A finger guide device that positions a finger (or minutiae containing digit) of a human subject on a fingerprint sensor in a manner optimal for the data capture operation of authentication or identification of said subject wherein a relevant portion of the finger is in alignment with a sensor or scanner. The finger guide device may also be used for enrollment of the initial fingerprint data into the system. The device may contain an outer surface ridge which feels somewhat uncomfortable due to application of a high pressure per square inch on small areas of the finger when the finger is incorrectly positioned to encourage correct placement of the finger. The finger guide device may have a curved inside surface to contour to a wide variety of fingertip shapes and sizes, wherein the sides and front have shorter radii of curvature than the rearward portion of the finger guide device.

Techniques for classifying records in a dataset are described. The method includes identifying a set of features of a target record and assigning a scoring metric to each feature in the set of features. The method also includes processing the set of features based on the scoring metric to obtain a reduced subset of features and an expanded subset of features. The method also includes searching a store of electronic records using the reduced subset of features to obtain a reduced subset of electronic records. The method also includes searching the reduced subset of electronic records using the expanded subset of features to obtain a set of matching electronic records.

Methods and systems for of generating reporting data in an automated, efficient, and risk-free fashion relating to an identification match relating to a probe image are disclosed. Methods include automatically capturing a comparison area in the probe image and a comparison area of a candidate image based on examiner input; facilitating a determination of whether a similarity or a dissimilarity exists between the comparison area in the probe image and the comparison area of the candidate image; automatically recording metadata based on the determination of whether the similarity or the dissimilarity exists between the comparison area in the probe image and the comparison area of the candidate image and updating an audit log; and generating a report comprising the metadata.

A computer-implemented method for generating a representation for a fingerprint includes receiving, by a computer processor, an image of a given fingerprint. The method extracts particular attributes for the given fingerprint from the image using a first neural network. The first neural network is trained to identify particular attributes in fingerprints and constructs a first feature vector from the extracted particular attributes, where the first feature vector has a first fixed length. The method includes extracting textural features of the given fingerprint from the image using a second neural network, where the second neural network is trained to identify textural features that are not limited to particular attributes and constructing a second feature vector from the extracted textural features, where the second feature vector has a second fixed length. The method includes concatenating the first feature vector with the second feature vector to form a representation for the given fingerprint.

In order to authenticate a user of an electronic device, an image of the user's fingerprint is captured. Before feature information is extracted, the fingerprint image is enhanced via localized normalization thereby increasing contrast within the fingerprint image. Thereafter, feature information, such as key point data, is extracted from the image and compared to a predefined template to determine whether the feature information matches the template. If so, the user is authenticated. By enhancing the quality of the fingerprint image through localized normalization, the reliability of the matching operation is significantly enhanced. In addition, using key point comparisons for assessing similarity between the feature information and the template helps to address inconsistencies relating to finger rotation, scale, and translation during capture.

A method for extracting a signature of a fingerprint shown on a source image is described. For this purpose, the source image is transformed into the frequency domain. One or more ridge frequencies are next determined by means of a convolutional neural network applied to said transformed image, n being an integer greater than or equal to 1. The source image is normalized in response to said n ridge frequencies determined. One or more signatures of said fingerprint are finally extracted from said n normalized images.

The authentication information processing method includes acquiring related information generated for each of a plurality of base points representing feature points of biometric information extracted from an image, for a collation base point and a registration base point. The collation base point is included in authentication information for collation used for biometric authentication. The registration base point is included in authentication information for registration. The related information associates attribute information with a central base point. The method includes determining whether the attribute information associated with the collation base point matches the attribute information associated with the registration base point, and comparing the collation base point and the registration base point for which it is determined that the respective attribute information match each other, and determining a correspondence between the authentication information for collation and the authentication information for registration used to calculate a degree of similarity.

A fingerprint authentication method and device, display device, and biometric security apparatus include: a fingerprint sensor; a minutiae extraction circuit connected to the fingerprint sensor; a minutiae storage circuit connected to the minutiae extraction circuit; and a minutiae match circuit connected to the minutiae extraction circuit and the minutiae storage circuit, wherein the minutiae match circuit includes a class-wise comparator having a first input connected to the minutiae extraction circuit for receiving sensed fingerprint minutiae from each class of a plurality of classes, a second input connected to the minutiae storage circuit for receiving stored fingerprint minutiae belonging to each same class of the plurality of classes, respectively, and an output providing a fingerprint authentication signal responsive to the class-wise comparator.

Methods and systems for of generating reporting data in an automated, efficient, and risk-free fashion relating to an identification match relating to a probe image are disclosed. Methods include automatically capturing a comparison area in the probe image and a comparison area of a candidate image based on examiner input; facilitating a determination of whether a similarity or a dissimilarity exists between the comparison area in the probe image and the comparison area of the candidate image; automatically recording metadata based on the determination of whether the similarity or the dissimilarity exists between the comparison area in the probe image and the comparison area of the candidate image and updating an audit log; and generating a report comprising the metadata.

Technologies are presented herein in support of a system and method for performing fingerprint recognition. Embodiments of the present invention concern a system and method for capturing a user's biometric features and generating an identifier characterizing the user's biometric features using a mobile device such as a smartphone. The biometric identifier is generated using imagery captured of a plurality of fingers of a user for the purposes of authenticating/identifying the user according to the captured biometrics and determining the user's liveness. The present disclosure also describes additional techniques for preventing erroneous authentication caused by spoofing. In some examples, the anti-spoofing techniques may include capturing one or more images of a user's fingers and analyzing the captured images for indications of liveness.