A method of generating an image recognition model for recognising an input image and a system thereof are provided. The method includes appending at least one feature extraction layer to the image recognition model, extracting a plurality of feature vectors from a set of predetermined images, grouping the plurality of feature vectors into a plurality of categories, clustering the plurality of feature vectors of each of the plurality of categories into at least one cluster, determining at least one centroid for each of the at least one cluster, such that each of the at least one cluster comprises at least one centroid, such that each of the at least one centroid is represented by a feature vector, generating a classification layer based on the feature vector of the at least one centroid of the plurality of categories, and appending the classification layer to the image recognition model. In addition, a method of classifying an input image and a system thereof are provided.

In various examples, potentially highlight-worthy video clips are identified from a gameplay session that a gamer might then selectively share or store for later viewing. The video clips may be identified in an unsupervised manner based on analyzing game data for durations of predicted interest. A classification model may be trained in an unsupervised manner to classify those video clips without requiring manual labeling of game-specific image or audio data. The gamer can select the video clips as highlights (e.g., to share on social media, store in a highlight reel, etc.). The classification model may be updated and improved based on new video clips, such as by creating new video-clip classes.

Embodiments include techniques to determine a set of credit risk assessment data samples, generate local credit risk assessment attributions for the set of credit risk assessment samples, and normalize each local credit risk assessment attribution of the local credit risk assessment attributions. Further, embodiments techniques to compare each pair of normalized local credit risk assessment attributions and assign a rank distance thereto proportional to a degree of ranking differences between the pair of normalized local credit risk assessment attributions. The techniques also include applying a K-medoids clustering algorithm to generate clusters of the local risk assessment attributions, generating global attributions, and determining insights for the neural network based on the global attributions.

An acquisition unit (15a) detects an operation event of a user to acquire an occurrence position of the operation event in an operation screen and a captured image of the operation screen. An extraction unit (15b) extracts images that are able to become candidates for a GUI part from the acquired captured image, identifies which image the operation event has occurred on from the occurrence position of the operation event, and records an occurrence clock time of the operation event and the identified image in an associated manner. A classification unit (15c) classifies a group of recorded images into clusters in accordance with similarities of the images. A determination unit (15d) adds up the number of times the operation event has occurred in the images for each classified cluster, and in a case in which the aggregated value is equal to or greater than a predetermined threshold value, determines an image included in the cluster as an image of the GUI part that is an operation target at the occurrence clock time of the operation event.

The present disclosure relates to the field of image processing and discloses an agricultural advisory system (100) comprising a user device (102) and a cloud server (104). The user device (102) captures a digital image of a scene, receives a sensed data corresponding to scene-related and environmental parameters, and transmits the image and the sensed data to the cloud server. The server (104) stores one or more pre-trained prediction models and a three-dimensional HyperIntelliStack which maps red green blue (RGB) pixel values with hyperspectral reflectance values. The server (104) receives the digital images and the sensed data, transforms the received image made of RGB pixel values into a hyperspectral image using the HyperIntelliStack data structure, computes vegetation indices for each pixel of the hyperspectral image to generate a segmented image, and generates at least one advisory for agriculture and allied areas using the segmented image and one or more prediction models.

The present disclosure is directed towards methods and systems for determining multimodal image edits for a digital image. The systems and methods receive a digital image and analyze the digital image. The systems and methods further generate a feature vector of the digital image, wherein each value of the feature vector represents a respective feature of the digital image. Additionally, based on the feature vector and determined latent variables, the systems and methods generate a plurality of determined image edits for the digital image, which includes determining a plurality of set of potential image attribute values and selecting a plurality of sets of determined image attribute values from the plurality of sets of potential image attribute values wherein each set of determined image attribute values comprises a determined image edit of the plurality of image edits.

Methods, systems, and non-transitory computer readable media for analyzing type curve regions in a subsurface volume of interest are disclosed. Exemplary implementations may include: obtaining initial clusters of type curve regions in the subsurface volume of interest; obtaining production values as a function of position; generating an autocorrelation correction factor; attributing the autocorrelation correction factor to the production values as a function of position; generating type curve mean values; generating range distribution values; generating a type curve cluster probability value for each of the type curve regions; generating a first representation of the type curve regions as a function of position; clustering the type curve regions in updated clusters; generating a second representation of the type curve regions as a function of position; and displaying one or more of the first representation and the second representation.

An apparatus for providing anonymity in geographic data for probe devices in a geographic region for a location-based service includes at least a database, a clustering calculator and an anonymity controller. The database stores trajectory data based on sequences of sensor measurements of the probe devices. The clustering calculator clusters the trajectory data, according to a first iteration threshold, into clusters each defined by a cluster point and compares distance for a first cluster from the clusters to cluster points of other clusters of the clusters. The clustering calculator selects a second cluster from the clusters based on the comparison of distances and merges the first cluster and the second cluster into a merged cluster. The anonymity controller modifies the trajectory data to provide a predetermined level of anonymity to locations from the trajectory data in response to the merged cluster.

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.

The present disclosure provides a system for monitoring unstructured environments. A predetermined path can be determined according to an assignment of geolocations to one or more agronomically anomalous target areas, where the one or more agronomically anomalous target areas are determined according to an analysis of a plurality of first images that automatically identifies a target area that deviates from a determination of an average of the plurality of first images that represents an anomalous place within a predetermined area, where the plurality of first images of the predetermined area are captured by a camera during a flight over the predetermined area. A camera of an unmanned vehicle can capture at least one second image of the one or more agronomically anomalous target areas as the unmanned vehicle travels along the predetermined path.