Abstract: Examples of automatically generating natural language pipelines to process an input to generate tags, semantic or syntactic, are described. In an example, on receiving a request to process input data to generate tags, a dependency graph, based on identified dependees and further dependees may be created to satisfy the request, the dependency graph including natural language operations arranged in order of their dependencies on each other. Based on the dependency graph, a pipeline for the tags may be automatically generated, which includes a series of natural language operations such that the operations for dependee tags are processed before any of their associated depender tags.

Abstract: The present invention allows text analysis and routing of an outgoing message. The system intercepts outgoing messages for analysis by a TAS software module. The module assigns an analytical score to the message, then compares the score to a threshold. If the score is below the threshold, the message is transmitted to its ultimate destination. If not, the message may be routed for correction by the message's composer or quality assurance staff. After such correction, the message new analytical score is generated and compared, and, if necessary, the process repeats again.

Abstract: An electronic apparatus is disclosed. The electronic apparatus includes a display, a storage in which keyword information by product specification is stored, and a processor configured to obtain user feedback on the product by crawling a website, identify positive feedback or negative feedback among the user feedback corresponding to the keyword information by specification by performing natural language processing (NLP) to which at least two different algorithms are applied, and display a result of the identification through the display.

Abstract: Implementations of the subject matter described herein provide a solution for generating a text from the structured data. In this solution, the structured data is converted into its representation, where the structured data comprises a plurality of cells, and the representation of the structured data comprises plurality of representations of the plurality of cells. A natural language sentence associated with the structured data may be determined based on the representation of the structured data, thereby implementing the function of converting the structured data into a text.

Abstract: The present invention relates to computer-based clinical decision support tools including, computer-implemented methods, computer systems, and computer program products for clinical decision support. These tools assist the clinician in identifying epilepsy patients who are candidates for surgery and utilize a combination of natural language processing, corpus linguistics, and machine learning techniques.

Abstract: A translation method includes: selecting a source word from a source sentence; generating mapping information including location information of the selected source word mapped to the selected source word in the source sentence; and correcting a target word, which is generated by translating the source sentence, based on location information of a feature value of the target word and the mapping information.

Abstract: Techniques for generating natural language text with a natural language generation (NLG) system using a plurality of semantic objects including a first semantic object. The techniques include: obtaining a first specification of the first semantic object, the first specification specifying a first set of one or more data variables, first attributes, a first vocabulary, and a first document structure configuration; obtaining, from at least one data store, first data related to the first set of data variables; determining values of at least some of the first set of data variables using the first data; generating the natural language text including first natural language text, using the first specification, the values of at least some of the first set of data variables; and outputting the generated natural language text.

Abstract: This application relates to computing circuitry (200), and in particular to analogue computing circuitry suitable for neuromorphic computing. An analogue computation unit (210) for processing data is supplied with a first voltage (VCOMP) from a voltage regulator (220) which is operable in a sequence of phases to cyclically regulate the first voltage. A controller (230) is configured to control operation of the voltage regulator and/or the analogue computation unit, such that the analogue computation unit processes data during a plurality of compute periods that avoid times at which the voltage regulator undergoes a phase transition which is one of a predefined set of phase transitions between defined phases in said sequence of phases. This avoids performing computation operations during a phase transition of the voltage regulator that could result in a transient or disturbance in the first voltage, which could adversely affect the computing.

Abstract: In accordance with a first aspect of the present disclosure, a transponder is provided, comprising: a field strength range determination unit configured to determine a field strength range of a radio frequency (RF) field generated by an external reader device; a controller configured to delay processing of a command by the transponder in dependence on the field strength range determined by the field strength range determination unit. In accordance with further aspects of the present disclosure, a corresponding method of operating a transponder is conceived, and a corresponding computer program is provided.

Abstract: Methods, systems, and apparatuses are provided using RFID devices to assist in detecting retail product label removal. For example, a system includes a product identifier including a base substrate, a first RFID tag device, a second RFID tag device, a metallic substrate, a first attachment mechanism, and a second attachment mechanism. By one approach, the first attachment mechanism is configured to fail with an application of a lower separation force than the second attachment mechanism, such that upon an action causing a separation force to separate the base substrate from a first retail product will cause the first attachment mechanism to fail such that the base substrate will be removed from the metallic substrate and the first retail product. In some embodiments, upon this separation and removal, the second RFID tag device will then be readable by the RFID tag reader.

Abstract: An operation of calibrating the object using a reference reader is performed, the calibration operation including an operation of placing the reference reader at various distances away from the object that correspond to various values of a parameter within the object that is representative of the intensity of the signal received by the object, and, for each distance, an operation of determining an internal phase-shift compensation in the object with respect to a nominal internal phase shift, making it possible to obtain a load modulation amplitude that is higher, in terms of absolute value, than a threshold, and an operation of storing a lookup table of the various values of the parameter and the corresponding internal phase-shift compensations.

Abstract: A wireless tag system including a tag signal antenna configured to receive a tag signal transmitted from a wireless transmission tag; and a communication area shaping antenna configured to transmit a reception area shaping signal for narrowing an area in which the tag signal antenna can communicate with the wireless transmission tag.

Abstract: A radio frequency device utilizing an antenna having a single antenna structure resonant on multiple resonant frequency ranges. The antenna can be configured to operate within multiple frequency ranges for communication according to respective protocols associated with the respective frequency ranges.

Abstract: The present disclosure provides a method for processing data, a method and an apparatus for detecting an object. The apparatus comprises: a first sensor provided in a first region; a second sensor provided in a second region; a first processing unit configured to classify tags of target objects collected by the second sensor, to obtain a first region tag cluster and a second region tag cluster, wherein the first region tag cluster comprises tags of target objects in the first region, and the second region tag cluster comprises tags of target objects in the second region, wherein the first sensor is configured to detect the tags of the target objects in the first region tag cluster based on a classification result of the first processing unit.

Abstract: A method includes: storing, in a first database, first data regarding a life cycle of a product made using a manufacturing process; scanning an encoded image on a physical object to obtain at least one parameter associated with the product; querying, using the obtained at least one parameter, the first database to obtain the first data; generating a communication that includes the first data; and sending, to a server over a network, the communication, wherein the server is configured to update a second database based on the first data.

Abstract: A method includes: scanning an encoded image on a physical object to obtain parameters associated with a product made using a manufacturing process; storing, in a database and based on the obtained parameters, data regarding materials used in the manufacturing process to make the product; sending, based on the stored data, a communication to a computing device requesting data regarding a first material; receiving a communication including the requested data; and in response to receiving the communication, updating the stored data regarding the first material to provide updated data regarding the first material that is stored in the database.

Abstract: An image recognition method of a terminal is provided. An image sensor is controlled to capture an image stream in response to receiving an image recognition trigger. A first image is extracted from the image stream. A determination is made as to whether an image type of the first image is one of an object image and a code image. One of a plurality of recognition processes is performed on a second image in the image stream according to the determined image type.

Abstract: Provided is a fingerprint recognition circuit, including a resetting sub-circuit, a fingerprint sensing sub-circuit, a signal acquiring sub-circuit, and a driving sub-circuit, the resetting sub-circuit is connected to the reading node, the resetting port, a first port for resetting the reading node; the fingerprint sensing sub-circuit is connected to the reading node for acquiring fingerprint information, converting it into a detection signal to output to the reading node; the signal acquiring sub-circuit is connected to the reading node, the driving sub-circuit and a power port to output a signal of the reading node to the driving sub-circuit; the driving sub-circuit is connected to a reading port, the signal acquiring sub-circuit, an output port and a second port, the signal output by the signal acquiring sub-circuit through the reading port in a fingerprint recognition stage, outputs the signal of the reading port to the output port in a display stage.

Abstract: A sensor, a manufacturing method thereof, a panel, and a recognition device are provided. The sensor comprises a substrate, a first electrode layer on the substrate, a second electrode layer on a side of the first electrode layer away from the substrate, and a piezoelectric layer between the first electrode layer and the second electrode layer. An orthographic projection of a top surface of the piezoelectric layer facing away from the first electrode layer on the substrate covers an orthographic projection of a bottom surface thereof facing the first electrode layer on the substrate.

Abstract: A smart card with a fingerprint sensing system, includes a controller and a fingerprint sensing device. When the fingerprint sensing device senses a fingerprint to generate a fingerprint frame data, the controller enters a sleep mode, and when the controller reads the fingerprint frame data, the fingerprint sensing device stops sensing the fingerprint. Since operations of sensing the fingerprint and reading the fingerprint frame data do not occur at the same time, the high current condition can be avoided so as to decrease power consumption.

Abstract: A piezoelectric panel speaker and an electronic apparatus including the same are disclosed. The piezoelectric panel speaker may include a piezoelectric panel including at least one hole and configured to vibrate, and a fingerprint sensor accommodated into the one hole and configured to sense biometric information.

Abstract: A display module and a mobile terminal are provided. The display module includes: a screen cover plate, a fingerprint sensitive component, and a display component; the fingerprint sensitive component is arranged between the screen cover plate and the display component; the fingerprint sensitive component includes: an optical fingerprint sensitive layer made of transparent conductive material, a sensitive surface thereof having multiple pixels; the sensitive surface is attached to a surface of the screen cover plate, a attaching surface of the optical fingerprint sensitive layer is attached to a display surface of the display component; when the display component is on, the light emitted passes through the fingerprint sensitive component towards the screen cover plate, and is reflected to the sensitive surface by a finger pressed on the screen cover plate, the fingerprint sensitive component derives a pattern of a fingerprint from the amount of light received by pixels.

Abstract: A screen module includes an external screen, a first light blocking layer, a substrate, and a reflection layer that are disposed from outside to inside. An imaging unit array is disposed on the substrate, the imaging unit array includes a plurality of imaging units), and a photosensitive surface of the imaging unit is opposite to the reflection layer. A first aperture array is disposed on the first light blocking layer, the first aperture array includes a plurality of first apertures, and the first aperture is used to allow light reflected by an object outside the screen to the reflection layer to pass through. The reflection layer is configured to reflect, to the imaging unit, the light passing through the first aperture. Thus, user convenience can be improved.

Abstract: A fingerprint identification module and an electronic device are provided. The electronic device includes a screen assembly provided with a glass substrate. The fingerprint identification module includes: a color filter coating applied onto the glass substrate; an optical collimator arranged at a side of the color filter coating away from the glass substrate; and an image sensor arranged at a side of the optical collimator away from the color filter coating.

Abstract: The invention concerns a method and a biometric acquisition device for biometric vascular recognition and/or identification. The method comprising a step of capturing a plurality of veins images (116, 117, 118) of supposed subcutaneous veins (21) of a same inspecting portion (20) of a presented entity (2) from various converging orientations (113, 114, 115). The method further comprises a step of determine if said entity is a spoof based on estimated likelihood that said supposed subcutaneous veins within said plurality of veins images (116, 117, 118) are likely projections of solid veins (120).

Abstract: It is provided a biometric authentication system, which is configured to execute authentication by using registered biometric information, the biometric authentication system comprising: a light source unit configured to irradiate a living body with light; an image pickup unit configured to photograph a vessel image with light radiated from the light source unit and transmitted through the living body; a control unit configured to generate authentication biometric information from the vessel image photographed by the image pickup unit; a category selection unit configured to select a category that corresponds to the authentication biometric information, based on supplementary information including information that has been obtained about a position and posture of the living body at timing of photographing the vessel image; and an authentication unit configured to execute authentication processing by comparing registered biometric information of the selected category and the authentication biometric informatio

Abstract: The present disclosure relates to a device for contactless optical imaging of features of a hand, wherein the device comprises an illumination arrangement for illuminating a measuring site with light of substantially a first wavelength and with light of at least substantially a second wavelength. The device further comprising a camera comprising a detector and imaging optics configured for imaging the measuring site on the detector. Within the measuring site a region of depth of field of the imaging optics with respect to the first wavelength overlaps with a region of depth of field of the imaging optics with respect to the second wavelength.

Abstract: A total internal reflection based imaging system may include a light transmitting member having an imaging surface. A pressure sensitive membrane may be arranged on the imaging surface. The pressure sensitive membrane may include a top surface, a bottom surface, and an elastic deformable film forming at least a portion of the top surface. The imaging system may include a textured surface disposed between the pressure sensitive membrane and the imaging surface. An application of pressure on the top surface may deform the deformable film to reduce a distance between the deformable film and the imaging surface. A light source may be configured to emit a light towards the imaging surface such that reduced total internal reflection of the light occurs where the bottom surface of the pressure sensitive membrane contacts the imaging surface. A sensor may be configured to capture the light reflected from the imaging surface.

Abstract: The disclosure facilitates fingerprint recognition, user authentication, and prevention of loss of control of personal information and identity theft. The disclosure also facilitates identifying spoofed fingerprint authentication attempts, and/or securing user touch sensitive devices against spoofed fingerprint authentication attempts.

Abstract: In one aspect, a method includes receiving query fingerprint data representing content received by a content-presentation device. The method also includes identifying a geographic area of the content-presentation device. The method also includes using at least the identified geographic area as a basis to select, from among a plurality of reference fingerprint data sets, a reference fingerprint data set that corresponds with the identified geographic area. The method also includes detecting a match between the query fingerprint data and at least a portion of reference fingerprint data in the selected reference fingerprint data set. The method also includes responsive to detecting the match, performing an action.

Abstract: In one aspect, a method includes identifying a geographic area of a content-presentation device. The method also includes using at least the identified geographic area as a basis to select, from among a plurality of reference fingerprint data sets, a reference fingerprint data set that corresponds with the identified geographic area. The method also includes transmitting to the content-presentation device, the selected reference fingerprint data set that corresponds with the identified geographic area to facilitate the content-presentation device detecting a match between query fingerprint data representing content received by the content-presentation device and at least a portion of reference fingerprint data in the transmitted reference fingerprint data set.

Abstract: In one aspect, a method includes receiving query fingerprint data representing content received by a content-presentation device, identifying a geographic area of the content-presentation device, using at least the identified geographic area as a basis to select, from among a plurality of reference fingerprint data sets, a first reference fingerprint data set that corresponds with the identified geographic area, detecting that the query fingerprint data does not match any reference fingerprint data in the selected first reference fingerprint data set, responsive to the detecting, selecting, from among the plurality of reference fingerprint data sets, a second reference fingerprint data set that does not correspond with the identified geographic area, detecting a match between the query fingerprint data and at least a portion of reference fingerprint data in the selected second reference fingerprint data set, and responsive to detecting the match, performing an action.

Abstract: In one aspect, a method includes receiving a first portion of query fingerprint data representing content transmitted by a content-distribution system. The method also includes detecting a match between the first portion of the query fingerprint data and a first portion of reference fingerprint data representing a modifiable content-segment. The method also includes after detecting the match: (i) receiving a second portion of the query fingerprint data, wherein the second portion of the query fingerprint data is different from the first portion of the query fingerprint data; and (ii) detecting a mismatch between the second portion of the query fingerprint data and a second portion of the reference fingerprint data representing the modifiable content-segment, wherein the second portion of the reference fingerprint data is different from the first portion of the reference fingerprint data. The method also includes responsive to detecting the mismatch, performing an action.

Abstract: In one aspect, a method includes receiving query fingerprint data representing content received by a content-presentation device. The method also includes comparing at least a first portion of the query fingerprint data with at least one first reference fingerprint data set, where each first reference fingerprint data set corresponds with a respective channel. The method also includes determining that the query fingerprint data does not match any of the at least one first reference fingerprint data sets. The method also includes responsive to the determining, comparing at least a second portion of the query fingerprint data with second reference fingerprint data representing a modifiable content-segment. The method also includes detecting a match between at least the second portion of the query fingerprint data and the second reference fingerprint data.

Abstract: Systems and methods are disclosed for capturing multiple sequences of views of a three-dimensional object using a plurality of virtual cameras. The systems and methods generate aligned sequences from the multiple sequences based on an arrangement of the plurality of virtual cameras in relation to the three-dimensional object. Using a convolutional network, the systems and methods classify the three-dimensional object based on the aligned sequences and identify the three-dimensional object using the classification.

Abstract: Systems and methods are provided for control of a personal computing device based on user face detection and recognition techniques.

Abstract: A method for training a model, the method including: defining a primary model for identifying a class of input data based on a first characteristic of the input data; defining a secondary model for detecting a change to a second characteristic between multiple input data captured at different times; defining a forward link from an output of an intermediate layer of the secondary model to an input of an intermediate layer of the primary model; and training the primary model and the secondary model in parallel based on a training set of input data.

Abstract: A display device capable of automatically adjusting displayed image comprises a display device, a camera assembly, an image recognition device and a signal processor. The display device including a shell and a display panel partially exposed from the shell, wherein the display panel faces a first direction. The camera assembly obtains a first image with a first visual angle and obtain a second image with a second visual angle. The image recognition device generates a first instruction when the first image meets a first condition and generates a second instruction when the second image meets a second condition. The signal processor adjusts the display signal to conceal the displayed image according to the first instruction and to adjust the display signal to generate a reminder message on the displayed image according to the second instruction.

Abstract: Methods, apparatuses, and devices, including computer programs encoded on computer storage media, for recognizing an unauthorized behavior are provided. One of the methods includes: obtaining, through machine vision, body movement pattern data of a user; obtaining feature data of an object; comparing the body movement pattern data with a preset body movement pattern; and determining that the user's behavior is unauthorized in response to the body movement pattern data matching the preset body movement pattern and that: a distance between the user's body and the object is within a distance threshold over a preset length of time, the attribute category of the object is a preset category, and the external surface image does not match a default external surface image of the object. The feature data may include: position data of the object based on a radio frequency identification tag on the object, attribute category data of the object, and external surface image of the object.

Abstract: A processing device provides a plurality of motion capture sensors affixed to different portions of a subject and establishes, without using a magnetometer, a common reference frame for the plurality of motion capture sensors. The processing device further receives, from the plurality of motion capture sensors, 3D motion capture data corresponding to a movement of the subject and interprets, using the common reference frame, the 3D motion capture data from the plurality of motion capture sensors to represent the movement of the subject.

Abstract: The technology disclosed can provide methods and systems for identifying users while capturing motion and/or determining the path of a portion of the user with one or more optical, acoustic or vibrational sensors. Implementations can enable use of security aware devices, e.g., automated teller machines (ATMs), cash registers and banking machines, other secure vending or service machines, security screening apparatus, secure terminals, airplanes, automobiles and so forth that comprise sensors and processors employing optical, audio or vibrational detection mechanisms suitable for providing gesture detection, personal identification, user recognition, authorization of control inputs, and other machine control and/or machine communications applications. A virtual experience can be provided to the user in some implementations by the addition of haptic, audio and/or other sensory information projectors.

Abstract: This application discloses a human attribute recognition method performed at a computing device. The method includes: determining a human body region image in a surveillance image; inputting the human body region image into a multi-attribute convolutional neural network model, to obtain, for each of a plurality of human attributes in the human body region image, a probability that the human attribute corresponds to a respective predefined attribute value, the multi-attribute convolutional neural network model being obtained by performing multi-attribute recognition and training on a set of pre-obtained training images by using a multi-attribute convolutional neural network; determining, for each of the plurality of human attributes in the human body region image, the attribute value of the human attribute based on the corresponding probability; and displaying the attribute values of the plurality of human attributes next to the human body region image.

Abstract: The invention relates to a method in a computing device for hand-drawing elements, comprising: detecting input elements hand-drawn on an input surface; displaying the input elements in digital ink on a display device; classifying input digital ink as text or non-text and predefining blocks of input elements; selecting one or more input element according to a first selection mode triggered by a first gesture or according to a second selection mode triggered by a second gesture to select input elements within a selection area. Once selection is made, editing may be performed on the selected input elements in a different manner depending of which of the first and second selection mode is used.

Abstract: A technique in the present disclosure makes it possible to accurately obtain a value selected by a user with respect to a selection-type item for which a legend is prepared in a situation where a value entered in a document is extracted from a scanned image of the document. An item name is extracted from a document image, input information input by a user is extracted from the document image, and a legend is extracted from the document image. Additionally, in a case where the input information is unsuitable as a value corresponding to the item name, the value corresponding to the item name is obtained based on the legend and the input information.

Abstract: A machine receives, for a given target in a given image, a plurality of annotations, each annotation indicating a range of pixels corresponding to the given target. The machine computes a number of pixels in an intersection of the plurality of annotations. The machine computes an average pixels on target (APOT) for the given target by computing, for each annotation, a number of pixels that corresponds to the given target and taking a mean of those numbers. The machine computes a precision value of the plurality of annotations as the number of pixels in the intersection divided by the APOT. The machine provides an output representing the precision value.

Abstract: The present disclosure describes systems and methods for iris liveness determination. A sensor can acquire a first image of an iris with pupillary constriction, and a second image of the iris without the pupillary constriction. A processor can extract an iris portion of the first image into a first iris image, and an iris portion of the second image into a second iris image. The processor can normalize the first iris image and the second iris image. The normalized first iris image can have same dimensions as that of the normalized second iris image, in pixels. The processor can compute a minimum average difference between values of specific pixels of the normalized first iris image and values of corresponding pixels of the normalized second iris image. The specific pixels can correspond to an innermost annular portion of the iris. The processor can determine that the iris is a live iris, responsive to determining that the computed minimum average difference is below a defined threshold value.

Abstract: Methods, devices, and systems enable an originating entity to use a digital fingerprint, alone or in conjunction with other data related to the physical object, to characterize the physical object so that the physical object may be confirmed as authentic when it is returned to the originating entity or another entity. A determination that expected changes to the object occurred, and/or that unexpected changes did not occur, while the physical object was outside the control of the originating entity can be made. The originating entity may induct the object into a repository before the physical object leaves the originating entity's control, and the originating entity may authenticate the physical object upon return by a process that queries the repository for matching records.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for identifying traffic control features based on telemetry patterns within digital image representations of vehicle telemetry information. The disclosed systems can generate a digital image representation based on collected telemetry information to represent the frequency of different speed-location combinations for transportation vehicles passing through a traffic area. The disclosed systems can also apply a convolutional neural network to analyze the digital image representation and generate a predicted classification of a type of traffic control feature that corresponds to the digital image representation of vehicle telemetry information. The disclosed systems further train the convolutional neural network to determine traffic control features based on training data.

Abstract: A system for identifying and determining predictions of an entity of interest (EOT) includes a processor configured to receive real-time FMV data of an area of interest (AOI); a memory operatively coupled to the processor and storing a machine learning algorithm for identifying the EOT in the AOI; a database for use in classifying the EOT and determining predictions associated with the EOT; and a translator operatively coupled to the processor and configured to cause the processor to operationally communicate with the machine learning algorithm. The processor may be further configured to correlate a stored video data with the current video data and cause the database to store the correlated video data with its associated EOT. The processor may be configured to determine predictions associated with the EOT by identifying trends in the correlated video data.

Abstract: The present disclosure relates to methods and systems for obtaining image information of an organism including a set of optical data; calculating a growth index based on the set of optical data; and calculating an anticipated harvest time based on the growth index, where the image information includes at least one of: (a) visible image data obtained from an image sensor and non-visible image data obtained from the image sensor, and (b) a set of image data from at least two image capture devices, where the at least two image capture devices capture the set of image data from at least two positions.