Abstract: The disclosed techniques are directed to identifying textual data instances depicted within images having an unstructured/undefined format. A machine-learning model may be trained to identify textual data instances within the image and corresponding data types for the textual data instances. Data provider information may be obtained from the textual data instances that were identified by the machine-learning model and an approved process may be selected from a plurality of automated processes based on an approved process type identified in the data provider information. Executing the approved process may comprise transmitting one or more data messages that include one or more values of the textual data instances. The disclosed techniques may be executed as part of a monitoring process that obtains images over a time period, detects and validates the textual data instances depicted within those images, and executes one or more additional processes using values extracted from the images.

Abstract: A vehicle device setting method including: capturing, by an image sensing unit, a first image frame; recognizing a user ID according to the first image frame; showing ID information of the recognized user ID on a screen or by a speaker; capturing a second image frame; generating a confirm signal when a first user expression is recognized by calculating an expression feature in the second image frame and comparing the recognized expression feature with stored expression data associated with a predetermined user expression to confirm whether the recognized user ID is correct or not according to the second image frame captured after the ID information is shown; controlling an electronic device according to the confirm signal; and entering a data update mode instructed by the user and updating setting information of the electronic device by current electronic device setting according to a saving signal generated by confirming a second user expression in a third image frame captured after the user ID is confirmed

Abstract: Technology is disclosed herein to execute an inference model by a processor which includes a reshape layer. In an implementation, the reshape layer of the inference model receives an output produced by a previous layer of the inference model and inserts padding into the output, then supplies the padded output as an input to a next layer of the inference model. In an implementation, the inference model includes a stitching layer at the beginning of the inference model and an un-stitch layer at the end of the model. The stitching layer of the inference model stitches together multiple input images into an image batch and supplies the image batch as an input to a subsequent layer. The un-stitch layer receives output from a penultimate layer of the inference model and unstitches the output to produce multiple output images corresponding to the multiple input images.

Abstract: Embodiments described herein provide a mechanism for replacing existing text encoders in text-to-image generation models with more powerful pre-trained language models. Specifically, a translation network is trained to map features from the pre-trained language model output into the space of the target text encoder. The training preserves the rich structure of the pre-trained language model while allowing it to operate within the text-to-image generation model. The resulting modularized text-to-image model receives prompt and generates an image representing the features contained in the prompt.

Abstract: Systems and methods to train a convolutional neural network having two or more filter layers having different filtering parameters corresponding to respective different portions of a digital representation of an image. A processor comprising one or more arithmetic logic units (ALUs) to be configured to identify one or more features within an image based, at least in part, on a convolutional neural network having two or more filter layers having different filtering parameters corresponding to respective different portions of a digital representation of the image.

Abstract: Methods and systems are described herein for improvements to authenticate users, particularly authenticating a user based on data known to the user. For example, methods and systems allow for users to be securely authenticated based on data known to the users over remote communication networks without storing the data known to the users. Specifically, methods and systems authenticate users by requiring users to select images that are known to the users. For example, the methods and systems may generate synthetic images based on the user's own images and require the user to select the synthetic image, from a set of a set of images, that is known to the user to authenticate the user. Moreover, the methods and systems alleviate storage and privacy concerns by not storing the data known to the users.

Abstract: A fluorescent single molecule emitter simultaneously transmits its identity, location, and cellular context through its emission patterns. A deep neural network (DNN) performs multiplexed single-molecule analysis to enable retrieving such information with high accuracy. The DNN can extract three-dimensional molecule location, orientation, and wavefront distortion with precision approaching the theoretical limit of information content of the image which will allow multiplexed measurements through the emission patterns of a single molecule.

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: Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for acquiring an image. The method includes distilling an original image set through a capsule neural network model to generate a distilled image set, wherein the distilled image set includes a plurality of distilled images. The method further includes acquiring a first feature of a first image through the capsule neural network model. The method further includes acquiring a plurality of distilling features of the plurality of distilled images respectively through the capsule neural network model. The method further includes determining a plurality of similarities between the first feature and the plurality of distilling features respectively. The method further includes acquiring at least one original image matching the first image based on the plurality of similarities.

Abstract: Embodiments of the present disclosure relate to a method, a device and a computer storage medium for data analysis. The method comprises: obtaining a prediction model, a processing layer of the prediction model comprising a plurality of processing units, parameters of each of the a plurality of processing units satisfying an objective parameter distribution, an output of the prediction model being determined based on a plurality of groups of parameters determined from the parameter distribution; and applying model input data to the prediction model, so as to obtain a prediction for the model input data. In this way, a more accurate prediction result may be obtained.

Abstract: An encoding apparatus extracts features of an image by applying multiple padding operations and multiple downscaling operations to an image represented by data and transmits feature information indicating the features to a decoding apparatus. The multiple padding operations and the multiple downscaling operations are applied to the image in an order in which one padding operation is applied and thereafter one downscaling operation corresponding to the padding operation is applied. A decoding method receives feature information from an encoding apparatus, and generates a reconstructed image by applying multiple upscaling operations and multiple trimming operations to an image represented by the feature information. The multiple upscaling operations and the multiple trimming operations are applied to the image in an order in which one upscaling operation is applied and thereafter one trimming operation corresponding to the upscaling operation is applied.

Abstract: The disclosed techniques are directed to identifying textual data instances depicted within images having an unstructured/undefined format. A machine-learning model may be trained to identify textual data instances within the image and corresponding data types for the textual data instances. The values and/or data types of the textual data instances may be compared to previously-stored data that is associated with a data provider. If the values and/or data types match the previously-stored data, the values corresponding to the textual data instances may be used to execute one or more processes. Executing a process may comprise transmitting one or more data messages that include one or more values of the textual data instances. The disclosed techniques may be executed as part of a monitoring process that obtains images over a time period, detects and validates the textual data instances depicted within those images, and executes one or more additional processes using values extracted from the images.

Abstract: A need for a system and method for preventing shrinkage in physical retail store environment using real-time camera feeds is fulfilled in the ongoing description by (a) configuring cameras in a retail store forming a distributed on-device-AI (DODA) model (b) sampling two-dimensional (2D) frames from cameras, (c) generating labels and location for at least one object identified using a first unsupervised deep neural network model (DNN), (d) visually classifying anatomical parts of the human body using a second unsupervised DNN, (e) enlarging and enhancing a product based on labels and location using a third unsupervised DNN, (f) generating an index of product associated with a person using a fourth unsupervised DNN by reidentifying objects from cameras, and (f) automatically classifying activity characterizing the movement of objects including a scan activity, an in-bag activity, a no scan activity, a mis-scan activity, and a theft activity to prevent shrinkage.

Abstract: A method for selecting a final model for detecting cells of interest in image datasets includes dividing a curated image dataset into a training set, a validation set, and a testing set where each image in the curated image dataset has been labeled as positive or negative for a cell of interest. The method trains each model of an ensemble of neural networks using the training and validation sets. Next, each model of the ensemble is tested using the testing set and the predictions of the ensemble are combined. The combined prediction is compared to the label and the method determines whether the combined prediction satisfies a pre-determined level of detection (LOD). If so, the method outputs the ensemble as a final ensemble. If not, the method modifies a hyperparameter of at least one of the models of the ensemble until the combined prediction satisfies the pre-determined LOD.

Abstract: Disclosed is a data recognition model construction apparatus. The data recognition model construction apparatus includes a video inputter configured to receive a video, an image composition unit configured to, based on a common area included in each of a plurality of images that form at least a portion of the video, generate a composition image by overlaying at least a portion of the plurality of images, a learning data inputter configured to receive the generated composition image, a model learning unit configured to make a data recognition model learn using the generated composition image, and a model storage configured to store the learnt data recognition model.

Abstract: This image generation device is provided with: a learning image generation unit (1) for generating a training input image and a training output image based on three-dimensional data; a noise addition unit (2) for adding the same noise to the training input image and the training output image; a learning unit (3) for learning a learning model for extracting or removing a specific portion by performing machine learning based on the training input image to which the noise has been added and the training output image to which the noise has been added; and an image generation unit (4) for generating an image from which the specific portion has been extracted or removed by using a learned learning model.

Abstract: A method of mesoscopic photogrammetry can be carried out using a set of images captured from a camera on a mobile computing device. Upon receiving the set of images, the method generates a composite image, which can include applying homographic rectification to warp all images of the set of images onto a common plane; applying a rectification model to undo perspective distortion in each image of the set of images; and applying an undistortion model for adjusting for camera imperfections of a camera that captured each image of the set of images. A height map is generated co-registered with the composite image, for example, by using an untrained CNN whose weights/parameters are optimized in order to optimize the height map. The height map and the composite image can be output for display.

Abstract: Content-adaptive online training for end-to-end (E2E) neural image compression (NIC) using a neural network performed by at least one processor, is provided, including receiving an input image, to an E2E NIC framework, including one or more blocks, preprocessing a first neural network of the E2E NIC framework, based on the one or more blocks, computing updated parameters using the preprocessed first neural network, encoding the one or more blocks and the updated parameters, updating the first neural network based on the encoded updated parameters, and generating a compressed representation of the encoded one or more blocks using the updated first neural network.

Abstract: A method of processing a digital image for use by a digital image classifier comprises: processing the digital image with computational models of a retinal ganglion cell (RGC) to produce sets of digital image features; and combining the sets of digital image features to produce a multi-channel retina model image. The method may be used in digital image classification and in training a digital image classifier. The creation and use of multi-channel retina model images improves the ability to detect pertinent image features during image classification and so improves the overall classification process.

Abstract: Techniques related to automatically segmenting video frames into per pixel fidelity object of interest and background regions are discussed. Such techniques include applying tessellation to a video frame to generate feature frames corresponding to the video frame and applying a segmentation network implementing context aware skip connections to an input volume including the feature frames and a context feature volume corresponding to the video frame to generate a segmentation for the video frame.