Abstract: A biological sample system that efficiently images and registers codes corresponding to biological samples depicted in an image. The biological sample system can implement a neural network to detect the codes individually, and further translate each code into an item identifier. The item identifiers are correlated with network server accounts and a user interface can depict the biological samples with data indicating their registration state.

Abstract: The present disclosure relates to the transmission of sets of data and metadata and more particularly to the transmission of light-field contents. Light-field data take up large amounts of storage space which makes storage cumbersome and processing less efficient. In addition, light-field acquisition devices are extremely heterogeneous and each camera has its own proprietary file format. Since acquired light-field data from different cameras have a diversity of formats a complex processing is induced on the receiver side. To this end, it is proposed a method for encoding a signal representative of a light-field content in which the parameters representing the rays of light sensed by the different pixels of the sensor are mapped on the sensor. A second set of encoded parameters are used to reconstruct the light-field content from the parameters representing the rays of light sensed by the different pixels of the sensor.

Abstract: The present invention involves positionally identifying several anatomical structures of interest of a patient's anatomy on images which have been acquired at different points of time. For each anatomical structure a separate image fusion transformation between these images is performed. For at least one of the image fusion transformations it is then determined whether this transformation is within a predetermined threshold, wherein for this determination, at least one further image fusion transformation of another anatomical structure is taken into account.

Abstract: Methods, apparatus and systems for movement tracking are described. In one example, a described system comprises: at least one sensor configured to generate at least one sensing information (SI); a memory; a processor communicatively coupled to the memory and the at least one sensor; and a set of instructions stored in the memory.

Abstract: Embodiments relate to hue preservation post processing for highlight recovery of an input image. Intensity values for multiple color channels of a plurality of color channels of a pixel of the input image is determined using corresponding ratios of target hues for the plurality of color channels of the pixel, wherein the pixel has at least one color channel with an intensity above a predetermined threshold. A hue preserved value for a color channel of the plurality of color channels of the pixel is determined using intensity values determined for the plurality of color channels of the pixel and the target hues. A recovered version of the input image is generated by adjusting hue information of the pixel, using the hue preserved value for the channel of the plurality of color channels of the pixel.

Abstract: Systems and methods to improve the optical character recognition of records, and in particular health records, are provided. An image of a medical record is received, and an initial optical image recognition (OCR) on the image is performed to identify text information. The OCR signal quality may be measured, and areas of insufficient OCR signal quality may be isolated. The signal quality is determined by a weighted average of semantic analysis of the resulting text, and/or OCR accuracy measures. The OCR process may be repeated on the isolated regions of lower signal quality, each time using a different OCR transform, until all regions are completed with a desired degree of signal quality (accuracy). All the regions of the document may then be recompiled into a single document for outputting.

Abstract: A data processing method for a convolutional neural network includes: (a) obtaining a matrix parameter of an eigenmatrix; (b) reading corresponding data in an image data matrix from a first buffer space based on the matrix parameter through a first bus, to obtain a next to-be-expanded data matrix, and sending and storing the to-be-expanded data matrix to a second preset buffer space through a second bus; (c) reading the to-be-expanded data matrix, and performing data expansion on the to-be-expanded data matrix to obtain expanded data; (d) reading a preset number of pieces of unexpanded data in the image data matrix, sending and storing the unexpanded data to the second preset buffer space, and updating, based on the unexpanded data, the to-be-expanded data matrix; and (e). repeating (c) and (d) until all data in the image data matrix is completely read out on the to-be-expanded data matrix.

Abstract: Methods, apparatus and systems for wireless writing tracking are described. In one example, a described system comprises: a transmitter configured for transmitting a first wireless signal through a wireless multipath channel of a venue; a receiver configured for receiving a second wireless signal through the wireless multipath channel; and a processor. The second wireless signal comprises a reflection of the first wireless signal by a tip of a writing instrument in the venue. The processor is configured for: obtaining a time series of channel information (CI) of the wireless multipath channel based on the second wireless signal, wherein each CI comprises at least one of: a channel state information (CSI), channel impulse response (CIR), channel frequency response (CFR), or received signal strength index (RSSI); and tracking a movement of the tip of the writing instrument based on the time series of CI (TSCI).

Abstract: A neural network pruning system can sparsely prune neural network models using an optimizer based approach that is agnostic to the model architecture being pruned. The neural network pruning system can prune by operating on the parameter vector of the full model and the gradient vector of the loss function with respect to the model parameters. The neural network pruning system can iteratively update parameters based on the gradients, while zeroing out as many parameters as possible based a preconfigured penalty.

Abstract: System and methods for matching color and appearance of a target coating are provided herein. The system includes an electronic imaging device configured to receive a target image data of the target coating. The target image data includes target coating features. The system further includes one or more feature extraction algorithms that extracts the target image features from the target image data. The system further includes a machine-learning model that identifies a calculated match sample image from a plurality of sample images utilizing the target image features. The machine-learning model includes pre-specified matching criteria representing the plurality of sample images for identifying the calculated match sample image from the plurality of sample images. The calculated match sample image is utilized for matching color and appearance of the target coating.

Abstract: Methods and systems used for the classification of a crop grown within an agricultural field using remotely-sensed image data. In one example, the method involves unsupervised pixel clustering, which includes gathering pixel values and assigning them to clusters to produce a pixel distribution signal. The pixel distribution signals of the remotely-sensed image data over the growing season are summed up to generate a temporal representation of a management zone. Location information of the management zone is added to the temporal data and ingested into a Recurrent Neural Network (RNN). The output of the model is a prediction of the crop type grown in the management zone over the growing season. Furthermore, a notification can be sent to an agricultural grower or to third parties/stakeholders associated with the grower and/or the field, informing them of the crop classification prediction.

Abstract: Methods, apparatus and systems for periodic or transient motion detection, e.g. fall event detection, based on wireless signals are described. In one example, a described system comprises: a transmitter configured for transmitting a first wireless signal through a wireless multipath channel of a venue; a receiver configured for receiving a second wireless signal through the wireless multipath channel; and a processor. The second wireless signal differs from the first wireless signal due to the wireless multipath channel that is impacted by a target motion of an object in the venue. The processor is configured for: obtaining a time series of channel information (TSCI) of the wireless multipath channel based on the second wireless signal, computing a time series of spatial-temporal information (STI) of the object based on the TSCI, and detecting the target motion of the object based on the time series of STI (TSSTI).

Abstract: The measurement system 100 includes: a measurement apparatus 20 that measures vibrations of an object 40; an imaging apparatus 30 that is located so as to capture an image of the measurement apparatus 20; and a correction processing apparatus 10. the correction processing apparatus 10 includes: a displacement calculation unit 11 that calculates a displacement of the measurement apparatus 20 based on time-series images of the measurement apparatus 20 output from the imaging apparatus 30; a movement amount calculation unit 12 that calculates an amount of movement of the measurement apparatus 20 relative to the imaging apparatus 30, based on the displacement; and a correction processing unit 13 that corrects vibrations of the object measured by the measurement apparatus 20, using the calculated amount of movement of the measurement apparatus 20.

Abstract: An image processing apparatus including a division unit configured to divide first image data having a first dynamic range into a plurality of regions, an obtaining unit configured to obtain distance information indicating a distance from a focal plane in each of the plurality of regions, a determining unit configured to determine a conversion characteristic of each of the plurality of regions based on the distance information, a conversion unit configured to convert each of the plurality of regions into second image data having a second dynamic range smaller than the first dynamic range by using the conversion characteristic determined by the determining unit, and a storage unit configured to store a first conversion characteristic and a second conversion characteristic that can be used for the conversion.

Abstract: Systems and methods for spatial analysis of analytes are provided. A data structure is obtained comprising an image, as an array of pixel values, of a sample on a substrate having a identifier, fiducial markers and a set of capture spots. The pixel values are used to identify derived fiducial spots. The substrate identifier identifies a template having reference positions for reference fiducial spots and a corresponding coordinate system. The derived fiducial spots are aligned with the reference fiducial spots using an alignment algorithm to obtain a transformation between the derived and reference fiducial spots. The transformation and the template corresponding coordinate system are used to register the image to the set of capture spots. The registered image is then analyzed in conjunction with spatial analyte data associated with each capture spot, thereby performing spatial analysis of analytes.

Abstract: Methods, apparatus and systems for wireless tracking with graph-based particle filtering are described. A described wireless monitoring system comprises a transmitter transmitting a series of probe signals, a receiver, and a processor. The receiver is configured for: receiving the series of probe signals modulated by the wireless multipath channel and an object moving in a venue, and obtaining a time series of channel information (TSCI) of the wireless multipath channel from the series of probe signals. The processor is configured for: monitoring a motion of the object relative to a map based on the TSCI, determining an incremental distance travelled by the object in an incremental time period based on the TSCI, and computing a next location of the object at a next time in the map based on at least one of: a current location of the object at a current time, the incremental distance, and a direction of the motion during the incremental time period.

Abstract: Methods, apparatus and systems for wireless proximity sensing are described. In one example, a described system comprises: a transmitter configured for transmitting a first wireless signal through a wireless multipath channel of a venue; a receiver configured for receiving a second wireless signal through the wireless multipath channel; and a processor. The second wireless signal differs from the first wireless signal due to the wireless multipath channel that is impacted by a movement of an object in the venue.

Abstract: Methods, apparatus and systems for wirelessly tracking keystrokes on a surface are described. In one example, a described system comprises: a transmitter configured for transmitting, using a transmit antenna, a first wireless signal through a wireless channel of a venue including the surface; a receiver configured for receiving, using a plurality of receive antennas, a second wireless signal through the wireless channel, wherein the second wireless signal comprises a reflection of the first wireless signal by at least one moving object in the venue; and a processor.

Abstract: A system, method, and computer-readable storage medium, of which the method includes receiving an image of a tool including a consumable object from a remote device via a network at a processor, decoding the image to identify the consumable object, using the processor, and determining a degradation characteristic, a consumption, or both for the consumable object by providing the decoded image to a neural network. The degradation characteristic represents a mode of degradation and the consumption represents an amount of degradation.

Abstract: According to one aspect of the present disclosure, a method is disclosed in a user equipment (UE) for performing downlink measurements on a plurality of cells according to a received measurement configuration. The UE receives measurement configuration information from a radio base station supporting a serving cell of a wireless communications network, the measurement configuration information including an indication of a variably sized measurement bandwidth over which measurements are to be performed on the serving cell and one or more neighbor cells. The UE performs measurements on each of the serving cell and the one or more neighbor cells over the measurement bandwidth, and reports the measurements to the network.