Abstract: An optical shutter device includes: a projection shutter disposed in front of a projection device that projects an AR image onto an object surface with a local content; an imaging shutter disposed in front of an image capturing device that captures a local image of the local content; and a controller that electrically drives the projection and imaging shutters and switches the optical shutter device between a projection state and an imaging state. In the projection state, the controller electrically drives: the projection shutter to an open state, and the imaging shutter to a closed state. In the imaging state, the controller electrically drives: the projection shutter to the closed state, and the imaging shutter to the open state.

Abstract: An integrated sensing system to perform multi-modality sensing of an environment. The integrated sensing system includes a first sensing element that generates a first modality sensing output of the environment, a first edge artificial intelligence (AI) engine that controls the first sensing element and generates a first data analysis result based on the first modality sensing output, a second sensing element that generates a second modality sensing output of the environment, a second edge AI engine that controls the second sensing element and generates a second data analysis result based on the second modality sensing output, and a computer processor that generates, using a central AI algorithm, a classification result of the environment based on the first data analysis result and the second data analysis result, where the computer processor is directly coupled to the first edge AI engine and the second edge AI engine.

Abstract: A method to extract static user content on a marker board is disclosed. The method includes generating a sequence of samples from a video stream comprising a series of images of the marker board, generating at least one center of mass (COM) of estimated foreground content of each sample in the sequence of samples, detecting, based on a predetermined criterion, a stabilized change of the at least one COM in the sequence of samples, wherein the stabilized change of the at least one COM identifies, in the sequence of samples, a stable sample with new content, generating, in response to the stabilized change of the at least one COM and from the stable sample with new content, a mask of full foreground content, and extracting, based at least on the mask of full foreground content, a portion of the static user content from the video stream.

Abstract: An image processing method to generate a layout of searchable content from a physical document. The method includes generating extracted content blocks in the physical document, generating, based on a bounding box of a text block, a layout rectangle that identifies where machine-encoded text is placed in the layout of the searchable content, generating, based on a bounding box of a non-text block, an avoidance region that identifies where the machine-encoded text is prohibited in the layout of the searchable content, generating, based on the layout rectangle and the avoidance region, a draft layout of the searchable content, and iteratively adjusting a point size of the machine-encoded text in the draft layout to generate the layout of the searchable content.

Abstract: An optical shutter device includes: a projection shutter disposed in front of a projection device that projects an AR image onto an object surface with a local content; an imaging shutter disposed in front of an image capturing device that captures a local image of the local content; and a controller that electrically drives the projection and imaging shutters and switches the optical shutter device between a projection state and an imaging state. In the projection state, the controller electrically drives: the projection shutter to an open state, and the imaging shutter to a closed state. In the imaging state, the controller electrically drives: the projection shutter to the closed state, and the imaging shutter to the open state.

Abstract: A method and system providing an anti-counterfeiting label or mark, using ordinary inkjet printers, take advantage of a phenomenon called a coffee ring pattern, something that inkjet printers. Even the same inkjet printer can output different patterns under different conditions. As a result, the likelihood of reproduction of a particular printer's coffee ring pattern using another printer is so low as to be negligible. It is possible to capture images of the coffee rings using a smartphone camera. The coffee ring approach may be used on any labels or packages on which inkjet printing can be used.

Abstract: Method and apparatus to match bounding boxes around text to align forms. The approach is less computationally intensive, and less prone to error than text recognition. For purposes of achieving alignment, information per se is not as important as information location. Information within the bounding boxes is not as critical as is the location of the area which the bounding boxes occupy. Scanning artifacts, missing characters, or noise generally do not affect bounding boxes themselves so much as they do the contents of the bounding boxes. Thus, for purposes of form alignment, the bounding boxes themselves are sufficient. Using bounding boxes also avoids misalignment issues that can result from stray marks on a page, for example, from holes punched in a sheet, or from handwritten notations.

Abstract: A method and system for securely registering a user in a biometric system. The method includes: receiving, on a computer processor of the biometric system, an identifier of a biometric device and user information; sending, with the computer processor, a request that the biometric device be sent to the user of the biometric device upon the receipt of the identifier of the biometric device and user information; receiving, on the computer processor, the identifier of the biometric device and one or more authenticators from the user; initiating, with the computer processor, a registration of the user based on the receipt of the identifier of the biometric device and the one or more authenticators from the user; and receiving, on the computer processor, biometric data of the user from the biometric device to complete a registration of the user in the biometric system.

Abstract: A method for processing images in an information sharing and collaboration environment includes: receiving a plurality of graphical contents including a first graphical content from a first source and a second graphical content from a second source different from the first source within the information sharing and collaboration environment and overlapping the first and second graphical contents; determining a probability that the first graphical content was created before the second graphical content; rendering, using a transparency blending formula and based on the probability that the first graphical content was created before the second graphical content, an opacity of an overlapped portion of the first and second graphical contents; and displaying, on a display, the overlapped first and second graphical contents.

Abstract: An image processing method includes: generating, from combined connected components (CCs) of a document image, candidate text CCs, candidate background CCs, and candidate natural image CCs where the candidate background CCs are excluded from the combined CCs to generate the candidate natural image CCs with a predetermined criterion dependent on the candidate text CCs; generating a final natural image bounding box by expanding a candidate natural image bounding box of the candidate natural image CCs and including in the expanded candidate natural image bounding box at least one combined CC that intersects the expanded candidate natural image bounding box; and modifying, based on the final natural image bounding box, the document image and displaying the modified document image to a user.

Abstract: A method and system to detect visual spoofing of a process of authenticating a person's identity employs computer vision techniques to define characteristics of different kinds of spoofing. Embodiments identify a foreground object within an image and by examining positions and/or orientations of that foreground object within the image, determine whether the presentation of the foreground object is an attempt to spoof the authentication process.

Abstract: A care plan risk rating (CPR2) system and method enables physicians and other clinicians to manage patient health care plans remotely in response to patient input to generate CPR2 values. In one aspect, patients under care for a particular condition respond to a series of questions related to that condition. The questions may be weighted according to predetermined criteria which a physician or clinician may set. Based on the CPR2 values, the physician or clinician may alter a care plan for a patient or a group of patients. In one aspect, patients with CPR2 values in a predetermined range may be grouped into a cohort, and their care plans managed as a group.

Abstract: A method to reduce background noise in a document image includes: extracting, from the document image, a connected component corresponding to a background of the document image; generating a histogram of pixel values of the connected component; generating a replacement range using a range pruning algorithm that narrows a range of the histogram by iteratively discarding at least one pixel value and corresponding pixel count of the histogram from at least one side of the histogram; selecting, from the connected component, at least one pixel having a corresponding pixel value within the replacement range; converting the corresponding pixel value of the at least one pixel to a uniform background color; and outputting, subsequent to the converting, the document image.

Abstract: A method and system to generate training data for a deep learning model in memory instead of loading pre-generated data from disk storage. A corpus may be stored as lines of text. The lines of text can be manipulated in the memory of a central processing unit (CPU) of a computing system, using asynchronous multi-processing, in parallel with a training process being conducted on the system's graphics processing unit (GPU). With such an approach, for a given line of text, it is possible to take advantage of different fonts and different types of image augmentation without having to put the images in disk storage for subsequent retrieval. Consequently, the same line of text can be used to generate different training images for use in different epochs, providing more variability in training data (no training sample is trained on more than once). A single training corpus may yield many different training data sets.

Abstract: A method, a non-transitory computer readable medium, and a system are disclosed for scheduling print jobs on a plurality of printers. The method includes: collecting job information on each of a plurality of print jobs; obtaining a predicted success rate for each of the plurality of print jobs with each of the plurality of printers based on the job information on the each of the plurality of print jobs, the predicted success rate being a likelihood that a print job can be successfully completed by a printer; and assigning each of the plurality of print jobs to one or more printers of the plurality of printers with the predicted success rate for each of the one or more printers of the plurality of print jobs being greater than a predicted success threshold.

Abstract: An authentication server that connects a client device and a target server via a first network. The authentication server includes: a storage and a processor. The storage stores user-specific information that includes a plurality of data items. The processor: upon receiving an authentication request including a user ID and a user password, an authentication ID, a biometric device ID unique to a user, or biometric data of a user, identifies a corresponding credential data of the user; determines which of the items in the user-specific information will be sent to the client device; and returns the determined items to the client device, and causes the client device to store the determined items as cache data used for logging into at least one of the client device and the target service, wherein the client device and the target server have given a login authority to the user.

Abstract: A method is disclosed for training a machine learning model to process electronic documents (EDs). The method includes obtaining a structured ED (SED) from a document repository, where the SED includes a first metadata. The method further generates, based on the SED, a bitmap and a second metadata. The method also determines whether the second metadata is within a predetermined threshold of the first metadata and generates, based on the SED and in response to determining that the second metadata is not within the predetermined threshold of the first metadata, a third metadata. The method additionally determines whether the third metadata is within the predetermined threshold of the first metadata and stores, in response to determining that the third metadata is within the predetermined threshold of the first metadata, a second SED comprising the bitmap and the third metadata.

Abstract: Aspects of the present invention provide a new text location technique, which can be applied to general handwriting detection at a variety of levels, including characters, words, and sentences. The inventive technique is efficient in training deep learning systems to locate text. The technique works for different languages, for text in different orientations, and for overlapping text. In one aspect, the technique's ability to separate overlapping text also makes the technique useful in application to overlapping objects. Embodiments take advantage of a so-called skyline appearance that text tends to have. Recognizing a skyline appearance for text can facilitate the proper identification of bounding boxes for the text. Even in the case of overlapping text, discernment of a skyline appearance for words can help with the proper identification of bounding boxes for each of the overlapping text words/phrases, thereby facilitating the separation of the text for purposes of recognition.

Abstract: A carbon nanotube (CNT) resonator includes: a first CNT having a first end and a second end both fixed to a substrate; and a second CNT having a first end fixed to the substrate. The second CNT creates a Van der Waals (VdW) bond with the first CNT where the second CNT overlaps the first CNT. A length of the VdW bond along a distance between the first and the second CNTs oscillates based on a DC voltage applied between the first end of the first CNT and the first end of the second CNT. An electrical current passing through the first and the second CNTs using the VdW bond oscillates based on the oscillation of the length of the VdW bond.

Abstract: A light emitting device includes a substrate layer, a first electrode layer, a light emitting layer, and a patterned second electrode layer. The patterned second electrode layer includes a periodic grating structure having a grating period ?g less than or equal to 200 nm and the patterned second electrode layer and the light emitting layer are separated by at most 100 nm.