Abstract: A receipt capture tool residing on a customer mobile device may be initiated when a customer completes an in-store or online purchase. The receipt capture tool may prompt the customer to capture an image of a receipt detailing a purchase and an item (e.g., product or service) purchased. For instance, the photo of a physical receipt may be taken by the mobile device, or an electronic receipt or email detailing the purchasing transmitted from a physical merchant or online merchant server may be stored. Receipt information may be extracted and saved with other information pertinent to the item purchased, including warranty information. If the customer needs to return or repair the item purchased at a future date, the receipt and warranty information may be subsequently accessed via their mobile device. The receipt and warranty information may also be stored in a searchable database to facilitate easy retrieval by the customer.

Abstract: Various embodiments of a deep learning (DL)-based face perception engine for constructing, providing, and applying a highly-personalized face perception model for an individual through a deep learning process are disclosed. In some embodiments, a disclosed face perception engine includes a deep neural network configured for training a personalized face perception model for a unique individual based on a standard set of training images and a corresponding set of decisions on the set of training images provided by the unique individual. When sufficiently trained using the standard set of training images and the corresponding set of decisions, the personalized face perception model for the unique individual perceives a new face photo/image as if through the eyes of that unique individual.

Abstract: A system and method are presented to create custom versions for users of recorded sessions of individuals. Individuals are recorded at a booth responding to prompts. Audio and visual data recorded at the booth are divided into time segments according to the timing of the prompts. Depth sensors at the booth are used to assign score values to time segments. Prompts are related to criteria that were selected as being relevant to an objective. Users are associated with subsets of criteria in order to identify subsets of prompts whose responses are relevant to the users. Time segments of audio and visual data created by the identified subset of prompts are selected. The selected time segments are ordered according to herd behavior analysis. Lesser weighted time segments may be redacted. The remaining portions of ordered time segments are presented to the user as a custom version.

Abstract: A system to extract data from regions of interest on a document is provided. The system includes a storage device storing an image derived from a document having text information. The system includes a document importer operable to perform optical character recognition to convert image data in the image to machine readable data. The system includes a neural network that identifies at least one region of interest on the image to classify an area of the at least one region of interest as a table. The neural network is operable to take as input the machine readable data and the image and combine both the machine readable data and the image to determine that the classified area is the table.

Abstract: This application relates to a method and a system for compressing a captured image of an item such as a mailpiece or parcel. The system may include a memory configured to store images of a plurality of items captured while the items are being transported and a processor in data communication with the memory. The processor may be configured to receive or retrieve one or more of the captured images, perform a wavelet scattering transform on the one or more captured images, perform deep learning on the wavelet scattering transformed images to classify the wavelet scattering transformed images and compress the classified wavelet scattering transformed images. Various embodiments can significantly improve a compression efficiency, a communication efficiency of compressed data and save a memory space so that the functionality of computing devices is significantly improved.

Abstract: Described herein are systems, methods, and other techniques for segmenting an input text. A set of tokens are extracted from the input text. Token representations are computed for the set of tokens. The token representations are provided to a machine learning model that generates a set of label predictions corresponding to the set of tokens. The machine learning model was previously trained to generate label predictions in response to being provided input token representations. Each of the set of label predictions indicates a position of a particular token of the set of tokens with respect to a particular segment. One or more segments within the input text are determined based on the set of label predictions.

Abstract: A method for training of a process for generating an image of an object from measurement data modified by scatter radiation. Individual sets of measured data are each made up of matrix elements. Each matrix element corresponds to an individual detector element that detects ionizing radiation. Signals measured by the individual detector elements in an energy bin are assigned as values for each matrix element. The individual sets of measured data and a template image are used as input for a procedure for determining a correction image for correcting a modification of the measured data by the scatter radiation. The preliminary image obtained using the individual sets of measured data is adjusted to the template. These steps are repeated until the deviation between the preliminary image and the template image is below a threshold. The procedure is used to generate the image of the object from the measurement data.

Abstract: An image processing method, a related device, and a computer storage medium are provided. The method includes: obtaining a feature intensity image corresponding to a training image, where an intensity value of a pixel in the feature intensity image is used to indicate importance of the pixel for recognizing the training image, and resolution of the training image is the same as resolution of the feature intensity image; and occluding, based on the feature intensity image, a to-be-occluded region in the training image by using a preset window, to obtain a new image, where the to-be-occluded region includes a to-be-occluded pixel, and the new image is used to update an image recognition model. According to the embodiments of the present application, a prior-art problem that a model has low accuracy and relatively poor generalization performance because of limited training data can be resolved.

Abstract: The present invention is to improve accuracy of position information of an object. A labeling unit 13 of an information integration device 1 associates a label included in tracking data with an object area having a largest ratio of overlapping areas overlapping label areas included in the tracking data with regard to the object area or an object area having a largest size of overlapping areas overlapping label areas included in the tracking data, among a plurality of object areas included in a Depth map.

Abstract: In some aspects, the disclosure is directed to methods and systems for detection and classification of stamps in documents. The system can receive image data and textual data of a document. The system can pre-process and filter that data, and covert the textual data to a term frequency inverse document frequency (TF-IDF) vector. The system can detect the presence of a stamp on the document. The system can extract a subset of the image data including the stamp. The system can extract text from the subset of the image data. The system can classify the stamp using the extracted text, the image data, and the TF-IDF vector. The system can store the classification in a database.

Abstract: A method of obtaining contact information for a person or an entity is disclosed. The method comprises detecting a name of the person or the entity in a frame from a screen of a device; determining a presence status for the detected name based on one or more connectivity status for the detected name in one or more communication applications and/or one or more databases, where the one or more communication applications operate on the device from which the frame originates and where the one or more databases are accessible on the device; displaying the presence status on the screen of the device.

Abstract: A method includes executing a Optical Character Recognition (OCR) preprocessor on training images to obtain OCR preprocessor output, executing an OCR engine on the OCR preprocessor output to obtain OCR engine output, and executing an approximator on the OCR preprocessor output to obtain approximator output. The method further includes iteratively adjusting the approximator to simulate the OCR engine using the OCR engine output and the approximator output, and generating OCR preprocessor losses using the approximator output and target labels. The method further includes iteratively adjusting the OCR preprocessor using the OCR preprocessor losses to obtain a customized OCR preprocessor.

Abstract: A system and a method for training and utilizing deep convolutional neural networks to perform diagnostic and image enhancement operations on images of dentition uses digital images and other auxiliary parameters as inputs for a convolutional neural network. The neural network can output a tooth segmentation map, tooth identifiers, a probability map indicating the presence of caries, cavities or other dental anomalies/conditions, and recommended parameters for use in image enhancement algorithms.

Abstract: A vehicle periphery monitoring device stores images photographed with a front camera, a rear camera, a left side camera, and a right side camera as a past front image, a past rear image, a past left side image, and a past right side image, respectively. When a vehicle travels while making a turn, the vehicle periphery monitoring device generates an underfloor image indicating a condition of an underfloor of the vehicle using at least one of the past front image and the past rear image and at least one of the past left side image and the past right side image. The vehicle periphery monitoring device displays the generated underfloor image on a display.

Abstract: Methods, apparatus, systems and articles of manufacture to compress data are disclosed. An example apparatus includes a data slicer to split a dataset into a plurality of blocks of data; a data processor to select a first compression technique for a first block of the plurality of blocks of data based on first characteristics of the first block; and select a second compression technique for a second block of the plurality of blocks of data based on second characteristics of the second block; a first compressor to compress the first block using the first compression technique to generate a first compressed block of data; a second compressor to compress the second block using the second compression technique to generate a second compressed block of data; and a header generator to generate a first header identifying the first compression technique and a second header identifying the second compression technique.

Abstract: Techniques are described for dynamically correcting image distortion during imaging of a patterned sample having repeating spots. Different sets of image distortion correction coefficients may be calculated for different regions of a sample during a first imaging cycle of a multicycle imaging run and subsequently applied in real time to image data generated during subsequent cycles. In one implementation, image distortion correction coefficients may be calculated for an image of a patterned sample having repeated spots by: estimating an affine transform of the image; sharpening the image; and iteratively searching for an optimal set of distortion correction coefficients for the sharpened image, where iteratively searching for the optimal set of distortion correction coefficients for the sharpened image includes calculating a mean chastity for spot locations in the image, and where the estimated affine transform is applied during each iteration of the search.

Abstract: A camera system may automatically identify high frequency motion regions in a field of view of the camera system. Analysis of motion events detected at different regions of a scene in the field of view, may be performed. Similar events frequently occurring at a certain region may be recorded/accumulated and compared to a threshold. Regions with high frequency activity may be determined and a user may be notified. If the user is not interested in events within the high activity regions, the regions may be ignored and notifications to the user may cease. The camera system may determine specific actions/events occurring in a region, such as a person approaching or leaving a home.

Abstract: A Robotic control system has a wand, which emits multiple narrow beams of light, which fall on a light sensor array, or with a camera, a surface, defining the wand's changing position and attitude which a computer uses to direct relative motion of robotic tools or remote processes, such as those that are controlled by a mouse, but in three dimensions and motion compensation means and means for reducing latency.

Abstract: Image encoded documents are identified by recognizing known objects in each document with an object recognizer. The objects in each page are filtered to remove lower order objects. Known features in the objects are recognized by sequentially organizing each object in each filtered page into a one-dimensional array, where each object is positioned in a corresponding one-dimensional array as a function of location in the corresponding filtered page. The one-dimensional array is then compared to known arrays to classify the image document corresponding to the one-dimensional array.

Abstract: A Fast Non-Maximum Suppression (NMS) Algorithm post-processing for object detection includes getting original data output from a deep learning model inference output, the original data including a plurality of bounding boxes, pre-emptively filtering out at least one bounding box of the plurality of bounding boxes from further consideration when applying the algorithm, the at least one bounding box filtered out according to a predetermined criteria, processing data, using sigmoid functions or exponential functions, from bounding boxes of the plurality of bounding boxes not filtered out to generate processed bounding boxes, calculating final scores of the processed bounding boxes, and choosing a processed bounding boxes utilizing the final scores.