Hyperspectral imaging of biofluids for biometric applications
Hyperspectral imaging (HSI) of biofluids for biometric applications is disclosed. A HSI device scans a region of a human subject's skin with sweat thereon, without requiring the human subject to touch any surface. The resulting HSI data is processed to identify aspects of the data that represent physical and/or chemical features that uniquely identify the subject. Processing the HSI data includes identifying one or more particular metabolites in the subject's sweat by analyzing wavelengths which those metabolites reflect. Processing the HSI data includes identifying one or more glands beneath the outermost surface of the subject's skin based on HSI-detected wavelength reflectance and wavelength penetration. The disclosed system may generate and store an identity profile corresponding to a human's unique identity features, as determined based on the HSI data processing. A subject's identity is verified by comparing subsequent HSI scans of his skin with sweat thereon to his stored identity profile.
1 . A method comprising:
capturing, via a hyperspectral image (HSI) scanner, HSI scan data of a human subject's skin comprising a biofluid thereon, wherein the biofluid comprises sweat excreted from the human subject's skin;
generating a data cube representation of the HSI scan data, wherein the data cube comprises a three-dimensional data structure further comprising a spatial domain and a spectral domain;
processing the data cube, wherein processing the data cube comprises;
detecting one or more signals in the spatial domain and in the spectral domain, wherein the one or more signals are indicative of one or more uniquely identifiable biofluid metabolite features, and wherein the one or more uniquely identifiable biofluid metabolite features comprise at least one of lactate dehydrogenase, glutamate dehydrogenase, and urea present in the biofluid;
detecting one or more points in the spatial domain, wherein the one or more points are indicative of one or more glands in a subdermal layer of the human subject's skin; and
calculating at least one Euclidean distance between the one or more points; and
generating a feature vector comprising the detected one or more signals indicative of one or more uniquely identifiable biofluid metabolite features and the at least one Euclidean distance between the one or more points, whereby the feature vector is used for subsequent identity verification of the human subject based on the one or more signals indicative of one or more uniquely identifiable biofluid metabolite features.
2 . The method of claim 1 , further comprising:
comparing the feature vector comprising the detected one or more signals indicative of one or more uniquely identifiable biofluid metabolite features and the at least one Euclidean distance to an identity profile to determine a match, wherein the identity profile comprises one or more previously detected signals indicative of one or more uniquely identifiable biofluid metabolite features and at least one previously calculated Euclidean distance corresponding to previously captured HSI scan data of a previous human subject's skin comprising the biofluid thereon; and
in response to determining a first match between the one or more signals indicative of one or more uniquely identifiable biofluid metabolites and the one or more previously detected signals indicative of one or more uniquely identifiable biofluid metabolite features and a second match between the at least one Euclidean distance and the at least one previously calculated Euclidean distance corresponding to previously captured HSI scan data of a previous human subject's skin, determining that the human subject and the previous human subject are the same human subject, thereby verifying the human subject's identity.
3 . The method of claim 1 , wherein the one or more signals indicative of uniquely identifiable biofluid metabolite features comprise a HSI-detected presence of the lactate dehydrogenase, the glutamate dehydrogenase, and/or the urea in the sweat detected above and/or below an outermost skin surface of the human subject's finger.
4 . The method of claim 3 , wherein the lactate dehydrogenase is detected at a wavelength of about 405 nm.
5 . The method of claim 3 , wherein the glutamate dehydrogenase and the urea are detected at a wavelength of about 340 nm.
6 . The method of claim 1 , wherein capturing the HSI scan data of the human subject's skin further comprises positioning the human subject's skin in physical proximity to the HSI scanner and within a field of view of the HSI scanner without the human subject's skin making contact with any surface.
7 . The method of claim 1 , wherein the biofluid on the human subject's skin comprises a plurality of metabolites in their natural states and undisturbed by chemical reagents.
8 . A system comprising:
a hyperspectral image (HSI) scanner; and
a processor operatively connected to the HSI scanner, wherein the processor is operatively configured to:
receive, from the HSI scanner, HSI scan data of a human subject's skin comprising a biofluid thereon, wherein the biofluid comprises sweat excreted from the human subject's skin;
generate a data cube representation of the HSI scan data, wherein the data cube comprises a three-dimensional data structure further comprising a spatial domain and a spectral domain;
process the data cube, wherein processing the data cube comprises:
detecting one or more signals in the spatial domain and in the spectral domain, wherein the one or more signals are indicative of one or more uniquely identifiable biofluid metabolite features and the one or more uniquely identifiable biofluid metabolite features comprise at least one of lactate dehydrogenase, glutamate dehydrogenase, and urea present in the biofluid;
detecting one or more points in the spatial domain, wherein the one or more points are indicative of one or more glands in a subdermal layer of the human subject's skin; and
calculating at least one Euclidean distance between the one or more points; and
generate a feature vector comprising the detected one or more signals indicative of one or more uniquely identifiable biofluid metabolite features, whereby the feature vector is used for subsequent identity verification of the human subject based on the one or more signals indicative of one or more uniquely identifiable biofluid metabolite features.
9 . The system of claim 8 , wherein the processor is further operatively configured to:
compare the feature vector comprising the detected one or more signals indicative of one or more uniquely identifiable biofluid metabolite features and the at least one Euclidean distance to an identity profile to determine a match, wherein the identity profile comprises one or more previously detected signals indicative of one or more uniquely identifiable biofluid metabolite features and at least one previously calculated Euclidean distance corresponding to previously captured HSI scan data of a previous human subject's skin comprising the biofluid thereon; and
in response to determining a first match between the one or more signals indicative of one or more uniquely identifiable biofluid metabolites and the one or more previously detected signals indicative of one or more uniquely identifiable biofluid metabolite features and a second match between the at least one Euclidean distance and the at least one previously calculated Euclidean distance corresponding to previously captured HSI scan data of a previous human subject's skin, determine that the human subject and the previous human subject are the same human subject, thereby verifying the human subject's identity.
10 . The system of claim 8 , wherein the one or more signals indicative of uniquely identifiable biofluid metabolite features comprise a HSI-detected presence of the lactate dehydrogenase, the glutamate dehydrogenase, and/or the urea in the sweat detected above and/or below an outermost skin surface of the human subject's finger.
11 . The system of claim 10 , wherein the lactate dehydrogenase is detected at a wavelength of about 405 nm.
12 . The system of claim 10 , wherein the glutamate dehydrogenase and the urea are detected at a wavelength of about 340 nm.
13 . The system of claim 8 , wherein capturing the HSI scan data of the human subject's skin further comprises positioning the human subject's skin in physical proximity to the HSI scanner and within a field of view of the HSI scanner without the human subject's skin making contact with any surface.
14 . The system of claim 8 , wherein the biofluid on the human subject's skin comprises a plurality of metabolites in their natural states and undisturbed by chemical reagents.
15 . A tangible, non-transitory, computer-readable medium comprising instructions encoded therein, wherein the instructions when executed by a processor, cause the processor to:
receive, from a hyperspectral image (HSI) scanner, HSI scan data of a human subject's skin comprising a biofluid thereon, wherein the biofluid comprises sweat excreted from the human subject's skin;
generate a data cube representation of the HSI scan data, wherein the data cube comprises a three-dimensional data structure further comprising a spatial domain and a spectral domain;
process the data cube, wherein processing the data cube comprises:
detecting one or more signals in the spatial domain and in the spectral domain, wherein the one or more signals are indicative of one or more uniquely identifiable biofluid metabolite features and the one or more uniquely identifiable biofluid metabolite features comprise at least one of lactate dehydrogenase, glutamate dehydrogenase, and urea present in the biofluid;
detecting one or more points in the spatial domain, wherein the one or more points are indicative of one or more glands in a subdermal layer of the human subject's skin; and
calculating at least one Euclidean distance between the one or more points; and
generate a feature vector comprising the detected one or more signals indicative of one or more uniquely identifiable biofluid metabolite features and at the at least one Euclidean distance between the one or more points, whereby the feature vector is used for subsequent identity verification of the human subject based on the one or more signals indicative of one or more uniquely identifiable biofluid metabolite features.
16 . The tangible, non-transitory, computer-readable medium of claim 15 comprising additional instructions encoded therein, wherein the additional instructions when executed by the processor, further cause the processor to:
compare the feature vector comprising the detected one or more signals indicative of one or more uniquely identifiable biofluid metabolite features and the at least one Euclidean distance to an identity profile to determine a match, wherein the identity profile comprises one or more previously detected signals indicative of one or more uniquely identifiable biofluid metabolite features and at least one previously calculated Euclidean distance corresponding to previously captured HSI scan data of a previous human subject's skin comprising the biofluid thereon; and
in response to determining a first match between the one or more signals indicative of one or more uniquely identifiable biofluid metabolites and the one or more previously detected signals indicative of one or more uniquely identifiable biofluid metabolite features and a second match between the at least one Euclidean distance and the at least one previously calculated Euclidean distance corresponding to previously captured HSI scan data of a previous human subject's skin, determine that the human subject and the previous human subject are the same human subject, thereby verifying the human subject's identity.
17 . The tangible, non-transitory, computer-readable medium of claim 15 , wherein the one or more signals indicative of uniquely identifiable biofluid metabolite features comprise a HSI-detected presence of the lactate dehydrogenase, the glutamate dehydrogenase, and/or the urea in the sweat detected above and/or below an outermost skin surface of the human subject's finger.
18 . The tangible, non-transitory, computer-readable medium of claim 17 , wherein the lactate dehydrogenase is detected at a wavelength of about 405 nm, and wherein the glutamate dehydrogenase and the urea are detected at a wavelength of about 340 nm.
19 . The tangible, non-transitory, computer-readable medium of claim 15 , wherein capturing the HSI scan data of the human subject's skin further comprises positioning the human subject's skin in physical proximity to the HSI scanner and within a field of view of the HSI scanner without the human subject's skin making contact with any surface.
20 . The tangible, non-transitory, computer-readable medium of claim 15 , wherein the biofluid on the human subject's finger comprises a plurality of metabolites in their natural states and undisturbed by chemical reagents.