A method of securing biometric information may involve obtaining a digital image that contains biometric information. The method may involve identifying at least one region of the digital image that contains the biometric information and masking the biometric information. The biometric information may be a user's fingerprint and the user's fingerprint may be sufficiently masked that the masked fingerprint would not be accepted as authentic by most or all biometric authentication systems as matching the original fingerprint.

Embodiments herein disclose computer-implemented methods, computer program products and computer systems for authenticating a user. The computer-implemented method may include receiving biographical data corresponding to a user. A change rate may be determined based on user biographical data. The computer-implemented method may include receiving first biometric data having a time-varying characteristic from the user at a first time and receiving second biometric data having the time-varying characteristic from the user at a second time that is later in time than the first time. Further, the computer-implemented method may include determining third biometric data based at least on the first biometric data, the second time, and the time-varying characteristic, and authenticating the user if the third biometric data is within a predetermined threshold of the second biometric data at the second time.

The present invention relates to a neural network training method. The neural network training method using a de-identified image according to the present invention comprises the steps of: encoding a first image represented by a n-th dimensional vector into a predetermined p-th dimensional second image; decoding the second image into a q-th dimensional third image; inputting the third image to a neural network and extracting object information included in the third image; and training at least one parameter information used for computation in the neural network by using the extracted object information. According to the present invention, de-identified images are used for neural network training such that neural network training is made possible without using personal information included in images.

A computer alters at least one recognizable metric or text in a digitally encoded photographic image by operating an alteration algorithm in response to user input data while preserving an overall aesthetic quality of the image and obscuring an identity of at least one individual or geographic location appearing in the image. An altered digitally-encoded photographic image prepared by the altering of the at least one recognizable metric or text in the image is stored in a computer memory. User feedback and/or automatic analysis may be performed to define parameter values of the alteration algorithm such that the alteration process achieves preservation of aesthetic qualities while obscuring an identity of interest.

A system managing vehicle operations based on thermal data. The system includes a thermal camera arranged in the vehicle to sense intra-vehicle thermal conditions. The system also includes a hardware-based storage device including a thermal-data analysis module that, when executed by a hardware-based processing unit, determines, based on the intra-vehicle thermal data, an activity or state of one or more vehicle occupants. The storage device may also include: an action module that, when executed, determines an output action based on the activity or state; and an output-interface module that, when executed, initiates performing the output action. The storage device may also include In various embodiments, the hardware-based storage device includes a database module that, when executed, obtains pre-stored occupant data corresponding to an occupant, and determining the output action is based on the pre-stored occupant data and occupant activity or state determined.

A nonce is sent to a user communication device. Obfuscated biometric data is received from the user communication device. The obfuscated biometric data is generated by an obfuscation process that uses the nonce and first biometric data. The first biometric data is generated from a biometric of a user at the user communication device. For example, the first biometric data may be biometric data from a fingerprint scan. The obfuscation process is reversed by using the first nonce to produce the first biometric data. The first biometric data is compared to known biometric data of the user. In response to the first biometric data being within a threshold of the known biometric data, the user is authenticated.

A method labels an image of a street view by first extracting, for each pixel, an appearance feature for inferring a semantic label, a depth feature for inferring a depth label. Then, a column-wise labeling procedure is applied to the features to jointly determine the semantic label and the depth label for each pixel using the appearance feature and the depth feature, wherein the column-wise labeling procedure is according to a model of the street view, and wherein each column of pixels in the images includes at most four layers.

Embodiments herein disclose computer-implemented methods, computer program products and computer systems for authenticating a user. The computer-implemented method may include receiving biographical data corresponding to a user. A change rate may be determined based on user biographical data. The computer-implemented method may include receiving first biometric data having a time-varying characteristic from the user at a first time and receiving second biometric data having the time-varying characteristic from the user at a second time that is later in time than the first time. Further, the computer-implemented method may include determining third biometric data based at least on the first biometric data, the second time, and the time-varying characteristic, and authenticating the user if the third biometric data is within a predetermined threshold of the second biometric data at the second time.

The present disclosure relates to secure storage of a detailed set of elements relating to fingerprint features for a finger and to a method for authenticating a candidate fingerprint of a finger using said detailed set of elements, allowing for improved security and user convenience.

The description relates in particular to a method for encoding information represented in the form of a function P, and to a corresponding method for decoding information. The encoding comprises the encoding of secondary information. These methods may be implemented within a context of biometric enrollment and (respectively) biometric authentication. The description also relates to an electronic device, a computer program, and a storage medium for the implementation of such methods.