Abstract: Various methods an apparatus to use facial recognition in a computing device are disclosed. In one aspect, a method of controlling a component of a computing device is provided. The method includes taking an IR image of a user and a background with an IR sensor of a computing device. The computing device is in a location. The IR image is segmented into user image data and background image data. An ambient temperature of the location is determined using the background image data. An aspect of the component is controlled based on the ambient temperature.

Abstract: A method for training a polyhedral classifier is described including obtaining training data in a data space, the training data including first data points associated with a first label and second data points associated with a second label, determining a pair of hyperplanes by determining an orientation of the pair of hyperplanes based on a minimization of a distance between the pair of hyperplanes such that the first data points lie between the hyperplanes in relation to a distance between the pair of hyperplanes such that both the first data points and the second data points lie between the hyperplanes and determining the position of the pair of hyperplanes such that the first data points lie between the pair of hyperplanes and the second data points are at least partially separated from the first data points by the pair of hyperplanes.

Abstract: In an approach for identifying a crop using satellite observation data and crop rotation data, a processor receives an aerial image of one or more agricultural fields in a pre-determined geographical region from an optical satellite. A processor selects a plurality of points from the aerial image. A processor clips the aerial image into one or more smaller images to generate one or more observed signatures. A processor determines there is a change in a spatial distribution of one or more crops. A processor generates an actual signature from the one or more observed signatures. A processor cross-correlates the actual signature against a plurality of historical reference signatures to determine a degree of similarity. A processor ranks one or more results of the cross-correlation. A processor identifies the one or more crops. A processor calculates a first estimate of an amount of the one or more crops.

Abstract: The disclosure provides an image clustering method and an image clustering apparatus. The method includes: obtaining new images, and clustering the new images to obtain a first cluster; determining a historical cluster similar to the first cluster as a second cluster from existing historical clusters; obtaining a distance between the first cluster and the second cluster; and generating a target cluster by fusing the first cluster and the second cluster based on the distance. In the image clustering method, with the image clustering apparatus of the disclosure, secondary clustering processing performed on the existing historical clusters based on newly added images is not required, new and old clusters are directly fused.

Abstract: An emotion determination device includes a memory and a processor connected to the memory. The processor is configured to acquire a facial image of a user, set an evaluation value for each of plural emotion classifications including a neutral state based on the acquired facial image, compute a correction value using an evaluation value set based on a neutral facial image acquired at a timing corresponding to a neutral state, and determine an emotion of the user by applying the computed correction value to the set evaluation values.

Abstract: An image data frame is received from an external source. An error concealment operation is performed on the received image data frame in response to determining that a first frame size of the received image data frame is erroneous. The first frame size of the image data frame is determined to be erroneous based on at least one frame synchronization signal associated with the image data frame. An image processing operation is performed on the received image data frame on which the error concealment operation has been performed, thereby enabling an image processing module to perform the image processing operation without entering into a deadlock state and thereby prevent a host processor from having to execute hardware resets of deadlocked modules.

Abstract: An electronic data processor is configured to identify the component pixels of a harvestable plant component within the obtained image data of plant pixels of the one or more target plants. An edge, boundary or outline of the component pixels is determined. The data processor is configured to detect a size of the harvestable plant component based on the determined edge, boundary or outline of the identified component pixels. A user interface is configured to provide an aggregate, sectional yield, or per row yield based on a detected size of the harvestable plant component for the one or more target plants as an indicator of yield of the one or more plants or standing crop in the field.

Abstract: An image processing method, an image processing device, an electronic device, and a storage medium are provided. The image processing method includes: obtaining an input image, wherein the input image includes M character rows; performing global correction processing on the input image to obtain an intermediate corrected image; determining the M character row lower boundaries; determining the relative offset of all pixels in the intermediate corrected image according to the M character row lower boundaries, the first image boundary and the second image boundary of the intermediate corrected image; determining the local adjustment offset of all pixels in the intermediate corrected image according to the relative offsets of all pixels in the intermediate corrected image; and performing local adjustment on the intermediate corrected image according to the local adjustment offsets of all pixels in the intermediate corrected image to obtain the target corrected image.

Abstract: Systems and methods for selecting data for training a machine learning model using active learning are disclosed. The methods include receiving a plurality of unlabeled sensor data logs corresponding to surroundings of an autonomous vehicle, identifying one or more trends associated with a training dataset comprising a plurality of labeled data logs, determining a function for assigning an importance score to each of the plurality of unlabeled sensor data logs, using the one or more trends, using the function for assigning the importance score to each of the plurality of unlabeled sensor data logs, selecting a subset of the plurality of sensor data logs that have an importance score greater than a threshold, and using the subset of the plurality of sensor data logs for further training the machine learning model trained using the training dataset to generate an updated model.

Abstract: An analyzing apparatus extracts, from a food image, food information relating to types and served states of foods included in the food image and an edible portion of each food, calculates an area ratio between the edible portion of the same kind of food extracted from a plurality of food images acquired at different timings, stores conversion information for converting the area ratio into a volume ratio corresponding to each type and served state of food, and converts the area ratio of each food into a volume ratio using the stored conversion information corresponding to the food whose area ratio is to be converted from among the stored conversion information based on the food information.

Abstract: A computer-implemented method of signal processing comprises providing images. The method comprises for each respective one of at least a subset of the images: applying a weakly-supervised learnt function, the weakly-supervised learnt function outputting respective couples each including a respective localization and one or more respective confidence scores, each confidence score representing a probability of instantiation of a respective object category at the respective localization. The method further comprises determining, based on the output of the weakly-supervised learnt function, one or more respective annotations, each annotation including a respective localization and a respective label representing instantiation a respective object category at the respective localization. The method further comprises forming a dataset including pieces of data, each piece of data including a respective image of the subset and at least a part of the one or more annotations determined for the respective image.

Abstract: The disclosed technology provides solutions for detecting and localizing road signage, such as speed limit signs. A process of the disclosed technology can include steps for receiving a first set of sensor data comprising a signage feature, wherein the first set of sensor data is associated with a first location, receiving a second set of sensor data comprising the signage feature, wherein the second set of sensor data is associated with a second location, and determining a location of the signage feature based on the first location and the second location. Systems and machine-readable media are also provided.

Abstract: Systems and methods are provided for. One embodiment is a system that includes an interface configured to receive an image of media printed on with print data, and memory configured to store defect reference data of nozzles belonging to printheads of a printer. The system also includes a print defect controller configured to detect a nozzle defect in the image based on a comparison of the image with the print data, and to determine a type of the nozzle defect based on a comparison of the nozzle defect with the defect reference data.

Abstract: Systems, methods, and computer-readable media are disclosed for improved camera color calibration. An example method may involve capturing a first wavelength emitted by a first type of traffic light. The example method may also involve determining, based on the first wavelength, a first color value associated with the wavelength emitted by the first type of traffic light. The example method may also involve capturing, by a first camera, a first image, video, or real-time feed of a first portion of a test target, the first portion of the test target including a first light color that is based on the first color value. The example method may also involve determining, based on the first image, video, or real-time feed of the first portion of a test target, a second color value output by the camera. The example method may also involve determining, based on a comparison between the first color value and the second color value, that a difference exists between the first color value and the second color value.

Abstract: Systems and techniques that facilitate synthetic training data generation for improved machine learning generalizability are provided. In various embodiments, an element augmentation component can generate a set of preliminary annotated training images based on an annotated source image. In various aspects, a preliminary annotated training image can be formed by inserting at least one element of interest or at least one background element into the annotated source image. In various instances, a modality augmentation component can generate a set of intermediate annotated training images based on the set of preliminary annotated training images. In various cases, an intermediate annotated training image can be formed by varying at least one modality-based characteristic of a preliminary annotated training image. In various aspects, a geometry augmentation component can generate a set of deployable annotated training images based on the set of intermediate annotated training images.

Abstract: The technology disclosed relates to classification of process cycle images to predict success or failure of process cycles. The technology disclosed includes capturing and processing images of sections arranged on an image generating chip in genotyping process. Image description features of production cycle images are created and given as input to classifiers. A trained classifier separates successful production images from unsuccessful or failed production images. The failed production images are further classified by a trained root cause classifier into various categories of failure.

Abstract: A computer-implemented clustering method is disclosed for image segmentation, social network analysis, computational biology, market research, search engine and other applications. At the heart of the method is a point-set kernel that measures the similarity between a data point and a set of data points. The method has a procedure that employs the point-set kernel to expand from a seed point to a cluster; and finally identifies all clusters in the given dataset. Applying the method for image segmentation, it identifies several segments in the image, where points in each segment have high similarity: but points in one segment have low similarity with respect to other segments. The method is both effective and efficient that enables it to deal with large scale datasets. In contrast, existing clustering methods are either efficient or effective; and even efficient ones have difficulty dealing with large scale datasets without massive parallelization.

Abstract: A method and system for crop health change monitoring is provided. The method includes acquiring a companion image of a crop growing within a field at a first point in time, acquiring a master image of the crop growing within the field at a second point in time, and computing, using a processor, vegetation indices using the master image and the companion image for subsequently determining regions of change within the master image. An alert condition is determined if change within one or more of the regions of change is sufficient to meet defined criteria. If a minimum field area threshold is met, a modulation coefficient is applied to the defined criteria that determines the alert condition. The coefficient reduces area-based thresholds used in health detection in a manner proportional to the size of the agricultural field of interest.

Abstract: A system first registers a two-dimensional image to targetable three-dimensional data. A user or automated process selects image coordinates of a target within the registered two-dimensional image. The system intersects the image coordinates of the target with the targetable three-dimensional data, thereby generating geodetic coordinates of the target in a point cloud. Error estimates for the geodetic coordinates of the target are generated, and the system stores the geodetic coordinates and associated error of the target in a database for use in downstream exploitation.

Abstract: A method for deblurring a target image includes receiving a burst of images that includes the target image; partitioning respective images of the burst of images into respective patches; converting, to a frequency domain, the respective patches into respective transform patches; selecting a first set of corresponding transform patches from the respective transform patches, where the first set of the corresponding transform patches includes a respective transform patch for a respective image of the burst of images; obtaining, using a neural network, respective weight maps for the corresponding transform patches; obtaining a deblurred transform patch by combining the first set of corresponding transform patches using the respective weight maps; obtaining a first deblurred patch by converting the deblurred transform patch to a pixel domain; and obtaining a deblurred image of the target image using the first deblurred patch.