Abstract: Provided are a text processing method and apparatus, an electronic device and a non-transitory computer-readable medium. The method includes: collecting a to-be-processed text image, and performing gesture recognition on the to-be-processed text image to obtain a to-be-processed text, where the to-be-processed text is a text selected from the to-be-processed text image through a gesture; performing voice broadcasting on the to-be-processed text to prompt a user to perform dictation processing on the to-be-processed text; and collecting a dictation text image, performing recognition on the dictation text image, and determining a dictation check result according to a recognition result and the to-be-processed text.

Abstract: Systems and techniques for a physical access control systems with localization-based intent detection are described herein. In an example, an access control system may regulate access to an asset. The access control system is adapted to establish a first connection with a key-device. The access control system may be further adapted to receive a credential for a user over the first connection. The access control system may be further adapted to establish a second connection with the key-device. The access control system may be further adapted to determine an intent of the user to access the asset. The access control system may use location data derived from the second connection to determine the intent of the user. The access control system may be further adapted to provide the credential to an access controller, based on identifying an intent of the user to access the asset.

Abstract: A method for recognizing at least one object in images by a camera and a processor is provided. The at least one object includes content information and operation direction information. The operation direction information includes inspection direction, re-inspection direction, and a combination thereof. The method includes a first re-inspection step, the first re-inspection step includes using the processor to inspect whether the re-inspection direction of one of the at least one object matches a paring relationship. If so, the processor processes the content information of the at least one object and another one object to generate computational result.

Abstract: An information processing method includes determining a type of a selected character, among a plurality of characters included in a displayed mathematical expression, that is selection-operated by a user; identifying, based on the determined type of the selected character, an associated character, among the plurality of characters, that is associated with the character that is selection-operated; and setting, a range including the selected character and the associated character among the plurality of characters as a selection range of the character selected by the user.

Abstract: In one embodiment, a method includes receiving a user request from a first user from a client system associated with a first user, wherein the user request comprise a gesture-input from the first user and a speech-input from the first user, determining an intent corresponding to the user request based on the gesture-input by a personalized gesture-classification model associated with the first user, executing one or more tasks based on the determined intent and the speech-input, and sending instructions for presenting execution results of the one or more tasks to the client system responsive the user request.

Abstract: The present disclosure relates to an information processing method in a game, which is applied to a mobile terminal for displaying a human-computer interaction interface in a touch screen and includes: obtaining an input fingerprint of a touch medium by means of the touch screen, and calculating similarity between the input fingerprint and a target fingerprint, wherein a mapping relationship exists between target fingerprints and a optional virtual object (S110); in response to detecting that the similarity is greater than a threshold value, obtaining action information of the touch medium on the touch screen, and determining a target virtual object according to the action information (S120); and controlling the optional virtual object corresponding to the target fingerprint to attack the target virtual object (S130).

Abstract: A highly reliable waterproof electronic pen includes a board holder in a board housing including a recessed portion having an opening over a lower surface of the recessed portion. A circuit board is housed in the recessed portion of the board housing. Circuit components easily affected by heat are installed on a first surface of the circuit board, and circuit components not easily affected by heat are installed on a second surface of the circuit board. A thermosetting resin formed over the second surface of the circuit board when the circuit board is housed in the recessed portion seals the opening over the lower surface of the recessed portion of the board housing.

Abstract: Provided is a pen data storage apparatus that stores pen data including at least coordinate data regarding a position instructed and input by an electronic pen, in units of the pen data, in which each piece of the stored pen data includes function identification information that identifies a processing function for the pen data.

Abstract: Systems and methods are disclosed for detecting tremors in a subject. One method comprises receiving data from a digital device, the data comprising a plurality of digital device positions and a plurality of timestamps, each timestamp in the plurality of timestamps being associated with a digital device position in the plurality of digital device positions. The method further comprises determining a plurality of frequencies of hand movements of the subject based on the plurality of digital device positions and plurality of timestamps. The method further comprises determining a subportion of the data corresponding to frequencies of hand movements above a low tremor threshold, and determining a magnitude of tremors of the subject's hand based, at least in part, on the subportion of the data.

Abstract: Provided is an ink amount calculation method performed by a processor of a computer. The method includes acquiring coordinate information related to stroke data generated according to an operation of an electronic pen, and calculating, based on the coordinate information, an ink amount related to an amount of the operation of the electronic pen.

Abstract: An apparatus includes a memory and processor. The memory stores document categories, text generated from an image a physical document page, and a machine learning algorithm. The machine learning algorithm is configured to extract features associated with natural language processing and features associated with the text. The machine learning algorithm is also configured to generate a feature vector that includes the first and second pluralities of features, and to generate, based on the feature vector, a set of probabilities, each of which is associated with a document category and indicates a probability that the physical document from which the text was generated belongs to that document category. The processor applies the machine learning algorithm to the text, to generate the set of probabilities, identifies a largest probability, and assigns the image to the associated document category.

Abstract: Systems and methods for aligning a mobile device and a document are disclosed. An exemplary method comprises the steps of determining a model identifier from the mobile device; associating the model identifier with a device configuration from a source; receiving an image of the document taken by the camera of the mobile device; identifying a document type; associating the document type with a document configuration from the source; selecting an alignment feedback schema based on the device configuration and the document configuration; generating alignment feedback based on the image processing; detecting for a data connection between the mobile device and the document; and generating a connection indication when the data connection is detected.

Abstract: A computer-implemented method, according to one embodiment, includes: receiving an image having characters that correspond to a language, and using a text recognition algorithm to determine a first language believed to correspond to the characters. A first confidence level associated with the first language is also computed, and a determination is made as to whether the first confidence level associated with the first language is outside a predetermined range. In response to determining that the first confidence level associated with the first language is not outside the predetermined range, the first language is output as the given language. The text recognition algorithm is trained using a simple shallow neural network and a generated mixed language corpus. The generated mixed language corpus is formed by: randomly sampling libraries having vocabulary and/or characters therein, and combining the randomly sampled vocabulary and/or characters to form the generated mixed language corpus.

Abstract: A computer implemented method for sending context information between programs, the method including: displaying a graphical user interface including a plurality of selectable application icons; receiving a simultaneous selection of a first icon and a second icon from the plurality of selectable application icons; launching a first program associated with the first icon; launching a second program associated with the second icon; and sending context information between the first program and the second program.

Abstract: The utility model discloses a non-adhesive detachable protective film, including the film body attached to the screen. The aforesaid film body has a soft resin layer fixed on the inner border; in which, the soft resin layer is set in strips along the edge of the border of the film body, forming a frame-sticking structure. Between the aforesaid soft resin layer and the film body, there is an adhesive layer for bonding and fixing; in which, the former one is pressed against the screen surface under pressure extrusion, forming a pressure-attached fixing structure with the screen surface. The utility model uses soft resin layer that allows the film body to be attach to the screen by extrusion, without using adhesive film. Besides, the film surface will not stick to dust when it is attached and removed in high frequency, and the fitting effect will not be reduced by repeated use.

Abstract: In one aspect, an example method includes a processor (1) applying a feature map network to an image to create a feature map comprising a grid of vectors characterizing at least one feature in the image and (2) applying a probability map network to the feature map to create a probability map assigning a probability to the at least one feature in the image, where the assigned probability corresponds to a likelihood that the at least one feature is an overlay. The method further includes the processor determining that the probability exceeds a threshold, and responsive to the processor determining that the probability exceeds the threshold, performing a processing action associated with the at least one feature.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media for accurately and flexibly generating scalable fonts utilizing multi-implicit neural font representations. For instance, the disclosed systems combine deep learning with differentiable rasterization to generate a multi-implicit neural font representation of a glyph. For example, the disclosed systems utilize an implicit differentiable font neural network to determine a font style code for an input glyph as well as distance values for locations of the glyph to be rendered based on a glyph label and the font style code. Further, the disclosed systems rasterize the distance values utilizing a differentiable rasterization model and combines the rasterized distance values to generate a permutation-invariant version of the glyph corresponding glyph set.

Abstract: A method for data presentation includes assembling a set of documents in response to a search query by a user having a social network. A respective person is identified with each of a group of documents in the set. For at least one document in the group, a chain of one or more links is found in the social network between the respective person and the user. A search results page is displayed, including an identification of the at least one document together with a sequence of breadcrumbs corresponding to the one or more links in the chain.

Abstract: A highly reliable waterproof electronic pen includes a board holder in a board housing including a recessed portion having an opening over a lower surface of the recessed portion. A circuit board is housed in the recessed portion of the board housing. Circuit components easily affected by heat are installed on a first surface of the circuit board, and circuit components not easily affected by heat are installed on a second surface of the circuit board. A thermosetting resin formed over the second surface of the circuit board when the circuit board is housed in the recessed portion seals the opening over the lower surface of the recessed portion of the board housing.

Abstract: Disclosed is an electronic pen that includes a conductive core body, a power supply circuit, a first signal generation circuit which receives power from the power supply circuit and generates a first signal, and a second signal generation circuit which receives power from the power supply circuit and generates a second signal different from the first signal, and an operation switch which sets an operation mode of the electronic pen to either a first operation mode or a second operation mode. While the operation mode of the electronic pen is set to the first operation mode, the conductive core body transmits the first signal generated by the first signal generation circuit. While the operation mode of the electronic pen is set to the second operation mode, the conductive core body transmits the second signal generated by the second signal generation circuit.

Abstract: An electronic device includes an input configured to receive a signature from a user; a communication interface configured to communicate with a server; and a controller configured to classify the signature into at least one stroke, to transmit authentication information for the at least one stroke to the server, and to control the communication interface to receive a result of authentication of the signature from the server.

Abstract: A call translation system and a method for operating the management system in a controlled environment is disclosed. The call translation system includes a calling device and a call translation server. The calling device receives authorization from the call translation server to conduct call sessions within the controlled environment. The calling device further receives a call session application from the call translation server that enables the calling device to initiate and establish call sessions through the call translation server. The call session application allows a user of the calling device to select outside parties to add to the call session.

Abstract: Disclosed is an electronic device for processing a handwriting input and including a touch screen, a processor operatively connected with the touch screen, and a memory operatively connected with the processor, wherein the memory stores instructions, which when executed, cause the processor to control the electronic device to perform handwriting recognition for a first handwriting input of a user displayed on the touch screen, to convert the first handwriting input into a text, identify at least one of an attribute or characteristic of the first handwriting input, apply at least one of the identified attribute or characteristic to the converted text, and in response to a request for conversion of the first handwriting input, replace the first handwriting input into a text (herein after, a first rich text) to which the identified at least one of the attribute or characteristic has been applied.

Abstract: A computer-implemented method for designing a user-specific writing skill game is provided. The computer-implemented method comprises tracking a handwriting performance and generating a digital representation of the handwriting performance. The handwriting performance is performed by a user with a writing instrument. The method further comprises identifying user-specific handwriting skills which require improvement based on the digital representation of the handwriting performance. Then a writing skill game is designed. The writing skill game is designed to include one or more game tasks to be performed by the user. The one or more game tasks require the user to apply the user-specific handwriting skills which are to be improved.

Abstract: The present disclosure relates to a handwritten text recognition method, including: acquiring an information sequence including a plurality of track points of handwritten text, wherein information on each track point comprises its abscissa, writing time and writing state value; dividing the plurality of track points into a plurality of strokes according to the writing state value of each track point, the writing state value including a first value representative of stroke pen-up and a second value representative of stroke pen-down, respectively; calculating a first segmentation threshold of the handwritten text; determining a first text segmentation point according to a result of comparison between an absolute value of a difference between abscissas of a start track point of one stroke and an end track point of its previous stroke and the first segmentation threshold; and performing text segmentation according to the first text segmentation point to obtain a text segmentation result.

Abstract: The driving circuit of the display includes a timing controller. The timing controller is coupled to a general purpose input/output (GPIO) pin of the touch driver. The timing controller receives an instruction signal via the general purpose input/output pin of the touch driver. The timing controller starts a detection period according to a main falling edge of the instruction signal. The timing controller determines a current operating status of the touch driver according to a number of sub-falling edges of the instruction signal during the detection period.

Abstract: An apparatus includes a memory and processor. The memory stores document categories, text generated from an image a physical document page, and a machine learning algorithm. The text includes errors associated with noise in the image. The machine learning algorithm is configured to extract features associated with natural language processing and features associated with the errors from the text. The machine learning algorithm is also configured to generate a feature vector that includes the first and second pluralities of features, and to generate, based on the feature vector, a set of probabilities, each of which is associated with a document category and indicates a probability that the physical document from which the text was generated belongs to that document category. The processor applies the machine learning algorithm to the text, to generate the set of probabilities, identifies a largest probability, and assigns the image to the associated document category.

Abstract: A computing system for adaptive point generation includes a storage to store a densely sampled polyline or surface, or mathematical function, and a processor to compute the area of a contour of the polyline or function with respect to itself, or compute the volume of the surface or function with respect to itself, adaptively resample the polyline, surface, or function, wherein the adaptive resampling is based on and inversely proportional to the computed area or volume, and connect adaptively resampled points as an adaptively sampled polyline or surface.

Abstract: Techniques for determining value of a home by applying one or more neural network models to images of spaces in the home. The techniques include: obtaining at least one image of a first space inside or outside of a home; determining a type of the first space by processing the at least one image of the first space with a first neural network model; identifying at least one feature in the first space by processing the at least one image with a second neural network model different from the first neural network model and trained using images of spaces of a same type as the first space; and determining a value of the home at least in part by using the at least one feature as input to a machine learning model different from the first neural network model and the second neural network model.

Abstract: The present disclosure relates to a system and method to extract information from unstructured image documents. The extraction technique is content-driven and not dependent on the layout of a particular image document type. The disclosed method breaks down an image document into smaller images using the text cluster detection algorithm. The smaller images are converted into text samples using optical character recognition (OCR). Each of the text samples is fed to a trained machine learning model. The model classifies each text sample into one of a plurality of pre-determined field types. The desired value extraction problem may be converted into a question-answering problem using a pre-trained model. A fixed question is formed on the basis of the classified field type. The output of the question-answering model may be passed through a rule-based post-processing step to obtain the final answer.

Abstract: Systems and techniques for a physical access control systems with localization-based intent detection are described herein. In an example, an access control system may regulate access to an asset. The access control system is adapted to establish a first connection with a key-device. The access control system may be further adapted to receive a credential for a user over the first connection. The access control system may be further adapted to establish a second connection with the key-device. The access control system may be further adapted to determine an intent of the user to access the asset. The access control system may use location data derived from the second connection to determine the intent of the user. The access control system may be further adapted to provide the credential to an access controller, based on identifying an intent of the user to access the asset.

Abstract: The present disclosure provides efficient communication techniques for transmission of model updates within a machine learning framework, such as, for example, a federated learning framework in which a high-quality centralized model is trained on training data distributed overt a large number of clients each with unreliable network connections and low computational power. In an example federated learning setting, in each of a plurality of rounds, each client independently updates the model based on its local data and communicates the updated model back to the server, where all the client-side updates are used to update a global model. The present disclosure provides systems and methods that reduce communication costs. In particular, the present disclosure provides at least: structured update approaches in which the model update is restricted to be small and sketched update approaches in which the model update is compressed before sending to the server.

Abstract: The disclosed technology includes systems and methods for determining secondary authentication of a user's log-in attempts by comparing received behavioral biometric data and/or received scenario-specific data to saved behavioral biometric data and/or saved scenario-specific data, respectively. Responsive to determining that the received behavioral biometric data and/or received scenario-specific data is above a predetermined threshold of similarity with respect to the saved behavioral biometric data and/or saved scenario-specific data, respectively, the systems and methods can determine that the corresponding log-in attempt is secondarily authenticated. of a user device via behavioral biometric data. Responsive to determining that the level of similarity is not above the predetermined threshold, the systems and methods can initiate a secondary authentication method and can associate the received behavioral biometric data with a second user model.

Abstract: Disclosed herein are system, method, and computer program product embodiments for associating a gesture to a website action. In an embodiment, an application receives a user instruction to associate a website action with a user gesture such that the website action occurs upon receipt of the user gesture and the user gesture relates to user input on a user device's display. Thereafter, based on the user instruction, the application creates and sends an interaction request to link the user gesture to the website action. The application then receives an acceptance message from the first website that indicates that the user gesture has been successfully linked to the website action.

Abstract: A sensory eyewear system for a mixed reality device can facilitate user's interactions with the other people or with the environment. As one example, the sensory eyewear system can recognize and interpret a sign language, and present the translated information to a user of the mixed reality device. The wearable system can also recognize text in the user's environment, modify the text (e.g., by changing the content or display characteristics of the text), and render the modified text to occlude the original text.

Abstract: The present disclosure generally relates to a new computer input and tracking device, and method of using, more particularly, a new type of digital pen which tracks user hand movements to generate series of point coordinates that represent a drawing or hand writing. Unlike prior digital pens such as the Apple Pencil™ or the Microsoft Surface Pen™, the new system does not require users to write on a touch-sensitive surface. Users can write on any surface such as a notebook, a table, a board, or even in mid air. Users can draw two-dimensional or three-dimensional drawings. The new method utilizes a pen marked with one or more groups of distinct tracking marks or tracking patterns and a camera to track the pen in real-time. A computer running a 3D algorithm processes the camera images, detects and distinguishes the tracking marks, and uses the tracking marks to calculate the positions of the tip of the pen in three-dimensional space.

Abstract: In one embodiment, a method includes receiving a user request from a first user from a client system associated with a first user, wherein the user request comprise a gesture-input from the first user and a speech-input from the first user, determining an intent corresponding to the user request based on the gesture-input by a personalized gesture-classification model associated with the first user, executing one or more tasks based on the determined intent and the speech-input, and sending instructions for presenting execution results of the one or more tasks to the client system responsive the user request.

Abstract: A computing device is disclosed which includes a processor and non-transient memory operably connected to the processor. The non-transient memory includes instructions that, when executed by the processor cause the processor to extract a plurality of sub-strings from a character string, analyze each sub-string for compliance with each of several field definitions, where each of the field definitions corresponds to a field in a digital form, and populate some of the fields in the digital form based on the analysis of each sub-string for compliance with the field definitions.

Abstract: Systems and methods for performing OCR of an image depicting text symbols and imaging a document having a plurality of planar regions are disclosed. An example method comprises: receiving a first image of a document having a plurality of planar regions and one or more second images of the document; identifying a plurality of coordinate transformations corresponding to each of the planar regions of the first image of the document; identifying, using the plurality of coordinate transformations, a cluster of symbol sequences of the text in the first image and in the one or more second images; and producing a resulting OCR text comprising a median symbol sequence for the cluster of symbol sequences.

Abstract: An image processing apparatus that enables easy setting of metadata of image data. The image processing apparatus obtains image data associated with a selected work. A key candidate is identified from t image data based on one or more key types defined according to the selected work. A value candidate corresponding to the identified key candidate is identified based on a value type rule and a value search area rule which are defined for each of the one or more key types, and the identified value candidate is set as the metadata of the image data.

Abstract: A computer-implemented method for generating feedback based on a handwritten text, comprises the steps of initializing a writing instrument to be used in a writing operation comprising a handwritten text and capturing and processing the handwritten text to generate digital text data. The method further comprises the steps of identifying at least one handwritten text attribute associated with the digital text data, comparing the at least one handwritten text attribute with predefined textual feature attributes, and generating a textual feature based on the compared at least one handwritten text attribute and predefined textual feature attributes. In addition, the method comprises the steps of modifying the digital text data using the textual feature and generating feedback to a user based on the modified digital text data.

Abstract: The disclosed technology relates to an inspection apparatus that includes a stage configured to retain a specimen for inspection, an imaging device having a field of view encompassing at least a portion of the stage to view a specimen retained on the stage, and a plurality of lights disposed on a moveable platform. The inspection apparatus can further include a control module coupled to the imaging device, each of the lights and the moveable platform. The control module is configured to perform operations including: receiving image data from the imaging device, where the image data indicates an illumination landscape of light incident on the specimen; and automatically modifying, based on the image data, an elevation of the moveable platform or an intensity of one or more of the lights to adjust the illumination landscape. Methods and machine-readable media are also contemplated.

Abstract: Provided are a device control method and apparatus. The method is applied to a server, and includes: receiving user voice instruction information, wherein the user voice instruction information is sent by a voice acquisition device after acquiring a user voice instruction, and the user voice instruction information indicates to-be-processed information and an information processing mode; determining, from a device set according to device information of devices in the device set, a target device capable of processing the to-be-processed information in the information processing mode, wherein the device set comprises the voice acquisition device, and all devices in the device set are bound to a same login account for logging into the server; and controlling the target device to process the to-be-processed information in the information processing mode.

Abstract: A data processing system for performing a semantic analysis of digital ink stroke data implements obtaining the digital ink stroke data representing handwritten text, drawings, or both; analyzing the digital ink stroke data to extract path signature feature information from the digital ink stroke data; analyzing the path signature feature information using a convolutional neural network (CNN) trained to perform a pixel-level sematic analysis of the digital ink stroke data and to output a pixel segmentation map with semantic prediction information for each pixel of digital ink stroke data; analyzing the pixel segmentation map to generate stroke-level semantic information using a pixel-to-stroke conversion model; and processing the digital ink stroke data based on the stroke-level semantic information.

Abstract: Techniques for candidate evaluation and filtering are provided. Enrollment criteria for a clinical trial are received, where the enrollment criteria include a plurality of conditions. A plurality of cost vectors is constructed for the plurality of conditions. A set of values for one or more of the plurality of conditions is determined for a candidate, where the set of values does not include a value for at least a first condition of the plurality of conditions. A utilized cost is generated for the candidate, based on the first set of values and the plurality of cost vectors. The candidate is then ranked based on the utilized cost.

Abstract: A handwritten data capture method creates handwritten data including a plurality of pieces of stroke data that is based on writing performed on each page of a paper medium having a plurality of pages. The handwritten data capture method includes: acquiring the plurality of pieces of stroke data created based on the writing sequenced in a writing order; displaying the pieces of stroke data together on a display device; accepting an input of a break position of the pieces of stroke data; identifying a continuous portion of the pieces of stroke data based on the break position and the writing order; updating the display device to display the identified continuous portion of the pieces of stroke data in the writing order; and repeating the accepting, the identifying, and the updating until a given operation is received.

Abstract: A computer model to identify a type of physical card is trained using simulated card images. The physical card may exist with various subtypes, some of which may not exist or be unavailable when the model is trained. To more robustly identify these subtypes, the training data set for the computer model includes simulated card images that are generated for the card type. The simulated card images are generated based on a semi-randomized background that varies in appearance, onto which an identifying marking of the card type is superimposed, such that the training data for the computer model includes additional randomized sample card images and ensure the model is robust to further variations in subtypes.

Abstract: A device includes a touch-sensitive display, one or more processors, and memory storing one or more programs including instructions for receiving data from an external device representing user input received over a duration of time at the external device. The programs may include instructions for determining whether the electronic device is actively executing an application for playback. The programs may further include instructions for in accordance with a determination that the electronic device is not actively executing an application for playback: displaying an indication of the receiving of the data; and displaying an affordance, wherein the affordance when selected launches the application for playback and causes the electronic device to playback the received data according to the duration of time of the user input.

Abstract: According to one aspect of the invention, health insurance claim data for a first group of individuals is obtained to generate a training corpus, including a training set of claim data and a holdout set of claim data. The first group of individuals represents enrollees of one or more first health insurance plans and the health insurance claim data represents historic insurance claim information for each individual in the first group. A Bayesian belief network (BBN) model is created by training a BBN network based on the training set of claim data using predetermined machine learning algorithms. The BBN model is validated using the holdout set of claim data. The BBN model, when having been successfully validated, is configured to identify at least one of individuals with risk for a disorder and individuals with risk who are most likely to benefit from intervention and treatment for the disorder.

Abstract: An example electronic system is described in which an imaging device includes a lens and an image sensor. The imaging device is aligned with an optical target. The optical target includes a text character of a defined text size. An image capturer activates the imaging device to capture an electronic image of the optical target. The electronic image includes the text character of the optical target. An optical recognizer generates an optical recognition result for the character based on the captured electronic image. A sharpness detector compares the optical recognition result with a true value of the text character included in the optical target. Based on the comparison, a designated or defined text size is selected as a designated resolution. The designated resolution is then associable with the imaging device, the optical target, the electronic image, or a component thereof.