %.

[0062] The number of images of the random image data may be on the order of the number of images of the image data. In case the image data comprises partial images or feature vectors, the number of images refers to the images from which the partial images or feature vectors are generated from. Alternatively, the number of feature vectors of the random image data may be on the order of the number of feature vectors of the image data. If too much random image data is produced, the training data may become skewed, i.e. contain too little data for the expected material in comparison to the data for the non-expected materials. For example, the number of images the random image data relates to may be 0.1 to 10 times the number of images the image data relates to, preferably 0.2 to 5 times the number of images the image data relates to, in particular 0.5 to 2 times the number of images the image data relates to. Alternatively, the number of feature vectors of the random image data may be 0.1 to 10 times the number of feature vectors of the image data, preferably 0.2 to 5 times the number of feature vectors of the image data, in particular 0.5 to 2 times the number of feature vectors of the image data.

[0063] The magnitude of the images of feature vectors of the random image data may be on the order of the magnitude of the images of feature vectors of the image data. This may mean that corresponding values are of similar size and multiple values have a similar distribution. For example, in case of a feature vector, the average values of the features in the vector of a random image may be between 0.1 and 10 times the average values of features in the vector of an image of the image data, such as between 0.5 and 2 times. The feature vectors of the random image data may have a mean and variance between 0.1 and 10 times the mean and variance of feature vectors of image data. For example, feature vectors may be normalized, so both feature vectors of image data and feature vectors of random image data may have a mean of 0 and a variance of 1 .

[0064] The material model may be trained using the training dataset, for example by minimizing a loss function indicative for how well the predicted class labels match the labels of the training dataset. The loss function may be minimized by gradient descent including stochastic gradient descent (SGD), mini-batch gradient descent, or adaptive gradient descent algorithms like Adam or RMSprop. The loss function may be a cross-entropy loss function, binary crossentropy loss, triplet loss, contrastive loss, center loss, margin loss, focal loss, or dice loss. If the material model comprises an encoder and a material classifier, both may be pre-trained using the image data and its associated labels. The material classifier may subsequently be retrained with random image data comprising random feature vectors.

[0065] The material authentication system comprises a processor. The term "processor” may refer to a logic circuitry configured to perform basic operations of a computer or system, and / or, generally, to a device which is configured to perform calculations or logic operations. In particular, the processor may be configured to process basic instructions that drive the computer or system. As an example, the processor may comprise at least one arithmetic logic unit (ALU), at least one floating-point unit (FPU), such as a math co-processor or a numeric co-processor, a plurality of registers, specifically registers configured to supply operands to the ALU and storing results of operations, and a memory, such as an L1 and L2 cache memory. In particular, the processor may be a multi-core processor.

[0066] Specifically, the processor may be or may comprise a central processing unit (CPU). Additionally or alternatively, the processor may be or may comprise a micro-processor, thus specifically the processor's elements may be contained in one single integrated circuitry (IC) chip. Additionally or alternatively, the processor may be or may comprise 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 unit (TPU) and / or one or more chip, such as a dedicated machine learning optimized chip, or the like. The processor specifically may be configured, such as by software programming, for performing one or more evaluation operations. At least one or any component of a computer program configured to perform the authentication process may be executed by the processing device. Alternatively or in addition, the processor may be or may comprise 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 a computer program configured to perform the authentication process may be executed by the remote device.

[0067] The processor may be configured, such as by software programming, for performing one or more evaluation operations. At least one or any component of a computer program configured to perform the authentication process may be executed by the processing device. Alternatively or in addition, the processor may be or may comprise 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 a computer program configured to perform the authentication process may be executed by the remote device.

[0068] The method of the present disclosure comprises receiving image data. The term "receiving” may refer to reading the image information from a file, a database or from an interface to a camera.

[0069] The method of the present disclosure comprises outputting the dataset obtained from the model. The term "outputting” may relate to writing the augmented dataset on a non-transitory data storage medium, for example into a file or database, display it on a user interface, for example a screen, or both. It is also possible to output the augmented dataset through an interface to a cloud system for storage and / or further processing. The present disclosure further relates to a non-transient computer-readable medium including instructions that, when executed by one or more processors, cause the one or more processors to perform the method according to the present disclosure. The term "computer-readable data medium" may refer to any suitable data storage device or computer readable memory on which is stored one or more sets of instructions (for example software) embodying any one or more of the methodologies or functions described herein. The instructions may also reside, completely or at least partially, within the main memory and / or within the processor during execution thereof by the computer, main memory, and processing device, which may constitute computer-readable storage media. The instructions may further be transmitted or received over a network via a network interface device. Computer-readable data medium include hard drives, for example on a server, USB storage device, CD, DVD or Blue-ray discs. The computer program may comprise all functionalities and data required for execution of the method according to the present disclosure or it may provide interfaces to have parts of the method processed on remote systems, for example on a cloud system.

[0070] The disclosure further relates to a method for granting a user access to a device or application. A device can be a mobile device, for example smartphone, a tablet computer, a laptop computer or a smartwatch, or it can be a stationary device such as a payment terminal or an access control system, for example to control access to a building, a subway train station, an airport gate, a production facility, a car rental site, an amusement park, a cinema, or a supermarket for registered customers. The access control system may further be integrated into a vehicle, for example a car, a train, an airplane, or a ship. An application may refer to a local program, for example installed on a smartphone or a laptop, or a remote service, for example a service on a cloud system to be accessed via internet. The application may serve several purposes, for example to authorize a payment, identify the user for a transaction with the public administration, for example to renew a driver's license, or authorize the user for high-security communication.

[0071] Brief Description of the Figures

[0072] Figure 1 illustrates an example for a material authentication system.

[0073] Figure 2 illustrates an example for a material model and its training data.

[0074] Figure 3 illustrates an example for the labelling of the training data.

[0075] Figure 4 illustrates an example for preprocessing image data.

[0076] Figure 5 illustrates an example for a biometric authentication system. Description of Embodiments

[0077] Figure 1 illustrates an example for a material authentication system. The material authentication system 100 may be integrated into a portable device, for example a smartphone, a tablet computer, a laptop computer or a smartwatch. It may comprise a projector 101 which projects light 111 onto a user 110. The light may be infrared light, for example with a wavelength of 940 nm, which is invisible to the user 110. The projected light 111 may be floodlight or patterned light, for example a hexagonal point pattern. The projected light 111 may impinge on the face of the user 110, but it may also impinge on the whole head including hair, the upper part of the body including head neck and shoulders or even the complete body. Alternatively, the light may impinge on any object, for example a leather sample. The reflected light 112 may be recorded by a camera 102 which thereby captures an image of the user 110 illuminated by the projected light. The camera 102 may generate an image in the optical range matching the wavelength emitted by projector 101, for example in the infrared range. The image may be a grayscale image, i.e. each pixel comprises only the total intensity information, or an RGB image, i.e. different pixels indicate the intensity in a particular wavelength. The image may be passed to processor 103. The processor 103 may be a microcontroller, i.e. comprising memory and IO controller functionalities, or it may be a CPU which is connected to memory and IO controllers. The processor 103 may execute program code which determines if the user 110 is an authorized user 110. Such determination may involve vectorizing the image into features. Such feature vector may be compared to a stored template. If the difference between the feature vector and the stored template is below a predefined threshold, the processor may determine that the user 110 in the vehicle is authorized. The processor 103 may further determine if the image really shows a human rather than a spoofing mask. This may be accomplished by classifying the material of the face in the image by evaluating reflection characteristics in the reflected light. If no skin is detected, the processor may determine that the user 110 in front of the transparent display is not authorized. The processor 103 may be communicatively coupled to memory 104. The memory 104 may be transient memory, for example random access memory (RAM), or persistent memory, for example flash memory. The memory 104 may comprise program code configured to determines if the user 110 is an authorized person as well as templates for registered authorized users.

[0078] The processor 103 may generate a signal 105 indicating that the user 110 is authorized. The signal 105 may be forwarded to an access control for unlocking the device, granting access to an application, or effecting a secure payment, for example via a wireless communication interface. Alternatively, the signal may be forwarded to a program, for example a payment app, or to a user interface, for example on the display 106, where the result is shown.

[0079] The material authentication system 100 may comprise a display 106. The display 106 may be transparent for the projected light 111 and the reflected light 112, such that the projector 101 and the camera 102 may be placed behind the display 106. The display 106 may only be transparent at the positions at which the projected light 111 and the reflected light 112 passes the display 106. Transparent may mean that at least 30 % or at least 50 % of the incident light passes through the transparent display 106. Figure 2 illustrates an example for a material model and its training data. Image data 201 may be obtained from a camera recording images of an object under illumination with patterned light, for example with patterned infrared light. The images may be cropped into multiple partial images, for example comprising a pattern feature and parts of its nearest neighbors. The partial images may be input to an encoder 211 . The encoder 211 may comprise a convolutional neural network. The encoder 211 may output a feature vector 212, for example one feature vector 212 for each partial image. A random generator 221 may generate feature vector 222. The random generator 221 may comprise a random number generator using a Gaussian algorithm. The feature vector 222 may have the same format as the feature vector 212, such as the same dimensionality and the same data type for the entries, for example a float value. The feature vector 222 may comprise value which resemble those of feature vector 212. For example, the random generator 221 may generate for each element in feature vector 222 a number using a Gaussian algorithm using the mean and the variance of the corresponding element of feature vectors 212.

[0080] Feature vectors 212 and 222 may be used as input to a material classifier 230. The material classifier 230 may be a fully connected artificial neural network. The material classifier 230 may output a material prediction 240, e.g. a predicted class label indicating whether the feature vector 212 or 222 corresponds to an expected material or not. The material prediction 240 may be a Boolean value or a float value, for example a value between 0.0 and 1 .0 corresponding to the probability if the object is of the expected material or not.

[0081] The training process may adjust the parameters of both encoder 211 and material classifier 230 or only the latter. In the former case, the training process may comprise two phases. In a first phase, the image data 201 comprising a class label indicating whether the corresponding object is of the expected material or not may be used as training dataset. A loss function, for example a cross-entropy loss or a triplet loss based on the material prediction 240 and the class labels, may be minimized by adjusting the parameters of the encoder 211 and the material classifier 230, for example by batch gradient descend. In a second phase, the material classifier 230 may be trained with feature vectors 212 and 222, wherein feature vectors 222 may be labelled non-expected material. A loss function, for example a cross-entropy loss or a triplet loss based on the material prediction 240 and the class labels, may be minimized by adjusting the parameters of the material classifier 230, for example by batch gradient descend. After the second phase, the material model comprising the encoder 211 and the material classifier 230 may be ready for use in a material authentication system. It may be output, for example to a memory of the material authentication system.

[0082] Figure 3 illustrates an example for the labelling of the training data. An image of an authentic object 301, i.e. an object made of the expected material, for example a real human face with skin, may be converted into feature vector 311 which may be labelled with expected material 312. An image of a spoofing object 302, i.e. an object made of a material other than the expected material, for example a spoofing mask out of silicone, may be converted into feature vector 313 which may be labelled with non-expected material 314. A random generator 303 may generate feature vectors 315, for example by adding Gaussian noise to feature vectors 311 and / or 313, may be labelled with non- expected material 316. Hence, training data 310 may comprise feature vector 311 labelled with expected material 312, feature vector 313 which may be labelled with non-expected material 314, and feature vector 315 which may be labelled with non-expected material 316. This training data may be used to train a material model, for example a material classifier which receives feature vectors derived from images and outputs a material class label.

[0083] Figure 4 illustrates an example for preprocessing image data. Pattern image 401 may be obtained from a camera which has recorded a face under illumination of hexagonally patterned infrared light. A segmentation algorithm may determine a region of interest 402, for example the face of a person. The pattern image 401 may be cropped around the region of interest 402. The region of interest 402 may be cropped into multiple partial images, for example pattern patches 403. A pattern patch 403 may comprise in its center one pattern feature and parts of its nearest neighbors. The pattern patches 403 may be used as image data for training the material model.

[0084] Figure 5 illustrates an example for a biometric authentication. The biometric authentication system may be a face authentication system which verifies if a face in front of a camera is really the claimed person, so neither a different person nor a spoofing mask. The biometric authentication system may be integrated into a portable device such as a smartphone, or in an access system, for example a door opening system of a building or a vehicle.

[0085] The face of the person may be illuminated with patterned illumination 501. A camera may record a pattern image 502 of the face under patterned illumination. The pattern image 502 may be used to classify the material 503 of the face, for example with a material model which has been trained with training data according to the present disclosure. The material classification may yield a predicted class label skin or non-skin. If non-skin is predicted, the authentication may be rejected 530. The face may be illuminated with flood light 511, for example shortly before or after illuminating the face with patterned light 501. A camera may record a flood image 512 of the face under flood illumination 511. The flood image 512 may be used to recognize the identity of the person, for example by extracting features of the flood image and compare them with a reference database. If recognition yields an incorrect person, for example a person without access rights, the authentication may rejected 530. If both the correct person is identified and the material classification yields skin, the person may be authenticated 520.

[0086] The present disclosure has been described in conjunction with preferred embodiments and examples as well. However, other variations can be understood and effected by those persons skilled in the art and practicing the claimed disclosure, from the studies of the drawings, this disclosure and the claims.

[0087] Any steps presented herein can be performed in any order. The methods disclosed herein are not limited to a specific order of these steps. It is also not required that the different steps are per-formed at a certain place or in a certain computing node of a distributed system, i.e. each of the steps may be performed at different computing nodes using different equipment / data processing. As used herein ..determining" also includes ..initiating or causing to determine", "generating" also includes ..initiating and / or causing to generate" and "providing” also includes "initiating or causing to determine, generate, select, send and / or receive”. "Initiating or causing to perform an action” includes any processing signal that triggers a computing node or device to perform the respective action.

[0088] In the claims as well as in the description the word "comprising” does not exclude other elements or steps and the indefinite article "a” or "an” does not exclude a plurality. A single element or other unit may fulfill the functions of several entities or items recited in the claims. The mere fact that certain measures are recited in the mutual different dependent claims does not indicate that a combination of these measures cannot be used in an advantageous implementation. In the claims as well as in the description the word "comprising” or "including” or similar wording does not exclude other elements or steps and shall not be construed limiting to the elements or steps lined out. The indefinite article "a” or "an” does not exclude a plurality. A single element or other unit may fulfill the functions of several entities or items recited in the claims. The mere fact that certain measures are recited in the mutual different dependent claims does not indicate that a combination of these measures cannot be used in an advantageous implementation or further elements may be included.

[0089] Providing in the scope of this disclosure may include any interface configured to provide data. This may include an application programming interface, a human-machine interface such as a display and / or a software module interface. Providing may include communication of data or sub-mission of data to the interface, in particular display to a user or use of the data by the receiving node, entity or interface.

[0090] Various units, circuits, entities, nodes or other computing components may be described as "con-figured to” perform a task or tasks. Configured to shall recite structure meaning "having circuitry that” performs the task or tasks on operation. The units, circuits, entities, nodes or other computing components can be configured to perform the task even when the unit / circuit / component is not operating. The units, circuits, entities, nodes or other computing components that form the structure corresponding to "configured to” may include hardware circuits and / or memory storing program instructions executable to implement the operation. The units, circuits, entities, nodes or other computing components may be described as performing a task or tasks, for convenience in the description. Such descriptions shall be interpreted as including the phrase "configured to.” Any recitation of "configured to” is expressly intended not to invoke 35 U.S.C. § 112(f) interpretation.

[0091] In general, the methods, apparatuses, systems, computer elements, nodes or other computing components described herein may include memory, software components and hardware components. The memory can include volatile memory such as static or dynamic random-access memory and / or nonvolatile memory such as optical or magnetic disk storage, flash memory, programmable read-only memories, etc. The hardware components may include any combination of combinatorial logic circuitry, clocked storage devices such as flops, registers, latches, etc., finite state machines, memory such as static random-access memory or embedded dynamic random-access memory, custom designed circuitry, programmable logic arrays, etc.

[0092] Any disclosure and embodiments described herein relate to the methods, the systems, apparatuses, devices, chemi- cals, materials, computer program elements lined out above and vice versa. Advantageously, the benefits provided by any of the embodiments and examples equally apply to all other embodiments and examples and vice versa. All terms and definitions used herein are understood broadly and have their general meaning.

Claims

Claims1 . A material authentication system for authenticating an object comprising: a. a camera configured to capture image data of the object under illumination, b. a processor configured to determine whether the object is made of an expected material by using the image data as input to a material model and authenticate the object based on the material determination, wherein the material model comprises an encoder which uses the image data as input and outputs a feature vector representing features in the image data and a material classifier which uses a feature vector as input and outputs a predicted class label, wherein the material model is trained with training data comprising image data captured from objects of the expected material, labelled with the expected material, image data captured from objects of a material other than the expected material, labelled with other material, and random image data labelled with other material, wherein the random image data comprises feature vectors comprising random values for training the material classifier.

2. The material authentication system according to claim 1 , wherein the feature vectors of the random image data have the same or a similar distribution of values as the feature vectors obtained from real images.

3. The material authentication system according to claim 1 or 2, wherein the material authentication system is a face authentication system, wherein the object is a human face, and the expected material is skin.

4. The material authentication system according to any of the claims 1 to 3, wherein the material authentication system further comprises a projector configured to illuminate the object with an infrared light pattern.

5. The material authentication system according to any of the claims 1 to 4, wherein the material authentication system further comprises a projector configured to illuminate the object with flood light, and wherein the processor is configured to identifying the object using the flood image.

6. The material authentication system according to any of the claims 1 to 5, wherein the material authentication is integrated into a mobile computing device.

7. A computer-implemented method for generating training data for training a material authentication system comprising: a. receiving a set of image data with a label indicating whether the image data is associate with an expected material or not, b. generating training data for training a material authentication system comprising a material model comprising an encoder which uses the image data as input and outputs a feature vector representingfeatures in the image data and a material classifier which uses a feature vector as input and outputs a predicted class label, wherein generating training data uses the received image data and random image data with a label indicating that the image data is not associated with the expected material and wherein the random image data comprises feature vectors comprising random values for training the material classifier, and c. outputting the training data.

8. The method according to claim 7, wherein the feature vectors of the random image data are obtained by generating feature vectors from the received image data and adding random values.

9. The method according to claim 8, wherein the number of feature vectors of the random image data is 0.5 to 2 times the number of feature vectors of the image data.

10. The method according to any of the claims 7 to 9, wherein the image data comprises an image of the object under illumination with an infrared light pattern and wherein a region of interest is determined in the image, and wherein multiple partial images are generated within the region of interest by cropping the image.

11. The method according to any of the claims 7 to 10, wherein the training data is suitable for training a biometric authentication system and wherein the expected material is skin.

12. The method according to any of the claims 7 to 11, wherein the image data augmented by adding further image data labelled with the expected material, wherein the further image data is generated by variations of the image data labelled with the expected material.

13. Use of the training data obtained by the method according to any of the claims 7 to 12 for training a material authentication system.

14. A system for generating training data for training a material authentication system comprising: a. an input for receiving a set of image data with a binary label indicating whether the image data is associate with an expected material or not, b. a processor for generating training data for training a material authentication system comprising a material model comprises an encoder which uses the image data as input and outputs a feature vector representing features in the image data and a material classifier which uses a feature vector as input and outputs a predicted class label, wherein generating training data uses the received image data and random image data with a label indicating that the image data is not associated with the expected material, andc. outputting the training data.

15. A non-transient computer-readable medium including instructions that, when executed by one or more processors, cause the one or more processors to perform a method comprising: a. receiving image data with a label indicating whether the image data is associate with an expected material or not, b. generating training data for training a material authentication system comprising a material model comprises an encoder which uses the image data as input and outputs a feature vector representing features in the image data and a material classifier which uses a feature vector as input and outputs a predicted class label, wherein generating training data uses the received image data and random image data with a label indicating that the image data is not associated with the expected material, and c. outputting the training data.

Images