Abstract: An imagery processing system determines alternative pixel color values for pixels of captured imagery where the alternative pixel color values are obtained from alternative sources. A main imagery capture device, such as a camera, captures main imagery such as still images and/or video sequences, of a live action scene. Alternative devices capture imagery of the live action scene, in some spectra and form, and that alternative imagery is processed to provide user-selectable alternatives for pixel ranges from the main imagery.

Abstract: Insects can be localized and classified using a predictive model. To begin, image data is obtained that corresponds to the insects. Using a predictive model, samples of the image data are evaluated to determine whether the image portions include an insect and, if so, into what category the insect should be classified (e.g., male/female, species A/species B, etc.).

Abstract: A multi-sensor edge computing system can have at least a sensor assembly connected to an edge computing device and a downstream host. The sensor assembly may have a first sensor and a second sensor with the respective sensors being different. The edge computing device can be configured to identify a false reading of the first sensor in response to data captured by the second sensor.

Abstract: Embodiments of the present invention are directed towards generating a captured font from an image of a target font. Character glyphs of the target font can be detected from the image. A character glyph can be selected from the detected character glyphs. A character mask can be generated for the selected character glyph. The character mask can be used to identify a similar font. A character from the similar font corresponding to the selected character glyph can be transformed to match the character mask. This transformed corresponding character can be presented and used to generate a captured font. In addition, a texture from the image can be applied to the captured font based on the transformed corresponding character.

Abstract: An optical safety scanner system comprises a first illumination source for detecting presence and distances of people or other objects within a hazardous industrial area based on triangulation, and a second illumination source that verifies accurate and reliable detection by the first illumination source. The first illumination source can project LED or laser light for triangulation of objects, and the second illumination source can project a wide beam of light for detection of other intrusive objects that may be blocking the scanner system's camera and preventing accurate triangulation of people or vehicles. If the image frame generated based on the second light identifies presence of an object that is not detected by the triangulation analysis of the laser light, the safety scanner system assumes that an object is obstructing the safety scanner system's camera, and performs a suitable safety action.

Abstract: Systems and methods of pushing content to secondary connected devices include pushing targeted content such as interactive advertisements, banners, games or application to secondary connected devices in a household. The targeted content may reflect user preferences associated with the secondary connected devices, including user behaviour and previous interaction with various forms of content viewed on the secondary connected devices. The targeted content may be either locally cached or retrieved from an advertisement server at the time of pushing to the secondary connected devices.

Abstract: A control system for operation of an industrial machine includes a processor and a tangible, non-transitory, computer-readable memory communicating with the processor. The tangible, non-transitory computer-readable memory includes instructions that, in response to execution by the processor, cause the processor to perform operations including: receiving image data from an imaging device that monitors an image zone around the industrial machine, and analyzing the image data. The processor further performs operations including determining, based upon the analyzing, that the control system is functional, determining, based upon the analyzing, that the image data includes at least one of a predefined color, a predefined pattern, and a predefined shape, and transmitting a proximity signal to at least one relay module coupled between the processor and the industrial machine to halt operation of the industrial machine.

Abstract: This disclosure proposes an image recognition method and apparatus. The method comprises: obtaining an image to be recognized; inputting the image into a first preset block of a residual neural network, to obtain a first image feature corresponding to the image; inputting the first image feature into a second preset block of the residual neural network, an attention model, a first convolution layer, and a pooling layer arranged in this order, to obtain first label information corresponding to the image, which has a label correlation representation; inputting the first image feature into a second convolution layer and a bidirectional neural network arranged in this order, to obtain second label information corresponding to the image, which has a label correlation representation; and determining label information corresponding to the image in accordance with the first label information and the second label information.

Abstract: Detection of typed and/or pasted text, caret tracking, and active element detection for a computing system are disclosed. The location on the screen associated with a computing system where the user has been typing or pasting text, potentially including hot keys or other keys that do not cause visible characters to appear, can be identified and the physical position on the screen where typing or pasting occurred can be provided based on the current resolution of where one or more characters appeared, where the cursor was blinking, or both. This can be done by identifying locations on the screen where changes occurred and performing text recognition and/or caret detection on these locations. The physical position of the typing or pasting activity allows determination of an active or focused element in an application displayed on the screen.

Abstract: A multiresolution optical code can be encoded. A first set of information and a second set of information to encode in an optical code is received. An optical code that encodes the first set of information in a plurality of dots is generated. Each dot of the plurality of dots is divided into a matrix of a first number of sub-dots by a second number of sub-dots, wherein each of the first number and the second number are integers equal to or greater than three and wherein this dividing creates a set of matrices of sub-dots. The second set of information is encoded in a plurality of the sub-dots of the set of matrices of sub-dots.

Abstract: An image processing device includes a processor; and a memory coupled to the processor, the memory storing a program that, when executed by the processor, causes the image processing device to: obtain first coordinate data indicating a coordinate position indicated by a position indicator from a sensor that detects the coordinate position; obtain first image data to which predetermined additional information is added; and associate the first image data with position data indicating a position on a display screen of a display device, the position corresponding to the first coordinate data.

Abstract: The invention pertains to a system for determining a distance, comprising: a light source for projecting a pattern of discrete spots of laser light towards the object in a sequence of pulses; a detector comprising picture elements, for detecting light representing the pattern as reflected by the object in synchronization with the sequence of pulses; and processing means to calculate the distance to the object as a function of exposure values generated by said picture elements. The picture elements generate exposure values by accumulating a first amount of electrical charge representing a first amount of light reflected during a first time window and a second electrical charge representing a second amount of light reflected during a second time window. The solid-state radiation source emits substantially monochromatic light having a wavelength spread of less than ±20 nm and the detector is equipped with a corresponding narrow bandpass filter.

Abstract: The present invention extends to methods, systems, and computer program products for ingesting streaming signals. Signal ingestion modules sample a frame from a raw streaming signal. A preliminary severity or possible event type is computed from the sampled frame. A deeper inspection request is triggered of the raw streaming signal or of another raw streaming signal. Segments of content from the raw streaming signal or the other raw streaming signal are inspected. An actual severity or actual event type is computed from the inspected content. The actual severity or actual event type can be included in a normalized signal.

Abstract: In one embodiment, an apparatus comprises a communication interface and a processor. The communication interface is to communicate with a plurality of cameras. The processor is to obtain metadata associated with an initial state of an object, wherein the object is captured by a first camera in a first video stream at a first point in time, and wherein the metadata is obtained based on the first video stream. The processor is further to predict, based on the metadata, a future state of the object at a second point in time, and identify a second camera for capturing the object at the second point in time. The processor is further to configure the second camera to capture the object in a second video stream at the second point in time, wherein the second camera is configured to capture the object based on the future state of the object.

Abstract: According to certain aspects of the disclosure, a computer-implemented method may be used for providing a vehicle recommendation based on user gestures. The method may include displaying at least one image of a vehicle to a user and receiving at least one gesture from the user performed on the at least one image of the vehicle. Additionally, the method may include assigning a value to the at least one gesture from the user and determining a feature of the vehicle based on the at least one gesture from the user. Additionally, the method may include receiving gesture information related to the at least one gesture and determining a vehicle preference of the user based on the value, the feature of the vehicle, and the gesture information. Additionally, the method may include identifying at least one available vehicle based on the vehicle preference of the user and displaying the at least one available vehicle to the user.

Abstract: Systems and methods for processing image data representing a document to remove deformations contained in the document are disclosed. A system may include one or more memory devices storing instructions and one or more processors configured to execute the instructions. The instructions may instruct the system to provide, to a machine learning system, a training dataset representing a plurality of documents containing a plurality of training deformations. The instructions may also instruct the system to use the machine learning system to process image data representing a target document containing a target document deformation. The machine learning system may generate restored image data representing the target document with the target document deformation removed. The instructions may further instruct the system to provide the restored image data to at least one of a graphical user interface, an image storage device, or a computer vision system.

Abstract: Systems and methods for processing image data representing a document to remove deformations contained in the document are disclosed. A system may include one or more memory devices storing instructions and one or more processors configured to execute the instructions. The instructions may instruct the system to provide, to a machine learning system, a training dataset representing a plurality of documents containing a plurality of training deformations. The instructions may also instruct the system to use the machine learning system to process image data representing a target document containing a target document deformation. The machine learning system may generate restored image data representing the target document with the target document deformation removed. The instructions may further instruct the system to provide the restored image data to at least one of a graphical user interface, an image storage device, or a computer vision system.

Abstract: A computing system engages in digital image processing of received video frames to generate sport data that indicates a score and/or a time associated with a sport event. The digital image processing includes: (i) identifying a first frame region of the video frames based on the first frame region depicting a scoreboard; (ii) executing a first procedure that analyzes the identified first frame region to detect, within the identified first frame region, second frame region(s) based on the second frame region(s) depicting text of the scoreboard; (iii) in response to detecting the second frame region(s), executing a second procedure to recognize the text in at least one of the second frame region(s); and (iv) based at least on the recognizing of the text, generating the sport data. In response to completing the digital image processing, the computing system then carries out an action based on the generated sport data.

Abstract: The invention proposes a high-voltage direct current cut-off device, comprising: in series, a cut-off device and a current limiter; an accumulation line in parallel with the current limiter, an oscillating circuit, in parallel with the cut-off apparatus, comprising an oscillation control switch and having an inductance wherein the accumulation line includes at least two accumulation capacitors, and in that the oscillation line extends from a branch connection point of the accumulation line situated between the two accumulation capacitors, determining a secondary segment of the accumulation line connected to the main conduction line between the current limiter and the main cut-off apparatus so as to form part of the oscillating circuit.

Abstract: Systems and methods are disclosed for assisting users in assessing costs of transactions. For instance, method may include: determining a cost value of at least one transaction associated with a user; classifying the user into a category, based on consumer interest characteristics of the user and consumer interest characteristics associated with the category; determining a relatable product based on the consumer interest characteristics associated with the category, the relatable product being a product purchased by a plurality of persons classified in the category; determining a relatable cost value, the relatable cost value being a representation of the cost value of the at least one transaction using a quantity of the respective relatable product; and presenting the relatable cost value to the user.

Abstract: Methods, systems, and devices, including computer programs encoded on computer storage media for transferring a robot customer service to a human customer service are provided. One of the methods includes: obtaining conversation characteristics from at least one round of conversations between the robot customer service and a customer; obtaining state characteristics of the customer; inputting the conversation characteristics and the state characteristics into a confidence score evaluation model to obtain a confidence score evaluation value; and when the confidence score evaluation value meets a robot-to-human intervention condition, transferring the customer to the human customer service. The confidence score evaluation model is a machine learning model, comprising a linear sub-model input with the conversation characteristics and a deep neural network sub-model input with the state characteristics.

Abstract: In an embodiment, a method monitors a plurality of data streams passing through a router in the connectivity service provider environment, and for each of the data streams, periodically samples packets at the router. The method further generates a stream signature based at least on the payload of the sampled packets. The method further includes, for each generated stream signature, attaching information to the stream signature. Such information may, for example, include time-stamp information for the stream signature, or an identification of the router. The method may further comprise storing the stream signatures corresponding to the data streams in a database. The stored stream signatures may be compared to determine matching stream signatures. Matching signatures may identify data streams that carry identical or similar content.

Abstract: In accordance with some embodiments, a method is provided. The method includes accessing a predefined numeric sequence at an application processor. The method further includes receiving, from a sensor of the sensor system, a verification sequence having a predetermined quantity of repetitions of the predefined numeric sequence. The method further includes correlating the verification sequence with the predefined numeric sequence. The method further includes counting a quantity of correlations between the predefined numeric sequence and the verification sequence. The method further includes adjusting a parameter of the sensor or the application processor in response to the predetermined quantity of repetitions not equaling the quantity of correlations.

Abstract: Method for detecting the presence of a body part carrying an imprint on an imprint sensor comprising a transparent face on which a body part must be placed, an image sensor, situated opposite the transparent face, able to acquire an image of an imprint, a light source for illuminating a body part placed on the transparent face. The method comprises: switching on the light source; acquiring a multicomponent image with the image sensor, each color component of the multicomponent sensor corresponding to a predefined wavelength range; obtaining, for each color component of said multicomponent image, information representing a signal generated by said image sensor for said color component; comparing said representative items of information with each other and detecting the presence of a body part according to the result of the comparison.

Abstract: There is provided an image processing apparatus including a processor that acquires document image data generated by reading the document and recognizes a character string included in the document image data by character recognition and a storage that saves the document image data, in which the processor compares a folder name of an existing folder in the storage with the character string included in the document image data to select a folder in which at least a part of the folder name matches the character string included in the document image data, as a folder of a save destination of the document image data.

Abstract: A method for recognizing a character includes: obtaining a character; converting the character into a radical based character recognition result, where the radical based character recognition result comprises symbols indicating radicals of the character and a structure of the radicals of the character; and recognizing the character based on the radical based character recognition result.

Abstract: Various methods are using SQL based data extraction for extracting relevant information from images. These are rule based methods of generating SQL-Query from NL, if any new English sentences are to be handled then manual intervention is required. Further becomes difficult for non-technical user. A system and method for extracting relevant from the images using a conversational interface and database querying have been provided. The system eliminates noisy effects, identifying the type of documents and detect various entities for diagrams. Further a schema is designed which allows an easy to understand abstraction of the entities detected by the deep vision models and the relationships between them. Relevant information and fields can then be extracted from the document by writing SQL queries on top of the relationship tables. A natural language based interface is added so that a non-technical user, specifying the queries in natural language, can fetch the information effortlessly.

Abstract: Provided is a screen recording preparation method for evaluating software usability using additional data of a user session carried out by a computing system includes at least the following steps in an initial phase: loading a screen recording including a number of N time-ordered screenshots of the user session from a storage medium and detecting visual features within each of the N screenshots, wherein each of the features is attributed a position within the respective screenshot and a score identifying the feature, and creating a set of metadata containing an identifier of each of the N screenshots and the features detected within each of the N screenshots and setting a threshold similarity value. The method also comprises a cycling phase for treating the metadata. Also, a computing system, a computer program and a computer-readable storage medium perform a method according to an embodiment of the present invention.

Abstract: In some examples, a computer receives event data relating to events of a system, and builds a graph comprising nodes representing respective values of attributes of the events, and edges between the nodes, each respective edge of the edges representing co-occurrence of values of attributes represented by nodes connected by the respective edge. The computer computes edge weights of corresponding edges of the edges, and identifies paths in the graph, where each path of the paths comprises two or more nodes and a corresponding edge or edges. The computer determines an affinity among the values of the attributes based on a shortest path determining process that uses the edge weights for distances of the identified paths, and resolves an anomaly in the system based on the determined affinity.

Abstract: A system includes a computing device that includes a memory configured to store instructions. The system also includes a processor to execute the instructions to perform operations that include receiving data representing an image, the image being represented in the data by a collection of visual elements. Operations also include determining whether to select the image for presentation by one or more entities using a machine learning system, the machine learning system being trained using data representing a plurality of training images and data representing one or more attributes regarding image presentation by the one or more entities.

Abstract: A machine system includes an image processor to transform a raw digital image to a set of drawing objects comprising individual lines, shapes, and text; a block diagram generator to transform the set of drawing objects into a block diagram; and a flow chart generator to transform the set of drawing objects into a flow chart. A client device receives a raw image signal of a print or display graph from a camera and in response processes the raw image to reduce noise, normalize the raw image data, and reduce pixel information. A server system receives the processed image from the client device and in response operates image processor logic to transform the processed image into a format in which image lines and other geometric objects are manipulatable.

Abstract: Described is a method that involves operating an unmanned aerial vehicle (UAV) to begin a flight, where the UAV relies on a navigation system to navigate to a destination. During the flight, the method involves operating a camera to capture images of the UAV's environment, and analyzing the images to detect features in the environment. The method also involves establishing a correlation between features detected in different images, and using location information from the navigation system to localize a feature detected in different images. Further, the method involves generating a flight log that includes the localized feature. Also, the method involves detecting a failure involving the navigation system, and responsively operating the camera to capture a post-failure image. The method also involves identifying one or more features in the post-failure image, and determining a location of the UAV based on a relationship between an identified feature and a localized feature.

Abstract: The present disclosure discloses methods and systems for selective translation of a language of a multi-function device, wherein the language of the multi-function device is a pre-defined language. The method includes receiving a print job from a user along with one or more job attributes, wherein at least one job attribute indicates a local language of the user. Then, the local language is identified from the at least one job attribute. One or more job specific user interfaces are identified. Based on the identified local language of the user, the identified one or more job specific user interfaces are translated in the local language of the user and stored. After this, an input from the user is received. Based on the input, at least one translated job specific user interface is displayed in the local language of the user.

Abstract: The disclosure is directed to systems and methods for image capturing technologies and, more particularly, to a slice scan imaging system and respective processes to achieve high quality images. The method can be implemented in a computing device, which includes: capturing multiple lines of an image in a single slice; capturing multiple slices; stitching together the multiple slices by aligning common features of the images of a previous slice with a successive slice; and blending together the stitched together multiple slices.

Abstract: Provided is a writing program for enabling accurate character recognition, and a character input device equipped with the same. The character input device includes: a storage configured to store a writing program; and an input unit configured to output the writing program to provide a character writing environment, wherein the writing program outputs the following input windows: a character output window for outputting a character input by a user, a first language input window for allowing a character written thereon by the user to be recognized as a first language, and a second language input window for allowing a character written thereon by the user to be recognized as a second language, and wherein the second language input window is distinguishable from the first language window. Accordingly, accurate character recognition may be enabled and thus errors possibly caused during character writing may be reduced.

Abstract: A computer-implemented method includes: receiving, by a computer device, original livestream video content from a livestreaming application on a first mobile device; receiving, by the computer device, a modification command from a second device located in a proximity of the first mobile device; modifying, by the computer device, the original livestream video content based on the modification command to create a modified livestream video content, the modified livestream video content being different from the original livestream video content; and transmitting, by the computer device, the modified livestream video content.

Abstract: An operating apparatus is provided with: a line-of-sight detector configured to detect a line of sight of an occupant of a vehicle; a face direction detector configured to detect a face direction of the occupant; and an estimator configured to estimate an operation intention intended by the face direction on the basis of the detected face direction, on condition that a change in the detected face direction is greater than a change in the detected line of sight by an amount that is greater than or equal to a predetermined amount.

Abstract: An image forming apparatus includes: an image reading device that optically reads a document to obtain image data; a character recognizer that recognizes a character pattern included in the image data as a character; a character estimator that, for the character pattern that the character recognizer failed to recognize, from characters, which precede and follow the character pattern and have been recognized by the character recognizer, estimates, in accordance with a grammar rule, a character that the character pattern indicates; and an image data reconfigurer that arranges each character recognized by the character recognizer and each character estimated by the character estimator in an order same as an arrangement order of each character pattern included in the image data to generate reconfigured image data.

Abstract: A three-dimensional shape data production method and a system for the same for realizing contactless receiving of data regarding the inner shape of a tubular body which includes a step of generating multiple pieces of two-dimensional image data based on a signal from an image capturing device configured to be movable inside a tubular body and configured to capture an image of the inside of the tubular body; a step of receiving space information on the image capturing device upon image capturing by the image capturing device based on a signal from a motion sensor placed at the image capturing device; and a step of associating the two-dimensional image data and the space information with each other and generating three-dimensional shape data of the inside of the tubular body based on the two-dimensional image data and the space information.

Abstract: The present invention relates to methods, computer readable medium and systems for detecting and counting single nucleic acid molecules confined in nanoliter volumes using an unmodified camera, such as a cell phone camera. In particular, it identifies colorimetric amplification-indicator dyes that are compatible with the spectral sensitivity of standard mobile phones. The invention further provides an optimal ratiometric image-process for a selected dye to achieve a readout that is robust to lighting conditions and camera hardware and provides unambiguous quantitative results, even for colorblind users.

Abstract: Detection of activity in video content, and more particularly detecting in video start and end frames inclusive of an activity and a classification for the activity, is fundamental for video analytics including categorizing, searching, indexing, segmentation, and retrieval of videos. Existing activity detection processes rely on a large set of features and classifiers that exhaustively run over every time step of a video at multiple temporal scales, or as a small improvement computationally propose segments of the video on which to perform classification. These existing activity detection processes, however, are computationally expensive, particularly when trying to achieve activity detection accuracy, and moreover are not configurable for any particular time or computation budget. The present disclosure provides a time and/or computation budget-aware method for detecting activity in video that relies on a recurrent neural network implementing a learned policy.

Abstract: A filter processing apparatus comprises: K arithmetic operation units configured to perform predetermined arithmetic operation processing parallelly; a data holding unit configured to hold a plurality of data values; a coefficient holding unit configured to hold a plurality of filter coefficients; a first pattern holding unit configured to hold a first pattern that selects K data values from the plurality of data values; a second pattern holding unit configured to hold a second pattern that selects one filter coefficient from the plurality of filter coefficients; and a control unit configured to sequentially input the K data values to the K arithmetic operation units with reference to the first pattern and sequentially input the one common filter coefficient to the K arithmetic operation units with reference to the second pattern.

Abstract: Briefly, embodiments of methods or systems providing a mobile device user with localized and/or time-selectable search query terms and/or search results are provided.

Abstract: Methods, systems, and computer programs are presented for adding new features to a network service. A method includes receiving an image depicting an object of interest. A category set is determined for the object of interest and an image signature is generated for the image. Using the category set and the image signature, the method identifies a set of publications within a publication database and assigns a rank to each publication. The method causes presentation of the ranked list of publications at a computing device from which the image was received.

Abstract: A data collecting device includes a receiver configured to receive an optical signal; an optical-to-electrical converter configured to convert the optical signal received by the receiver into an electrical signal; an analog-to-digital converter configured to convert the electrical signal into a digital signal; a data reducing circuit configured to reduce the digital signal output from the analog-to-digital converter; and a transmitter configured to transmit, to a managing device that manages the data collecting device, a signal obtained by reducing the digital signal by the data reducing circuit.

Abstract: An image processing device (100) includes a change detection unit (101) that detects a target state change in a person on the basis of an input image, and a determination unit (102) that determines an abnormal state in accordance with a detection obtained by detecting occurrences of the target state change in a plurality of persons.

Abstract: The present invention relates to an electronic business card exchange system and method using a mobile terminal. Particularly, the present invention relates to an electronic business card exchange system using a mobile terminal and an electronic business card exchange method using a mobile terminal, wherein an electronic business card is generated and is registered in a server, business card identification information of the registered electronic business card is assigned by the server, the business card identification information is used to transmit the business card to a mobile terminal of at least one business card exchange target nearby, and the business card exchange targets receiving the electronic business cards are grouped according to any one or more among a position, a time, and a keyword, such as a meeting name, or the like, for management.

Abstract: Vehicle safety is enhanced by providing a video system incorporating multiple cameras providing separate video feeds that are stitched together by a controller to provide a composite video viewable by the operator that changes in real time along with changes to the speed and direction of the vehicle.

Abstract: The present disclosure provides a method, apparatus and system for processing a case management model (CMM). According to an embodiment, there is provided a method for processing a CMM, the method includes: obtaining an existing CMM having a plurality of elements; obtaining a new CMM having at least one element; aligning an element of the new CMM to an element of the existing CMM according to match costs between the element of the new CMM and the plurality of elements of the existing CMM; and fusing the new CMM into the existing CMM based on the match cost between the aligned elements.

Abstract: According to one embodiment, an information processing device includes a storage device and a processor connected to the storage device. The processor is configured to perform a process for displaying an image and information related to a size of a recognition target, and recognize a recognition target from the image. The information related to the size of the recognition target includes visual information of the recognition target.