Abstract: A method for image processing is provided. The method includes: obtaining an image including a table; generating, for the table, a skeleton graph including a plurality of edges; identifying a plurality of angles and a plurality of lengths for the plurality of edges; and calculating a typesetness score that compares the table to a template table based on the plurality of angles and the plurality of lengths.

Abstract: To identify emphasized text, bounding boxes are based on clusters resulting from horizontal compression and horizontal morphological dilation. The bounding boxes are processed to determine if any contain words or characters in bold. A bounding box is eliminated based on a comparison of its density and an average density across all bounding boxes. If its density is greater, text elements within the bounding box are evaluated to determine whether the text element is bold.

Abstract: A method for training a deep neural network (DNN) to perform a specified task with respect to images captured by a target camera, including: using an image captured by the target camera as a style target image, training a style transformer network to perform a style transformation that transforms any photorealistic input image into a transformed image that has contents of the input image, maintains photorealistic quality of the input image, and has a style that matches a style of the style target image; using the trained style transformer network to transform training image of an original training dataset into transformed training images; labeling the transformed training images with the training labels of the corresponding training image of the original training dataset, to form an augmented training dataset; and using the augmented training dataset to train the DNN to perform the specified task.

Abstract: A method for character recognition. The method includes: obtaining a plurality of character segments extracted from an image; determining a first character bounding box including a first set of the plurality of character segments and a second character bounding box including a second set of the plurality of character segments; determining an ordering for the first set based on a plurality of texture properties for the first set; determining a plurality of directions of the first set based on a plurality of brush widths and a plurality of intensities for the first set; and executing character recognition for the first character bounding box by sending the first set, the plurality of directions for the first set, and the ordering for the first set to an intelligent character recognition (ICR) engine.

Abstract: A method, job management apparatus, and computer program product are disclosed for a job management apparatus, the job management apparatus managing a print job for at least one printer, wherein the code computer readable code configured to cause the job management apparatus to display a job scheduling screen. The process includes obtaining first information on a job to be executed by the at least one printer; obtaining second information on color reproduction state of the at least one printer; and generating the job scheduling screen, wherein the job scheduling screen is a two dimensional chart in which a first axis indicates an execution length of time for the job or a number of sheets of paper to be used for the job, and in which a part of a second axis of the two dimensional chart indicates the color reproduction state of the at least one printer.

Abstract: A terahertz (THz) spectral imaging system includes a THz 2D imaging camera, a tunable THz bandpass filter before the THz camera, and a broadband THz light source. The tunable THz bandpass filter includes a visible or infrared laser source, a spatial light modulator modulating the light to generate a spatially structured light pattern, and a semiconductor plate onto which the light pattern is projected. The light pattern generates carriers in the semiconductor plate to turn it into a metamaterial THz bandpass filter, which is tunable by changing the light patterns. A controller controls the light patterns and the THz camera in a timing sequence to acquire multiple 2D THz images at different THz frequencies. Such THz spectral image data can be further combined with visible images and LiDAR images in a security surveillance system to automatically detect security threats using image fusion and deep learning techniques.

Abstract: A method for processing an image with a processor, including: identifying, within an image, a candidate arrow including a long path adjacent to a plurality of short paths; determining a direction of the candidate arrow based on the long path; estimating a tip pixel within the plurality of short paths based on the direction of the candidate arrow; determining, for the candidate arrow, a plurality of arrowhead edges in the plurality of short paths based on the tip pixel; and generating, for the candidate arrow, a plurality of refined arrowhead edges based on the plurality of arrowhead edges, the direction, and the tip pixel.

Abstract: A low frequency power management bus, a method of power management of a device, and a non-transitory computer readable program code configured to execute a power management process for a device are disclosed. The power management bus including a bus, and a plurality of power nodes connected to the bus, each of the plurality of power nodes including power management control logic, a power regulator, and a power policy, and wherein the plurality of power nodes are arranged in a topology with at least one node of the plurality of nodes being designated as a super power node, the super power node configured to be connected either directly or through another power node to each of the plurality of power nodes within the topology.

Abstract: A method, a system, and a non-transitory computer readable program code are disclosed for authenticating users for services. The method includes registering one or more users in an authentication system; assigning a score index to each of the one or more users in the authentication system for one or more services, the score index representing a security level and corresponding authentication required to access each of the one or more services; inputting each request for services from the one or more users into the authentication system to continuously update the score index for each of the one or more users, each of the requests including one or more authenticators or biometric identifiers for the requested service; and requesting the one or more users to register one or more additional authenticators or biometric identifiers with the authentication system upon the score index for a user reaching of a predefined threshold value.

Abstract: A server in a digital rights management system implements version control for the digital documents being managed. Each document belongs to a document series and has a version number. The server maintains a version control database table that stores, for each document, the document series name and version number, and parameters indicating whether the document is obsoleted or deleted. When registering a new document, based on auto-obsolete and auto-delete parameters inputted by the user, the server automatically obsoletes or deletes certain older version documents that belong to the same series as the new document. The server controls access to the documents so that obsoleted documents will not be accessible to users even if they still have local copies of such documents. When a user requests access to an older version document that is not obsoleted, the server may allow access to the latest version document instead.

Abstract: A method for segmenting an image containing handwritten text into line segments and word segments. The image is horizontally down sampled at a first ratio. Connected regions in the down-sampled image are detected; horizontal neighboring ones are merged to form lines, to segment the original image into line images. Each line image is horizontally down sampled at a second ratio which is smaller than the first ratio. Connected regions in the down-sampled line image are detected to obtain potential word segmentation positions. A path is a way of dividing the line at some or all of the potential word segmentation positions into multiple path segments; for each of all possible paths, word recognition is applied to each path segment to calculate a word recognition score, and an average word recognition score for the path is calculated; the path with the highest score gives the final word segmentation.

Abstract: A patient identification method and related system use dynamic medical images of a patient, such as dynamic chest x-ray images, to generate pulsation and/or perfusion signals and use them for patient identification. A first pulsation and/or perfusion signal acquired from a current patient is compared to a previously stored second pulsation and/or perfusion signal associated with a known patient, to determine whether the current patient is the same as the known patient. At least one of the first and second pulsation and/or perfusion signals is generated from dynamic medical images. In some embodiments, one of the first and second pulsation and/or perfusion signals is pulsation-like signal obtained from electrocardiogram (ECG). When the current patient is determined to be different from the known patient, warning signals can be generated, and further steps can be taken to prevent medical procedures being conducted on the wrong patient.

Abstract: A method for searching content a page description language (PDL) file that was converted from an original file includes: receiving a search request specifying a description of graphics object in the original file; identifying, in response to the search request, a location of the description in an invisible layer of the PDL file; and displaying a portion of a visible layer of the PDL file that includes the image object in response to the portion of the visible layer overlapping the location. The PDL file includes an image object converted from the graphics object, object composition metadata for the image object generated based on a composition rule corresponding to a type of the graphics object and formatting attribute of the graphics object included in the original file, a visible layer comprising the image object, and an invisible layer comprising the object composition metadata for the image object.

Abstract: A method, a system, a server, and a computer readable medium are disclosed for a server connectable to at least one printer to judge an error level, which includes (a) receiving a notification of a given error which has occurred at a given printer; (b) judging on whether there is an unfinished job corresponding to the given printer; (c) judging on whether the unfinished job can be redirected to other printer than the given printer; and (d) determining an error level for displaying the given error based on the judgment at step (c).

Abstract: A method for creating local hot folders is provided. The method includes: receiving, by a print server that includes a first network hot folder and a second network hot folder, a request to create at least one local hot folder on a user computing device; determining, by the print server, that the request corresponds to the first network hot folder; and transmitting, by the print server to the user computing device, a first instruction set comprising an instruction to create a first local hot folder that implements a first transfer protocol. The first network hot folder executes a predetermined process and requires the first transfer protocol in response to executing the predetermined process, and the second network hot folder executes another process and requires a second transfer protocol.

Abstract: A method for character recognition. The method includes: obtaining a plurality of character segments extracted from an image; determining a first character bounding box including a first set of the plurality of character segments and a second character bounding box including a second set of the plurality of character segments; determining an ordering for the first set based on a plurality of texture properties for the first set; determining a plurality of directions of the first set based on a plurality of brush widths and a plurality of intensities for the first set; and executing character recognition for the first character bounding box by sending the first set, the plurality of directions for the first set, and the ordering for the first set to an intelligent character recognition (ICR) engine.

Abstract: A method, a computer program product, and a multi-function peripheral are disclosed, which secures a device using a link local network for transmission of data. The method includes starting an Internet Protocol Version 6 (IPv6) network initialization from an Internet of Things (IOT) device in an IPv6 link local network; deriving an identifier for a link local IPv6 address for the IOT device from a first public key of the IOT device; sending the link local IPv6 address with the identifier from the IOT device to the first host device for double address detection (dad) in the link local IPv6 network; and authenticating the link local IPv6 address on the first host device with a private key.

Abstract: A method, a non-transitory computer readable medium, and a system are disclosed for creating a mapping library for converting a job ticket. The method includes obtaining a print job ticket schema that comprises a plurality of user items and user values; obtaining at least one sample print ticket each of which comprises a part of the plurality of user items and user values; obtaining a print job history that indicates whether a print job was successfully executed using the job ticket that has been previously created; and displaying a graphical user interface (GUI), which allows a user to associate the user values with target values to be used to execute a print job, wherein at least one of the user values and/or at least one of the target values that was used for the successful print job is shown in a different appearance from other user values and/or target values.

Abstract: A method, a computer program product, and a system are disclosed for stitching aerial data using information from at least one previous image. The method includes capturing a plurality of images of the landscape; obtaining, image metadata for each of the captured images; generating, for each of the captured images, a set of transformed images based on the image metadata, comprises: setting a variable for each of the parameters; preparing a plurality of sets of transformed image metadata by applying the variables to the parameters; and preparing the set of transformed images from the captured image based on the plurality of sets of transformed image metadata, respectively; identifying, for each set of transformed images, one of the transformed images by calculating quality of fit to the top level image for each of the transformed images; and assembling a new aerial image based on the plurality of the identified transformed images.

Abstract: A method of providing security for data using a loopback interface, the method includes setting a security policy on a host device and a client device, the security policy configuration including a first loopback interface and an IP address for the host device and a second loopback interface and an IP address for the client device; sending an IP packet to the first loopback interface on the host device, wherein the first loopback interface configures the packet to be routed to the second loopback interface; sending the IP packet from the first loopback interface to a security module on the host device for encryption pursuant to a security protocol; filtering the encrypted packet received from first loopback interface and configuring the encrypted packet be sent to the client device; and sending the encrypted packet from the host device to the client device.