A method and computing apparatus for extracting information from a document are provided. The method includes receiving a document, extracting data from the document, assigning the document to a category from among a predetermined plurality of categories based on a result of the extracted data, and generating a structured output by formatting the extracted data based on the assigned category.

Provided are an augmented handwritten signature authentication method and an electronic device supporting the same, the method including: receiving a primary touch input corresponding to a primary handwritten signature input of a user; receiving, after the primary handwritten signature input is received and a specified time period elapses, a secondary mark input of the user; obtaining primary touch position data corresponding to the primary touch input, and the secondary mark input; and performing user authentication by comparing the primary touch position data corresponding to the primary touch input and secondary touch position data related to at least part of the secondary mark input with prestored primary touch registration data and secondary touch registration data, respectively.

An input device including: a display device including a first display region; a plurality of sensor electrodes configured for capacitive sensing, where the plurality of sensor electrodes overlap at least a portion of the first display region; and a processing system operatively connected to the plurality of sensor electrodes and configured to: output a placement guide graphic on the first display region, where the placement guide provides alignment indication for a feature of an input object; generate a pressure-gauge graphic based on pressure exerted on the input device by the input object; send the pressure-gauge graphic for display while the input object is still in contact with the input device; obtain, based on resulting signals received with at least one sensor electrode of the plurality of sensor electrodes, a first capacitive image including the input object; and authenticate a user based on at least the first capacitive image.

A method for training a classifier for authenticating signatures hand-drawn on an electronic input element includes receiving a set of multiple signature properties of each of multiple signatures documented over a time range of a common user, each set of multiple signature properties is associated with a time period during which a respective signature was documented at the time range, wherein the plurality of signatures were hand-drawn and digitally recorded using an electronic input element; generating a signature authenticating classifier for authenticating additional signatures of the common user based on the set of multiple signature properties of each of the plurality of signatures, wherein a weight assigned to each the set of multiple signature properties or a portion thereof decreases overtime, the weight is used for the generation of the classifier; and providing the signature authenticating classifier for authenticating the additional signatures.

Embodiments of the invention are generally directed to systems, methods, devices, and machine-readable mediums for implementing gesture-based signature authentication. In one embodiment, a method may involve recording a first gesture-based signature and storing the recorded first gesture-based signature. Then the method compares the first gesture-based signature with a second gesture-based signature. Then the method verifies the first gesture-based signature as authentic when the first gesture-based signature is substantially similar to the second gesture-based signature.

A handwriting geometry recognition and calibration system by using neural network and mathematical feature includes: a pre-processor for pre-processing coordinate points of geometric figures from user's handwriting so as to get a plurality of sample points which expresses the geometric figures to be recognized; a neural network connected to the pre-processor for receiving the sample points of the geometric figure and recognizing the geometric figure so as to acquire a coarse class of the geometric figure; and an mathematical logic unit connected to the neural network for receiving recognition results from the neural network, including coarse classifications which are used in a secondary classification by using conventional mathematical recognition logics so as to determine an exact geometry shape of the geometric figure; then the geometric figure being calibrated so as to get a geometry with a regular shape.

According to the present disclosure, a handwritten signature to be authenticated is received, a plurality of pieces of signature behavioral characteristic information are extracted, all of the plurality of the pieces of the extracted signature behavioral characteristic information are applied to each of first and second signature authentication algorithms using different techniques to analyze a degree of matching between the received handwritten signature and a registered handwritten signature, results of analysis performed by the first and second signature authentication algorithms are combined to adjust a false rejection rate and a false acceptance rate, and whether handwritten signature authentication succeeds is finally determined.

Methods and systems for adaptive, template-independent handwriting extraction from images using machine learning models and without manual localization or review. For example, the system may receive an input image, wherein the input image comprises native printed content and handwritten content. The system may process the input image with a model to generate an output image, wherein the output image comprises extracted handwritten content based on the native handwritten content. The system may process the output image to digitally recognize the extracted handwritten content. The system may generate a digital representation of the input image, wherein the digital representation comprises the native printed content and the digitally recognized extracted handwritten content.

Methods, systems, and computer program products are provided for signature verification. Signature verification may be provided for target signatures using genuine signatures. A signature verification model pipeline may extract features from a target signature and a genuine signature, encode and submit both to a neural network to generate a similarity score, which may be repeated for each genuine signature. A target signature may be classified as genuine, for example, when one or more similarity scores exceed a genuine threshold. A signature verification model may be updated or calibrated at any time with new genuine signatures. A signature verification model may be implemented with multiple trainable neural networks (e.g., for feature extraction, transformation, encoding, and/or classification).

Methods, systems, and computer program products are provided for signature verification. Signature verification may be provided for target signatures using genuine signatures. A signature verification model pipeline may extract features from a target signature and a genuine signature, encode and submit both to a neural network to generate a similarity score, which may be repeated for each genuine signature. A target signature may be classified as genuine, for example, when one or more similarity scores exceed a genuine threshold. A signature verification model may be updated or calibrated at any time with new genuine signatures. A signature verification model may be implemented with multiple trainable neural networks (e.g., for feature extraction, transformation, encoding, and/or classification).