A computer-implemented method for generating a feature descriptor for a location in an image for use in performing descriptor matching in analysing the image, the method comprising determining a set of samples characterising a location in an image by sampling scale-space data representative of the image, the scale-space data comprising data representative of the image at a plurality of length scales; and generating a feature descriptor in dependence on the determined set of samples.

A computer-implemented method of determining an explainability mask for classification of an input image by a trained neural network. The trained neural network is configured to determine the classification and classification score of the input image by determining a latent representation of the input image at an internal layer of the trained neural network. The method includes accessing the trained neural network, obtaining the input image and the latent representation thereof and initializing a mask for indicating modifications to the latent representation. The mask is updated by iteratively adjusting values of the mask to optimize an objective function, comprising i) a modification component indicating a degree of modifications indicated by the mask, and ii) a classification score component, determined by applying the indicated modifications to the latent representation and determining the classification score thereof. The mask is scaled to a spatial resolution of the input image and output.

Systems and methods are provided for embedded data inference. The systems and methods may process camera and other sensor data in by leveraging processing and storage capacity of one or more devices nearby or in the cloud to augment or update the sensor processing of an embedded device. The joint processing may be used in stationary cameras or in vehicular systems such as cars and drones, and may improve crop assessments, navigation, and safety.

A system for image segmentation is provided. The system may obtain a target image including an ROI, and segment a preliminary region representative of the ROI from the target image using a first ROI segmentation model corresponding to a first image resolution. The system may segment a target region representative of the ROI from the preliminary region using a second ROI segmentation model corresponding to a second image resolution. At least one model of the first and second ROI segmentation models may at least include a first convolutional layer and a second convolutional layer downstream to the first convolutional layer. A count of input channels of the first convolutional layer may be greater than a count of output channels of the first convolutional layer, and a count of input channels of the second convolutional layer may be smaller than a count of output channels of the second convolutional layer.

An object detection device detects a predetermined object from an image. The object detection device includes a first detection unit configured to detect a plurality of candidate regions where the predetermined object exists from the image, a region integrating unit configured to determine one or a plurality of integrated regions according to the plurality of candidate regions detected by the first detection unit, and a second detection unit configured to detect, in the one or the plurality of integrated regions, the predetermined object by using a detection algorithm different from an algorithm of the first detection unit. As a result, it is possible to detect the predetermined object faster and more accurately than before.

Systems and methods are described for dynamically adjusting an amount of retrieved recognition data based on the needs of a show, experience, or other event where participants are recognized. The retrieved recognition data may be deleted once it is no longer needed for the event. Recognition data retrieval is limited to just what is needed for the particular task, minimizing the uniqueness of any retrieved recognition data to respect participant privacy while providing an enhanced participant experience through recognition.

Methods and systems for automatic estimation of object characteristics from a digital image are disclosed, including a method comprising sub-dividing into two or more segments a digital image comprising pixels and depicting an object of interest, wherein each segment comprises two or more pixels; assessing content depicted in one or more of the segments for a predetermined object characteristic using machine learning techniques comprising General Image Classification of the one or more segments using a convolutional neural network, wherein the General Image Classification comprises analyzing the segment as a whole and outputting a general classification for the segment as a whole as related to the one or more predetermined object characteristic; and determining a level of confidence of one or more of the segments having the one or more predetermined object characteristic based on the General Image Classification assessment.

Methods, systems, and computer program products for vision-based cell structure recognition using hierarchical neural networks and cell boundaries to structure clustering are provided herein. A computer-implemented method includes detecting a style of the given table using at least one style classification model; selecting, based at least in part on the detected style, a cell detection model appropriate for the detected style; detecting cells within the given table using the selected cell detection model; and outputting, to at least one user, information pertaining to the detected cells comprising image coordinates of one or more bounding boxes associated with the detected cells.

Provided are a method and apparatus for extracting information about a negotiable instrument, an electronic device and a storage medium. The method includes inputting a to-be-recognized negotiable instrument into a pretrained deep learning network and obtaining a visual image corresponding to the to-be-recognized negotiable instrument through the deep learning network;

matching the visual image corresponding to the to-be-recognized negotiable instrument with a visual image corresponding to each negotiable-instrument template in a preconstructed base template library; and in response to the visual image corresponding to the to-be-recognized negotiable instrument successfully matching a visual image corresponding to one negotiable-instrument template in the base template library, extracting structured information of the to-be-recognized negotiable instrument by using the negotiable-instrument template.

Disclosed are a method and apparatus for identifying versions of a form. In an example, clients of a medical company fill out many forms, and many of these forms have multiple versions. The medical company operates in 10 states, and each state has a different version of a client intake form, as well as of an insurance identification form. In order to automatically extract information from a particular filled out form, it may be helpful to identify a particular form template, as well as the version of the form template, of which the filled out form is an instance. A computer system evaluates images of filled out forms, and identifies various form templates and versions of form templates based on the images.