Method and system for detecting vital signs

Abstract

The present invention relates to a method for detecting a vital sign, the method comprising the steps of: a) generating or receiving an image dataset representative of at least one reflected image of a speckle pattern produced by coherent electromagnetic radiation reflected from an object; b) determining a speckle contrast of the speckle pattern; c) determining a vital sign measurement value based on the determined speckle contrast; and d) providing a vital sign measurement value.

Description

[Technical field]

[0001] The present invention relates to a method, system and computer program for detecting vital signs indicative of the presence of a living body, and in particular to detecting whether a living body is presented to a camera as part of an authentication process. [Background technology]

[0002] In order to gain access to an electronic device, a user must typically verify that he or she is in fact authorized to access the device. Verification can typically be accomplished by entering a correct password or passcode into the device as part of an authentication process. Alternatively, biometric authentication processes can be used, including fingerprint authentication, which employs a fingerprint sensor, or facial recognition, which matches a human face from a recorded digital image against one or more reference images.

[0003] With regard to facial recognition, situations may arise where closely related faces of different persons, e.g. siblings or twins, become indistinguishable, which may allow unauthorized persons to gain access to electronic devices.

[0004] To avoid such situations, it has been proposed to use additional authentication processes and to grant access to the electronic device only after passing all these authentication processes.

[0005] For example, US10,719,692 B2 proposes to enhance the security of the facial recognition authentication process by using a subepidermal image of the user to evaluate subepidermal features, such as blood vessels, when the device attempts to authenticate the user. The subepidermal features must be compared to templates of subepidermal features of authorized users of the device. The proposed process requires that the user's face be captured with sufficient resolution to allow imaging of the subepidermal features of the user's face.

[0006] US 9,971,948 B1 proposes to apply imaging of the vascular pattern under the skin of the human body, which involves irradiating the skin with a series of very short pulses of infrared light. The pulses are modulated by the blood of the subcutaneous vessels and the surrounding tissue. Based on the modulation of the pulses, an image of the blood vessels located under the body surface is generated and used for the authentication process. It is expected that the skin will generally need to be irradiated for at least one heartbeat to obtain meaningful results. Summary of the Invention [Problem to be solved by the invention]

[0007] The invention is based on the object of providing a method, a system and a computer program that allows the detection of a living body presented to a camera. In particular, a method, a system and a computer program are provided that allow the detection of whether an object presented to a camera is in fact a living body. Preferably, the detection can be achieved relatively quickly. It is further preferred that no expensive hardware is required for the detection. [Means for solving the problem]

[0008] According to the present invention, a method for detecting vital signs is proposed, the method comprising the following steps: - generating or receiving an image dataset representative of at least one reflected image of a speckle pattern produced by coherent electromagnetic radiation reflected from an object; - determining a speckle contrast of the speckle pattern; - determining a vital sign measure based on the determined speckle contrast; - providing vital sign measurements; Includes.

[0009] The present invention is based on the recognition that moving fluids or moving particles in the body of a living body, such as blood cells, especially red blood cells, interstitial fluid, transcellular fluid, lymphatic fluid, ions, proteins and nutrients, can cause motion blur in the reflected light, while the rest of the body is stationary and therefore does not cause motion blur. Thus, when coherent electromagnetic radiation is reflected by moving scattering particles such as red blood cells, the speckle pattern fluctuates and the speckles become blurred (blurred). As a result of this blurring, the speckle contrast is reduced. Thus, the speckle pattern and the speckle contrast obtained from the speckle pattern contain information about whether the illuminated object is a living body or not. Speckle contrast values ​​are generally distributed between 0 and 1. When illuminating an object, a value of 1 may represent no motion, and a value of 0 may represent the fastest motion of the particles and thus the motion that causes the most pronounced blurring of the speckles. Since the vital sign measurements are determined based on the speckle contrast, the lower the speckle contrast value, the more certain the corresponding vital sign measurements indicate the presence of a living body. Conversely, the higher the speckle contrast value, the greater the certainty that the corresponding vital signs measurement indicates the presence of a non-living object.

[0010] The method according to the invention thereby makes it possible to detect vital signs in a reliable and efficient manner and therefore makes it possible to detect whether an object presented to the camera is a living being.

[0011] In particular, a single reflected image is sufficient to obtain sufficient information to reliably detect vital signs. A single illumination of an object with coherent electromagnetic radiation is sufficient to record a single reflected image. In this manner, vital sign measurements can be obtained relatively quickly.

[0012] Based on the vital sign measurements, it can be reliably determined whether a living body has been presented to the camera, and this method is particularly advantageous in that it is robust against spoofing, for example by presenting to the camera a mask replicating the face of an authorized user.

[0013] It is a further advantage of the method according to the invention that the reflected image represented by the image dataset can be recorded by using standard equipment, e.g. a standard laser and a standard camera comprising, e.g., a charge-coupled device (CCD) and / or a complementary metal-oxide semiconductor (CMOS) sensor element.

[0014] In the framework of this specification, a vital sign indicates the presence of a living body. In other words, a vital sign is any sign suitable for distinguishing a living body from a non-living material. An object for which a vital sign can be detected is therefore considered a living body. In this specification, a vital sign particularly relates to the presence of moving fluids or moving particles in the body of a living body. In this respect, blood flow, e.g. the presence of red blood cells, is a preferred vital sign. However, other moving fluids or moving particles present in the body of a living body, such as interstitial fluid, transcellular fluid, lymphatic fluid, ions, proteins and nutrients, can also be used as vital signs. Preferably, the vital sign is detectable by analyzing the speckle pattern, for example by detecting a blur of the speckles caused by moving fluids or moving particles in the body of the living body. This blur can reduce the speckle contrast compared to the absence of moving fluids or moving particles.

[0015] Coherent electromagnetic radiation refers to electromagnetic radiation that can exhibit interference effects. It may include partial coherence, i.e. not perfect correlation between phase values. Preferably, the electromagnetic radiation has a wavelength in the wavelength range of 800 nm to 1000 nm, preferably in the wavelength range of 850 nm to 950 nm, more preferably in the wavelength range of 930 nm to 950 nm, in particular in the wavelength range of 935 nm to 945 nm. Therefore, electromagnetic radiation in the infrared wavelength range is preferably used, which has the advantage that the electromagnetic radiation can be visually unperceivable by the user. This is particularly advantageous in the authentication process. On the one hand, the user may not be aware of the way in which the authentication is performed. On the other hand, the user is relatively less distracted during the authentication process.

[0016] A speckle pattern is an interference pattern produced by coherent electromagnetic radiation reflected from an object (e.g., reflected from the object's exterior surface or reflected from the object's interior surface). Speckle patterns typically arise from diffuse reflection of coherent electromagnetic radiation, such as laser light. Within a speckle pattern, the spatial intensity of the coherent electromagnetic radiation varies randomly due to the interference of coherent wavefronts.

[0017] The speckle contrast can represent the value of the average contrast of the intensity distribution within the area of ​​the speckle pattern. In particular, the speckle contrast K over the area of ​​the speckle pattern is expressed as the average speckle intensity The ratio of the standard deviation σ to

number

[0018] Speckle contrast values ​​typically range between 0 and 1.

[0019] The vital sign measurement preferably represents a measurement indicative of whether an object from which coherent electromagnetic radiation is reflected exhibits a vital sign. The vital sign measurement is determined based on the speckle contrast. Thus, the vital sign measurement may depend on the determined speckle contrast. When the speckle contrast changes, the vital sign measurement derived from the speckle contrast may change accordingly. The vital sign measurement may be a single number or value that may represent the likelihood that the object is a living organism.

[0020] Preferably, the complete speckle pattern of the reflected image is used to determine the speckle contrast. Alternatively, a section of the complete speckle pattern may be used to determine the speckle contrast. The section of the complete speckle pattern preferably represents an area smaller than the area of ​​the complete speckle pattern. The section of the speckle pattern may be obtained by cropping the reflected image.

[0021] Preferably, the method includes a step of authenticating the object, e.g. the user, based on the determined vital sign measurements. Authenticating the object based on the determined vital sign measurements has the advantage that it can be verified that a real living being is presented to the camera and not a mask or the like used to gain unauthorized access. Preferably, authenticating the object includes matching at least one biometric feature obtained from the object to be accessed with at least one reference or template biometric feature associated with the authenticated object. If the at least one biometric feature obtained from the object matches the at least one reference or template biometric feature associated with the recognized object, access may be authorized. The biometric feature may be, for example, a facial feature such as the relative position or size of the eyes, mouth, nose, a fingerprint, a hand shape, a palm print, an iris, etc. For example, in an authentication process, in a first step, a biometric authentication may be performed, and if the first authentication step is successfully passed, a second authentication step (including a determination of a vital sign measurement to verify that a real living being is presented to the camera and not a spoofing mask or the like) may be performed.

[0022] In the method, it is possible that the image data set represents at least two reflection images of a speckle pattern generated by coherent electromagnetic radiation reflected from the object. Preferably, for each of the at least two reflection images, an individual vital sign measurement value can be determined based on a speckle pattern of each of the at least two reflection images. As a result, from a plurality of reflection images each representing a speckle pattern, a number of vital sign measurements can be determined respectively. The determined individual vital sign measurements can then be provided, for example, to a user or provided for further processing by the same or a different device, for example for performing an authentication process.

[0023] The method can include a map of multiple vital sign measurements being generated. The vital sign measurement map can be generated from a speckle contrast map. The speckle contrast map can include multiple speckle contrast values, each associated with a location, e.g., a location on the object at which a corresponding reflectance image was recorded. The speckle contrast map can be represented using a matrix having the speckle contrast values ​​as matrix entries.

[0024] The vital sign measurement map can be represented by a matrix that includes the individual vital sign measurements as matrix entries. The map of vital sign measurements can represent a spatial distribution of the determined vital sign measurements. Each of the vital sign measurements can be associated with a different position on the object illuminated with coherent electromagnetic radiation to record a corresponding speckle pattern. It can therefore be beneficial if the vital sign measurements are associated with a position on the object. To generate the map of vital sign measurements, the positions associated with each vital sign measurement can be taken into account. The map can therefore represent, for example, a spatial distribution of the vital sign measurements in the coordinate system of the illuminated object. For example, the positions associated with the vital sign measurements can be represented by spatial coordinates in the coordinate system of the illuminated object.

[0025] Therefore, as part of the method, at least two vital sign measurements, each associated with a different spatial location on the object, may preferably be determined and provided as a map of vital sign measurements.

[0026] In this method, at least one reflected image may be divided into a number of partially reflected images, and an individual vital sign measurement may be determined for each of the partially reflected images. When determining the individual vital sign measurements for the number of partially reflected images, statistics may be performed on the individual vital sign measurements, e.g., averaging or weighting. For example, a composite vital sign measurement may be provided based on the individual vital sign measurements associated with the number of partially reflected images. The composite vital sign measurement may be generated by, for example, assigning a greater weight to the individual vital sign measurements associated with partially reflected images located in a central area of ​​the reflected image, and assigning a smaller weight to the individual vital sign measurements associated with partially reflected images located, for example, closer to a border of the reflected image. Such a composite vital sign measurement may have improved confidence as to whether a living being was actually presented to the camera.

[0027] Alternatively, the method can divide at least one reflected image into multiple partial reflectance images and determine the individual vital sign measurements for only a portion of the multiple partial reflectance images. For example, considering only some of the partial reflectance images can include considering a reduced number of partial reflectance images that is at least one less than the total number of partial reflectance images. Only partial reflectance images associated with a particular area of ​​each reflected image can be considered to determine the individual vital sign measurements. For example, the reflected images can be divided into quadrants or segments, and only those partial reflectance images within a particular quadrant or area, such as the top right quadrant or the central area, can be considered to determine the individual vital sign measurements.

[0028] In this case, by dividing at least one reflected image into multiple partial reflected images, it is possible to determine each individual vital sign measurement only for those partial reflected images that are within a particular quadrant or area of ​​the reflected image. When multiple reflected images are used, the quadrant or area may be the same for all reflected images. However, the respective quadrants or areas of the respective reflected images may overlap or only partially overlap.

[0029] Considering only a portion of the partial reflectance image, i.e. only a few partial reflectance images, for determining the individual vital sign measurements may have the advantage that more relevant or meaningful parts of the reflectance image can be selected or extracted for determining the individual vital sign measurements, so that the resulting individual vital sign measurements are more reliable. A number of individual vital sign measurements can be combined, for example by averaging or weighting, into a composite vital sign measurement. A composite vital sign measurement resulting from selected individual vital sign measurements may be more reliable compared to a single vital sign measurement determined for the entire reflectance image from which the partial reflectance images were derived.

[0030] It is also possible to split the reflected image into multiple partially reflected images to provide a map of vital sign measurements. Preferably, for each of the partially reflected images, or at least a substantial portion of the partially reflected images, an associated speckle contrast is determined and used to determine an individual vital sign measurement for each partially reflected image. It is further preferred that each of the partially reflected images at least partially overlaps with another of the multiple partially reflected images. In particular, when the partially reflected images at least partially overlap, the series of partially reflected images may resemble a sliding view of small sections of the total reflected image.

[0031] Alternatively, the map can be obtained from a set of reflected images received from a camera used to record a number of reflected images, for example by scanning the object. The set of reflected images can be represented by an image dataset. Preferably, each reflected image of the set of reflected images is associated with an individual scanning location, for example a location on the object or a location of the camera when the respective image was recorded. The locations associated with the reflected images of the reflected image set can be defined in the coordinate system of the object or in the coordinate system of the camera.

[0032] In some variations of the method, the image dataset represents at least two reflected images of a speckle pattern produced by coherent electromagnetic radiation reflected from an object at different spatial locations on said object. Preferably, for each of the at least two reflected images, a vital sign measurement associated with the respective spatial location is determined. The vital sign measurements associated with the respective spatial locations may be provided as a map of vital sign measurements.

[0033] If the image data set represents at least two reflection images, it may be preferred if motion correction is performed on one of the at least two reflection images, in particular if the object moves during the recording of the at least two reflection images.

[0034] If at least two reflectance images are used to generate, for example, a map of vital sign measurements, it may be beneficial for each, or at least a portion, of the at least two reflectance images to be split into a number of partial reflectance images, as described above. Preferably, for each, or at least a majority of, the partial reflectance images, an individual vital sign measurement may be determined. The number of individual vital sign measurements associated with each partial reflectance image may be provided as a map of vital sign measurements. This allows for an increased resolution of the map of vital sign measurements without the need to record a large number of additional reflectance images.

[0035] Preferably, the vital sign measurements are determined using an algorithm that may implement a mechanistic model or a data-driven model. The data-driven model may be a classification model, such as a neural network trained to determine the vital sign measurements, a visual transformer configured to determine the vital sign measurements, etc. The mechanistic model preferably reflects a physical phenomenon in a mathematical form, including, for example, a first-principles model. The mechanistic model may include a set of differential equations that describe the interaction between an object and coherent electromagnetic radiation, thereby resulting in a particular speckle contrast. In particular, the fluid flow and / or the shape of the object may be represented by the mechanistic model. Based on the necessary inputs to the mechanistic model that result in a speckle contrast determined from the speckle pattern of at least one reflected image, the associated vital sign measurements can be determined using the mechanistic model.

[0036] The vital sign measurement thus determined may indicate the likelihood that the object is a living organism. As mentioned above, possible speckle contrast values ​​are generally distributed between 0 and 1, with 0 representing maximum blur and thus the greatest likelihood that a living organism is present, and 1 representing minimum or no blur and thus the greatest likelihood that a living organism is not present. Thus, the determined vital sign measurement may indicate the likelihood that a living organism is presented to the camera based on the obtained speckle contrast value, for example obtained using a mechanism model. For example, the vital sign measurement may indicate a 100% likelihood that a living organism is present when the determined speckle contrast is 0. However, the vital sign measurement may indicate a 0% likelihood that a living organism is present when the determined speckle contrast is 1. A speckle contrast of 0.5 may lead to a 50% likelihood that a living organism is present. Of course, it is also possible that the speckle contrast does not have to be converted one-to-one into the corresponding percentage represented by the vital sign measurement. For example, a speckle contrast value of say 0.6 can lead to a vital signs measurement indicating that there is at least a 75% probability that the object presented to the camera is a living organism.

[0037] Preferably, the data-driven model is a trained neural network configured to predict a vital sign measurement of at least one reflectance image based on the determined speckle contrast. Historical data representing the determined speckle contrast values ​​from a plurality of reflectance images can be used to train the neural network. Preferably, the neural network is trained to use the determined speckle contrast or speckle contrast map as input and output a vital sign measurement or vital sign measurement map.

[0038] The trained neural network may be, but is not limited to, a multi-scale neural network, or a recurrent neural network (RNN), such as a gated recurrent unit (GRU) recurrent neural network or a long short-term memory (LSTM) recurrent neural network. Alternatively, the neural network may be a convolutional neural network (CNN).

[0039] The neural network can be trained using training data including, for example, speckle contrast values ​​and associated vital sign measurements. For example, if the neural network is a feed-forward neural network such as a CNN, a backpropagation algorithm can be applied to train the neural network. In the case of an RNN, a gradient descent algorithm or a backpropagation through-time algorithm can be employed for training purposes. As a result of the training, operating parameters for the neural network circuitry are generated such that the trained neural network receives the speckle contrast as input and outputs the associated vital sign measurements as predictions.

[0040] In some variants of the method, the image data set represents at least two reflection images of a speckle pattern generated by coherent electromagnetic radiation reflected from the object at the same or at least similar spatial positions within the object. The reflection images recorded at similar spatial positions preferably represent a significant spatial overlap. Preferably, for each of the images, a vital sign measurement value is determined and provided based on the speckle contrast of the respective reflection image. This allows a series of reflection images representing the evolution of the speckle pattern as a function of time to be generated. From each of the speckle patterns, the speckle contrast and the associated vital sign measurement value can be determined. It may therefore also be possible to provide, for example, the evolution of the vital sign measurement value as a function of time. Considering the blurring of the speckle pattern induced by blood flow, the variations in the blood volume in the irradiated volume, caused for example by cardiac activity, can be obtained by recording and processing a series of reflection images representing speckle patterns of the same spatial positions on the object.

[0041] Vital sign measurements can be used to detect the presence of a living body, such as a human or animal. For example, the method of detecting vital signs can be used as part of an authentication process implemented on a device to provide access control to a user attempting to access the device. The device can be, for example, a mobile phone, a tablet computer, or a smart watch.

[0042] Preferably, the method further comprises, preferably as part of the authentication process, predicting the presence of a living body based on the provided vital sign measurements.

[0043] Preferably, the step of predicting the presence of a living organism based on the provided vital sign measurements comprises the sub-steps of: - determining a confidence score based on the determined vital sign measurements; - comparing the confidence score with a predefined confidence threshold; - predicting the presence of a living organism based on the comparison; Includes at least one of the following.

[0044] The confidence score can be generated from the vital sign measurements, e.g., represented as a single number or value, or from a vital sign map, e.g., represented as a matrix of vital sign measurements. The confidence score can represent a confidence in indicating the presence of a living organism. The confidence score can be represented as a single number or value.

[0045] Preferably, the confidence score is determined by comparing the determined vital sign measurement to a reference, for example one or more reference vital sign measurements, each of which is preferably associated with a particular confidence score.

[0046] Alternatively, the confidence score may be determined using a neural network trained to receive the determined vital sign measurements as input and provide the confidence score as output. The neural network can be trained using historical data representing past vital sign measurements and associated confidence scores.

[0047] The confidence threshold is pre-determined to ensure a certain degree of confidence that the object is indeed a living organism. The confidence threshold may be pre-determined depending on the particular application, e.g., the security level required for providing access to the device. For example, the confidence threshold can be set such that the confidence score represents a relatively high level of confidence that the object presented to the camera is a living organism, e.g., 90% or more, e.g., 99% or more. The presence of a living organism is acknowledged only if the comparison with the confidence threshold results in the confidence score being sufficiently high, i.e., exceeding the confidence threshold. If the confidence score falls below the confidence threshold, access to the device is denied. Denial of access may trigger a new measurement, e.g., a repetition of the method of detecting vital signs and utilizing the vital signs measurements to predict the presence of a living organism as described above. Optionally, there may also be alternative authentication processes.

[0048] This allows for verification that the claimant attempting to access the device is in fact a biometric and not a spoofed attachment, and further allows for verification that the claimant is authorized for that particular request. Therefore, it is particularly preferred that the method includes the step of authenticating the object, e.g. the user, based on the determined confidence score.

[0049] In the method, it is also possible to determine a composite confidence score by combining at least two determined individual confidence scores. For example, in the method, a composite confidence score can be determined from at least two reflection images based on at least two confidence scores respectively determined for the at least two reflection images. Obtaining a composite confidence score can be achieved, for example, by averaging or weighting the at least two confidence scores determined for the at least two reflection images. When determining a composite confidence score, it is possible to achieve a higher confidence that the object is in fact truly a living body. This is particularly useful as part of an authentication process.

[0050] The above-described methods for determining vital signs of an object and for predicting the presence of a living body using the determined vital signs may in particular be part of an authentication process that further includes biometric authentication, e.g. facial recognition and / or fingering sensing.

[0051] The authentication process involves the following steps: - performing a biometric recognition of the user, for example on the user's face presented to a camera or by determining the user's fingerprint with a fingerprint sensor, preferably by performing the following sub-steps: - providing a detector signal from a camera, said detector signal representing an image of a user feature, e.g. a fingerprint feature or a facial feature; - A sub-step that generates a low-level representation of the image; - verifying user authorization based on the low-level representation of the image and the stored low-level representation template, sub-step; - if the biometric recognition is successful, determining the vital signs of the user, preferably by carrying out the steps of the method for determining the vital signs of an object as described above; - predicting the presence of a living body based on the determined vital signs, preferably comprising: - determining a confidence score based on the determined vital sign measurements; - comparing the confidence score to a predefined confidence threshold; - predicting the presence of a living organism based on the comparison; and and predicting by; - providing a positive authentication output signal if the presence of a biometric entity is confirmed; may include.

[0052] Upon receiving a positive authentication output signal, the user may be permitted to access the device. Otherwise, if no biometrics have been detected, a negative authentication output signal may be provided. In other words, an authentication output signal may be provided that generally indicates whether or not a biometric has been presented to the camera. If biometric authentication has already resulted in a negative outcome, a negative authentication output signal may be provided without determining the object's vital signs.

[0053] In an alternative authentication process, the object's vital signs are first determined and then, if the presence of a living body is successfully confirmed, biometric authentication, for example facial recognition or fingerprint detection, is performed.

[0054] The invention also relates to a computer program for detecting vital signs of an object, which computer program comprises instructions for carrying out, when it is executed on a computer, the steps of the method for determining vital signs of an object as described above.

[0055] The invention also relates to a non-transitory computer-readable data medium having stored thereon a computer program comprising instructions for carrying out the steps of the method for determining the vital signs of an object as described above.

[0056] With regard to the present system, the above object is achieved by a system for detecting vital signs, the system comprising a generating or receiving unit, a processor, and a providing unit.

[0057] The generating or receiving unit is configured to generate or receive an image dataset representative of at least one reflected image of a speckle pattern generated by coherent electromagnetic radiation reflected from the object. The processor is configured to determine a speckle contrast of the speckle pattern and to determine a vital sign measure based on the determined speckle contrast. The providing unit is configured to provide the vital sign measure.

[0058] The system is preferably configured to perform the method for detecting vital signs of an object as described above. For example, the system may include a computer program for detecting vital signs of an object, which computer program, when executed on a computer, includes instructions for performing the steps of the method for determining vital signs of an object as described above. The system may comprise a non-transitory computer-readable data medium storing the computer program for determining vital signs of an object.

[0059] The generating or receiving unit may be implemented as an input configured to receive image data or to generate image data from a received image signal. The processor may be an image signal processor (ISP) and may include circuitry suitable for processing the reflected image, in particular the reflected image received from the generating or receiving unit.

[0060] To determine a vital sign measurement based on the determined speckle contrast, the processor may include a neural network module including a neural network configured to use the speckle contrast as an input and output an associated vital sign measurement.

[0061] The providing unit may be configured as an output to provide the vital sign measurement, for example in the form of vital sign measurement data.

[0062] It is to be understood that the above-mentioned aspects, in particular the method of claim 1, the system of claim 16 and the computer program of claim 14, have similar and / or identical preferred embodiments, in particular as defined in the dependent claims.

[0063] It is to be understood that a preferred embodiment of the invention may be any combination of the dependent claims or the above embodiments with the respective independent claim.

[0064] These and other aspects of the invention will be apparent from and with reference to the embodiments described hereinafter. [Brief description of the drawings]

[0065] [Figure 1] 1 is a flow chart illustrating a method for detecting vital signs. [Diagram 2] 1 is a flow chart illustrating the use of vital signs measurements to predict the presence of a living organism, particularly as part of an authentication process. [Diagram 3] FIG. 1 is a schematic diagram of a system for detecting vital signs. [Figure 4] FIG. 1 illustrates a vital sign measurement map of vital signs in the human hand region. [Diagram 5] 1 is a flow chart illustrating an authentication process including determining vital signs. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0066] Detailed Description of the Embodiments FIG. 1 shows a flow chart representing a method for detecting vital signs. In this method, a reflected image represented by an image dataset is received (step S1). The reflected image shows a speckle pattern. The speckle pattern is generated by illuminating an object with coherent electromagnetic radiation, i.e. green light, having a line width with a central wavelength between 500 nm and 560 nm. Green light is expected to provide a relatively high contrast to the speckle pattern due to its interaction with hemoglobin in blood. Alternatively, infrared light is preferably used. Infrared light has the advantage that it is invisible to humans and therefore less disturbing to the user. The coherent electromagnetic radiation is reflected from the object, whereby the speckle pattern is generated by random interference. The reflected light is captured by a camera to record the speckle pattern.

[0067] Alternatively, one or more reflection images represented by the image dataset may be received, for example at least two reflection images, each of which preferably represents a speckle pattern obtained by illuminating the object with coherent electromagnetic radiation and recording the diffuse reflection from the object surface with a camera. The at least two images may be recorded at the same or at least similar spatial positions on the object, or at different spatial positions on the object, i.e. with no or only slight overlap, for example by scanning the object.

[0068] A speckle contrast is determined from the reflected images (step S2). If at least two reflected images are received, preferably the speckle contrast is determined for each of the reflected images. The multiple speckle contrasts can be combined into a speckle contrast map, for example represented as a matrix.

[0069] The speckle contrast is determined by the standard deviation of the illumination divided by the mean intensity. The speckle contrast may range between 0 and 1, with the speckle contrast being 1 when there is no speckle blur, i.e., no motion is detected in the illuminated volume of the object, and 0 when the speckle blur is maximized due to the detection of motion of particles, e.g., red blood cells, in the illuminated volume of the object. Thus, the speckle pattern and the speckle contrast derived therefrom are sensitive to motion within the illuminated volume. This motion within the illuminated volume indicates that the object is a living organism, since living organisms, such as humans or animals, have a circulatory system to transport blood cells within the body. If no blood circulation is detected, the object is expected to be non-living.

[0070] The more the speckle blur, the smaller the speckle contrast, and therefore the decreased speckle contrast allows the vital signs of the object to be detected more reliably.

[0071] The speckle contrast can be determined from the total reflected image or from a section of the reflected image obtained, for example, by cropping the total reflected image.

[0072] Optionally, if the object moves during capture of the reflected image, motion compensation may be performed on the reflected image (step S3).

[0073] From the speckle contrast, a vital sign measurement value is determined (step S4). If a speckle contrast map is determined from a series of reflection images, a vital sign measurement value map can be generated. A vital sign measurement value map can also be generated from a single reflection image by dividing the reflection image into a number of partial reflection images and determining the speckle contrast for each of the partial images. Based on each of the speckle contrasts by implementing the speckle contrast map, a corresponding vital sign measurement value can be determined. The vital sign measurements thus determined can be combined into a vital sign measurement value map. Thereby, the vital sign measurements can be more accurately matched to a given location on the object. In other words, it is possible to find the contribution of a part of the object to the total vital sign measurement value. For example, a part of the object that shows a relatively high movement of fluid is expected to contribute more significantly to the total vital sign measurement value associated with the total volume illuminated by the coherent electromagnetic radiation.

[0074] The determined vital sign measurements or vital sign measurement map are then provided (step S5), for example to a user, or to another component of the same device, or to another device or system for further processing. For example, the vital sign measurements may be used to predict the presence of a living body, for example as part of an authentication process implemented in a device such as that described with reference to FIG. 2. In particular, the vital sign measurements are indicative of an object exhibiting a vital sign. The vital sign measurements can thus be used to assess whether an object presented to the camera is a living body.

[0075] FIG. 2 shows a flow chart illustrating the use of vital sign measurements to predict the presence of a living body, particularly as part of the authentication process.

[0076] First, a vital sign measurement or a vital sign measurement map is provided (step T1). The vital sign measurement (e.g. a single numerical value) or the vital sign measurement map (e.g. a matrix) may be determined and provided by performing a method for detecting vital signs as described with reference to FIG.

[0077] A confidence score is determined based on the vital sign measurements or vital sign measurement map (step T2). A trained neural network is used to generate the confidence score. The neural network is trained to receive the vital sign measurements or vital sign measurement map and output a confidence score based on the vital sign measurements or vital sign measurement map, respectively. For example, the neural network can be trained using training data representing pairs of vital sign measurements or vital sign measurement maps and corresponding confidence scores.

[0078] Alternatively, the confidence score can be generated by comparing the vital sign measurement or vital sign measurement map to a reference. A confidence score is generated according to the degree of matching between the vital sign measurement or vital sign measurement map and the reference. For example, a number of intervals are defined around the reference, and a confidence score is generated according to each interval within which the vital sign measurement or vital sign measurement map is located.

[0079] The confidence score indicates the confidence that the object presented to the camera is indeed a living body based on the vital sign measurements or vital sign measurement map. For example, the confidence score is generated if the vital sign measurements have a predetermined numerical value derived from the associated speckle contrast based on the vital sign measurements. If the vital sign measurements most certainly indicate that the object is a living body, the confidence score generated therefrom can indicate that the object is indeed a living body with, for example, 95% or more confidence.

[0080] The generated confidence score is later compared with a predefined confidence threshold (T3). The confidence threshold is predefined depending on the security level required for a particular application. If the security level is high, e.g., when making an online payment, the confidence threshold can be set to only accept confidence scores that indicate almost 100% certainty that the object presented to the camera is a living body, and the confidence threshold may be required to be exceeded. If access to a less sensitive application is requested, the confidence threshold may be predefined to require a relatively low confidence score to allow access to this particular application.

[0081] If the confidence score exceeds the confidence threshold, the authentication may be valid (step T4), otherwise the request is either rejected or a new measurement is triggered (step T5).

[0082] The method described with reference to Figure 2 can be combined with other elements such as facial recognition or fingerprint scanning to ensure that the claimant is truly biometric and not an imitation attach, and further to ensure that the claimant is in fact authorized for the particular request, thereby providing an additional level of security.

[0083] Fig. 3 shows a schematic diagram of a system 300 for detecting vital signs. The system 300 comprises a projector 302 configured to project coherent electromagnetic radiation along a transmission path 304 onto an object 306 (the object 306 is not part of the system 300). The projector 302 may be a laser. The object 306 may be a human body part such as a human face or a hand. The projector 302 may be selected from a group of projectors emitting coherent electromagnetic radiation at different wavelengths. Preferably, the projector 302 is configured to emit coherent electromagnetic radiation with a linewidth having a central wavelength between 500 nm and 560 nm, i.e. green light, or between 780 nm and 3000 nm, i.e. falling in the infrared (IR) spectrum, preferably between 780 nm and 1000 nm, i.e. falling in the near infrared spectral range. Green light usually provides the highest contrast due to its interaction with hemoglobin in blood. Infrared light has the advantage that it is invisible and therefore causes less disturbance to the user.

[0084] The object 306 reflects the coherent electromagnetic radiation along a return path 308, and the reflected electromagnetic radiation is captured by the camera 310. Reflecting the coherent electromagnetic radiation from the object 306 produces a speckle pattern whose spatial intensity varies randomly due to interference of coherent wavefronts. Thus, the camera 310 records a reflected image of the speckle pattern produced by the coherent electromagnetic radiation reflected from the object. The speckle pattern is sensitive to motion within the illuminated volume, such as red blood cells transported in the object's circulatory system. In particular, if particles are moving within the illuminated volume, the speckles will blur such that the speckle contrast obtained from the speckle pattern is reduced. The degree of blurring of the speckle pattern is an indication of the presence of a living organism having a circulatory system.

[0085] In particular, the exterior surface of the object 306 typically exhibits specular reflection, while the interior of the sample exhibits diffuse reflection. Typically, specular reflection dominates. Because speckle patterns typically arise from diffuse reflection of coherent electromagnetic radiation, it may be advantageous to use a polarizing filter to remove most of the specular reflection.

[0086] The camera 310 records the reflected image and passes it to the processor 312 in the form of an image data set or image signal. To record the reflected image, the camera 310 preferably includes one or more lenses and one or more image sensors. The image sensor may be, for example, an array of sensors. The sensors of the sensor array may include, but are not limited to, charge-coupled device (CCD) or complementary metal-oxide semiconductor (CMOS) sensor elements to capture the reflected coherent electromagnetic radiation.

[0087] The processor 312 is preferably configured to perform the method steps described with reference to Fig. 1. In particular, the processor 312 may comprise a generating or receiving unit configured to generate or receive an image dataset representative of a reflected image of a speckle pattern generated by coherent electromagnetic radiation reflected from the object 306. For example, the generating or receiving unit may be configured as an input of the processor 312 for receiving image data representative of the reflected image captured from the camera 310. Alternatively, the input may be configured to receive an image signal from the camera 310. Based on the image signal, an image dataset can be generated for further processing by the processor 312. Preferably, the processor 312 comprises logic circuitry for processing the image signal and / or the image dataset provided by the camera 310.

[0088] The processor 312 is configured to determine a speckle contrast of a speckle pattern displayed in the reflected image. To determine the speckle contrast of the speckle pattern, the processor 312 is configured to calculate the standard deviation of the illumination divided by the average intensity. The resulting speckle contrast generally ranges between 0 and 1. A speckle contrast of 1 indicates no speckle blurring, i.e., no motion in the illuminated volume of the object 306, and a speckle contrast of 0 indicates maximum speckle blurring due to the motion of particles, e.g., red blood cells, detected in the illuminated volume of the object 306.

[0089] The processor 312 is further configured to determine a vital sign measurement value based on the determined speckle contrast. The processor 312 is also configured to determine a vital sign measurement value map based on the determined speckle contrast map, as described above.

[0090] To this end, the processor 312 has a neural network module including a trained neural network. The neural network is trained to predict vital sign measurements of the reflectance images based on the determined speckle contrast. Thus, the neural network is trained to use the speckle contrast determined by the processor as input and provide vital sign measurements as output. The trained neural network can be, for example, a multi-scale neural network, or a recurrent neural network (RNN), such as a gated recurrent unit (GRU) recurrent neural network or a long short-term memory (LSTM) recurrent neural network. Alternatively, the neural network can be a convolutional neural network (CNN).

[0091] Alternatively or in addition to a trained neural network, the processor 312 may include an algorithm that may implement a mechanism model. The device is configured to determine vital sign measurements based on (using) first principles assumptions.

[0092] The processor 312 may further comprise a providing unit for providing the determined vital sign measurements. The providing unit may be an output of the processor 312 and is configured to provide output data or an output signal representative of the determined vital sign measurements. The vital sign measurements determined by the system 300 may be used, preferably as part of an authentication process, to predict the presence of a living body, for example by performing the method steps described with reference to FIG. 3.

[0093] It is possible for system 300 to include only processor 312, and not projector 302 and camera 310. In this case, system 300, and in particular processor 312, is operatively connected to projector 302 and / or camera 310 for exchanging one or more reflected images.

[0094] Figure 4 shows a vital sign measurement map 400 of vital signs of a portion of a human hand 402. The vital sign map can be generated by performing the method described with reference to Figure 1 and / or by using the system 300 described with reference to Figure 3.

[0095] The vital sign measurement map 400 includes a plurality of vital sign measurements visualized according to their relative location on an illuminated portion of the hand 402. In other words, each of the vital sign measurements has an associated coordinate in the coordinate system of the hand 402, and the map is visualized in the coordinate system of the hand 402. The vital sign measurements thus represent vital sign measurements determined from a speckle pattern generated by illuminating respective locations on the hand 402 with coherent electromagnetic radiation.

[0096] In the map 400, the individual visual sign measurements are visualized with a color coding representing the degree of blood flow in each portion of the hand 402. Thus, from the individual vital sign measurements, it can be determined that areas 404, 405 of the hand 402 exhibit high blood flow, while other areas 406 and 408 exhibit relatively low blood flow.

[0097] In particular, areas 404, 405 of hand 402 exhibit high blood flow rates resulting in vital sign measurements based on which a confidence score can be determined that is relatively highly indicative of the presence of a living organism. In contrast, areas 406 and 408 exhibiting relatively low blood flow rates may lead to confidence values ​​that are relatively less indicative of the presence of a living organism. In the authentication process, a confidence score generated based on vital sign measurements of areas 404 or 405 may thus lead to a confirmation of authentication, whereas a confidence value based on vital sign measurements of areas 406 or 408 may lead to a denial of authentication. Alternatively, a relaunch of the authentication process may be triggered, for example, this time selecting a different position of the hand for generating a confidence score.

[0098] Vital sign measurement map 400 can be generated from a single reflectance image, for example, by splitting the reflectance image into multiple partial reflectance images. For each of the partial reflectance images, a vital sign measurement can be determined and combined into vital sign measurement map 400.

[0099] Alternatively, vital sign measurement map 400 may be generated from multiple reflectance images recorded by scanning over hand 402. For each of the multiple reflectance images, position information is preferably included to combine the vital sign measurements of the individual reflectance images into vital sign measurement map 400. To increase the resolution of the vital sign measurement map, each of the multiple reflectance images may be further divided into multiple sub-images, and for each sub-image, an individual vital sign measurement may be determined.

[0100] FIG. 5 shows a flow chart illustrating the authentication process including determining vital signs.

[0101] First, a detector signal is provided from a camera (step M1), representing, for example, an image of a fingerprint captured by a fingerprint sensor, or, for example, an image of a face in case of face recognition. The detector signal may be provided upon receiving a request to unlock the device from a user. The unlock request may trigger, for example, in case of face recognition, illumination of the user's face with flood infrared illumination and patterned infrared illumination. The reflected light may be captured by the camera to provide a detector signal representative of an image of the illuminated body part (e.g., face).

[0102] From the captured images, a low-level representation is generated (step M2). The low-level representation can be generated, for example, by employing Fast Fourier Transform (FFT), wavelets, deep learning such as CNN, energy models, regularized flows, vision transformers, or autoregressive image modeling.

[0103] Biometric authentication is performed based on the generated low-level representation (step M3). For this purpose, a low-level representation template is provided (step M4). For example, the analyzed facial or fingerprint features can be compared with a corresponding template. The template may be provided in order to obtain a matching score. In a particular embodiment, the template space may comprise templates of enrollment profiles of authorized users of the device, for example templates generated during the enrollment process. The matching score may be the score of the difference between the facial or fingerprint features in the template space and the corresponding features, for example a feature vector of an authorized user generated during the enrollment process. The matching score may be higher the closer the feature vector is to the feature vector in the template space, for example the shorter the distance or the smaller the difference.

[0104] Comparing the feature vector with the template from the template space to obtain a corresponding matching score may include using one or more classifiers or classifiable networks to classify and evaluate differences between the generated feature vector and the feature vector from the template space. Examples of different classifiers that may be used include, but are not limited to, linear, piecewise linear, non-linear classifiers, support vector machines, and neural network classifiers. In some embodiments, the matching score may be evaluated using a distance score between the feature vector and the template from the template space.

[0105] For authentication, the matching score may be compared to an unlock threshold of the device (step M5). The unlock threshold may represent, for example, a minimum difference in feature vectors between the face of an approved user according to the template and the face of the user in an unlock attempt to unlock the device. For example, the unlock threshold may be a threshold that determines whether the unlock feature vector is sufficiently close to the template vector associated with the face of the approved user.

[0106] If the matching score is below the unlock threshold, then the user's face or fingerprint in the captured image for unlocking does not match the authenticated user's face or fingerprint, in which case a signal indicating negative authentication is provided (step M6).

[0107] However, if the matching score is above the unlock threshold, then the user's face or fingerprint in the captured image for unlocking matches that of an authorized user, in which case a second authentication process can be initiated.

[0108] This second authentication process includes determining the user's vital signs (step M7), which may use the vital signs determination method described with reference to Figure 1. For example, the method described with reference to Figure 1 may be implemented using the system described with reference to Figure 3.

[0109] Based on the determined vital signs, it is verified whether the determined vital signs indicate the presence of a living body (step M8), for example by performing the method for predicting the presence of a living body described with reference to Fig. 2. For example, when combined with face recognition processing or fingerprint recognition, it can be determined whether a part of the user, for example a face or a finger, presented to the camera is a vital sign indicating the presence of a living body and not an attachment imitating, for example a spoofing attachment of, a respective body part of an approved user.

[0110] If the presence of a living body is denied, a signal indicating a negative authentication may be provided (corresponding to step M6).

[0111] However, if the user also successfully passes the second authentication step, ie the presence of a biometric is confirmed, a signal indicating a positive authentication may be provided (step M9).

[0112] As a result, the user is verified as an authorized user of the registration profile on the device and the device is unlocked. Unlocking may enable the user to access or use the device and / or to access selected features of the device, such as unlocking functionality of applications running on the device, unlocking a payment system or making payments, accessing personal data, displaying enhanced notifications, etc.

[0113] Alternatively, the authentication process may first be used to determine vital signs and predict the presence of a living body, and only if the presence of a living body is confirmed, then a separate second authentication process, such as biometric authentication including facial recognition or fingerprint sensing, may be performed.

[0114] Other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the appended claims.

[0115] The term "reflected image" as used herein is not limited to an actual visual representation of the imaged object. Instead, an "image" as referred to herein may generally be understood as a representation of the imaged object in terms of image data obtained by imaging the object, where "imaging" may refer to any process involving the interaction of electromagnetic waves, particularly light or radiation, with the object, specifically, for example, by reflection, and the subsequent capture of the electromagnetic waves with a light sensor (which may then also be considered as an image sensor). In particular, the term "reflected image" as used herein may refer to image data on the basis of which an actual visual representation of the imaged object may be constructed. For example, the image data may correspond to the assignment of color or grayscale values ​​to image locations, each image location may correspond to a location in or on the imaged object. The image or image data referred to herein may be, for example, two-dimensional, three-dimensional, or four-dimensional, where a four-dimensional image is understood as a three-dimensional image that changes over time, and similarly, a two-dimensional image that changes over time may be considered as a three-dimensional image. If the image data is digital image data, the reflected image may be considered a digital image, in which case the image locations may correspond to pixels or voxels of the image and / or image sensor.

[0116] In the claims, the word "comprising" does not exclude other elements or steps and the indefinite article "a" or "an" does not exclude a plurality.

[0117] A single unit or device may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

[0118] The steps performed by one or more units or devices, such as the steps of generating or receiving an image dataset representing at least one reflectance image of the speckle pattern, the steps of determining a speckle contrast of the speckle pattern, the steps of determining a vital sign measurement value based on the determined speckle contrast, and the steps of providing a vital sign measurement value, may be performed by any number of other units or devices. These steps may be implemented as program code means of a computer program and / or as dedicated hardware.

[0119] The computer program may be stored / distributed on a suitable medium, such as an optical storage medium or a solid-state medium, may be supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunications systems.

[0120] The units described herein may be processing units that are part of a classical computing system. The processing unit may include a general-purpose processor, or may include a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), or any other specialized circuit. The memory may be a physical system memory, which may be volatile, non-volatile, or a combination of the two. The term "memory" may include a computer readable storage medium, such as a non-volatile mass storage. If the computing system is distributed, the processing and / or memory capabilities may also be distributed. The computing system may include multiple structures as "executable components." The term "executable components" is a structure well understood in the computing arts as a structure that may be software, hardware, or a combination thereof. For example, when implemented in software, one skilled in the art will understand that the structure of the executable components may include software objects, routines, methods, etc. that may be executed on the computing system. This may include both executable components in the heap of the computing system or executable components on a computer readable storage medium. The structure of the executable components may reside on a computer-readable medium and, when interpreted by one or more processors, e.g., processor threads, of a computing system, cause the computing system to perform functions. Such structure may be directly computer readable by a processor, e.g., as where the executable components were binary, or may be structured to be interpretable and / or compilable to generate such binary directly interpretable by a processor, e.g., whether in a single stage or multiple stages. In other examples, the structure may be hard-coded or hard-wired logic gates that are implemented exclusively or nearly exclusively in hardware, such as in a field programmable gate array (FPGA), application specific integrated circuit (ASIC), or other specialized circuitry.Thus, the term "executable component" is a term that describes a structure well understood by one of ordinary skill in the art of computing, whether implemented in software, hardware, or a combination thereof. Any embodiment herein is described with reference to acts performed by one or more processing units of a computing system. When such acts are implemented in software, one or more processors direct the operation of the computing system in response to executing the computer-executable instructions that make up the executable component. A computing system may also include communication channels that enable the computing system to communicate with other computing systems, for example, over a network. A "network" is defined as one or more data links that enable the transmission of electronic data between computing systems and / or modules and / or other electronic devices. When information is transferred or provided to a computing system over a network or other communications connection (e.g., either wired, wireless, or a combination of wired or wireless), the computing system properly regards the connection as a transmission medium. A transmission medium may include a network and / or data links that may be used to transmit desired program code means in the form of computer-executable instructions or data structures and that may be accessed by a general-purpose or special-purpose computing system or combination thereof. Although not all computing systems require a user interface, in some embodiments a computing system includes a user interface system for use in interfacing with a user. The user interface serves as an input or output mechanism to a user, for example via a display.

[0121] Those skilled in the art will appreciate that at least a portion of the present invention may be implemented in a networked computing environment having many types of computing system configurations, including personal computers, desktop computers, laptop computers, message processors, handheld devices, multiprocessor systems, microprocessor-based or programmable consumer electronics, network PCs, minicomputers, mainframe computers, cell phones, PDAs, pagers, routers, switches, data centers, wearables such as glasses, etc. The present invention may also be implemented in a distributed system environment where both local and remote computing systems perform tasks that are linked, for example, through a network, by either wired data links, wireless data links, or a combination of wired and wireless data links. In a distributed system environment, program modules may be located in both local and remote memory storage devices.

[0122] Those skilled in the art will also appreciate that at least a portion of the present invention may be implemented in a cloud computing environment. A cloud computing environment may be distributed, but this is not required. If distributed, a cloud computing environment may be distributed internationally within an organization and / or may have components owned across multiple organizations. For purposes of this specification and the claims that follow, "cloud computing" is defined as a model that enables on-demand network access to a shared pool of configurable computing resources (e.g., networks, servers, storage, applications, and services). The definition of "cloud computing" is not limited to any of the many other advantages that such a model may derive when deployed. The computing system of the figure includes various components or functional blocks that may implement various embodiments disclosed herein, as described. The various components or functional blocks may be implemented on a local computing system or may be implemented on a distributed computing system that includes elements that reside in the cloud or that implement aspects of cloud computing. The various components or functional blocks may be implemented as software, hardware, or a combination of software and hardware. The computing system shown in the figure may have more or fewer components than those shown in the figure and may combine some of the components as appropriate.

[0123] Any reference signs in the claims shall not be construed as limiting the scope.

Claims

1. 1. A method for detecting vital signs, the method comprising: - generating or receiving (S1) an image dataset representing at least one reflected image of a speckle pattern produced by coherent electromagnetic radiation reflected from an object (306; 402); - determining the speckle contrast of said speckle pattern (S2); - determining a vital sign measurement based on said determined speckle contrast (S4); - providing said vital sign measurements (S5); A method comprising:

2. The method of claim 1 , comprising authenticating an object based on the provided vital sign measurements.

3. The method of claim 2 , wherein authenticating the object comprises matching at least one biometric characteristic obtained from the object with at least one reference biometric characteristic associated with an approved object.

4. 3. The method of claim 1 or 2, wherein at least two vital sign measurements, each associated with a different spatial location on the object (306; 402), are determined and provided as a map (400) of vital sign measurements.

5. 5. The method of claim 4, wherein to provide the map (400), the reflectance image is divided into multiple partial reflectance images, and an associated speckle contrast for each of the partial reflectance images is determined and used to determine an individual vital sign measurement for each partial reflectance image.

6. 5. The method of claim 4, wherein the image dataset represents at least two reflection images of a speckle pattern produced by coherent electromagnetic radiation reflected from the object (306; 402) at different spatial locations on the object (306; 402), and for each of the at least two reflection images, a vital sign measurement value associated with the respective spatial location is determined and provided as a map (400) of vital sign measurements.

7. The method of claim 6 , wherein each of the at least two reflectance images is divided into multiple partial reflectance images, and an individual vital sign measurement is determined for each of the partial reflectance images.

8. The method of claim 1 or 2, wherein the vital sign measurements are determined using a mechanistic model or a data-driven model.

9. 3. The method of claim 1 or 2, wherein the image dataset represents at least two reflection images of a speckle pattern produced by coherent electromagnetic radiation reflected from the object (306; 402) at the same or at least overlapping spatial locations on the object (306; 402), and for the reflection images vital sign measurements are determined and provided based on the speckle contrast of the respective reflection images.

10. and further comprising predicting the presence of a living organism based on the provided vital sign measurements, preferably comprising the following sub-steps: a substep (T2) of determining a confidence score based on said determined vital sign measurements; a substep (T3) of comparing said confidence score with a predefined confidence threshold; - a substep (T4, T5) of predicting the presence of a living organism based on said comparison; The method of claim 1 or 2, comprising at least one of:

11. The method of claim 10 , wherein the confidence score is determined by comparing the determined vital sign measurement to a standard or by using a trained neural network.

12. The method of claim 10 , comprising authenticating the object based on the determined confidence score.

13. The method of claim 10 , wherein from at least two reflection images of the speckle pattern, a composite confidence score is determined based on at least two confidence scores respectively determined for the at least two reflection images.

14. A computer program for detecting vital signs of an object (306; 402), comprising instructions for carrying out the steps of the method according to claim 1 or 2 when said computer program is executed on a computer.

15. A non-transitory computer-readable data medium storing the computer program of claim 14.

16. A system (300) for detecting vital signs, said system (300) comprising: a generating or receiving unit adapted to generate or receive an image dataset representative of at least one reflected image of a speckle pattern generated by coherent electromagnetic radiation reflected from an object (306; 402); a processor (312) configured to determine a speckle contrast of said speckle pattern and to determine a vital sign measurement based on said determined speckle contrast; a providing unit configured to provide said vital sign measurements; A system (300) comprising:

Images