Methods, systems, and processor-readable media for the detection and classification of license plates. In an example embodiment, an image of a vehicle can be captured with an image-capturing unit. A license plate region can then be located in the captured image of the vehicle by extracting a set of candidate regions from the image utilizing a weak classifier. A set of candidate regions can be ranked utilizing a secondary strong classifier. The captured image can then be classified according to a confidence driven classification based on classification criteria determined by the weak classifier and the secondary strong classifier.

An image pickup device transmits to a server a transmission sample including a detection image detected by a first detection section from a transmitting/receiving section under the control of a transmission sample control section. The server performs detection processing that requires more resources than those of the first detection section on the detection image transmitted by a second detection section from the image pickup device, and determines whether or not the detection image in question is spurious, based on a second detection score which is thereby obtained. A transmission frequency deciding section generates transmission frequency control information such as to raise the transmission frequency by an image pickup device that has a high frequency of spurious detection; a transmitting/receiving section transmits the transmission frequency control information to the image pickup device.

Provided are a learning method, a learning device, a generative model, and a program that generate an image including high resolution information without adjusting a parameter and largely correcting a network architecture even in a case in which there is a variation of the parts of an image to be input. Only a first image is input to a generator of a generative adversarial network that generates a virtual second image having a relatively high resolution by using the first image having a relatively low resolution, and a second image for learning or the virtual second image and part information of the second image for learning or the virtual second image are input to a discriminator that identifies the second image for learning and the virtual second image.

Disclosed in the present invention are a method and a system for monitoring unmanned aerial vehicles based on three-dimensional light field technology. Provided is an unmanned aerial vehicle monitoring method based on three-dimensional light field technology, comprising: beginning unmanned aerial vehicle monitoring; by means of a light field camera, acquiring low resolution video image information; determining whether the acquired video image information is an unmanned aerial vehicle; performing graphic reconstruction on an unmanned aerial vehicle image therein; and acquiring reconstructed light field image depth and position information to monitor the unmanned aerial vehicle and emitting an alert. The method and the system for monitoring in the present invention are able to acquire a clear stereoscopic image, thus raising efficiency and accuracy in the process of unmanned aerial vehicle monitoring or detection.

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 method for processing breast tissue image data includes processing the image data to generate a set of image slices collectively depicting the patient's breast; for each image slice, applying one or more filters associated with a plurality of multi-level feature modules, each configured to represent and recognize an assigned characteristic or feature of a high-dimensional object; generating at each multi-level feature module a feature map depicting regions of the image slice having the assigned feature; combining the feature maps generated from the plurality of multi-level feature modules into a combined image object map indicating a probability that the high-dimensional object is present at a particular location of the image slice; and creating a 2D synthesized image identifying one or more high-dimensional objects based at least in part on object maps generated for a plurality of image slices.

Techniques for saving bandwidth in performing facial recognition are provided. An image including a face may be received, over a wireless link, at a first resolution. A facial recognition system may identify a subset of people who may be associated with the face, wherein the facial recognition system cannot definitively associate the face with an individual person in the subset of people, based on the image including the face at the first resolution. A feature of the subset of people that may be used to identify a person within the subset of people may be determined. A request for the portion of the image containing the feature at a second resolution may be sent over the wireless link. The second resolution may be higher than the first.

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.

Aspects of the subject matter disclosed herein include methods, systems, and other techniques for training, in a first phase, an object classifier neural network with a first set of training data, the first set of training data including a first plurality of training examples, each training example in the first set of training data being labeled with a coarse-object classification; and training, in a second phase after completion of the first phase, the object classifier neural network with a second set of training data, the second set of training data including a second plurality of training examples, each training example in the second set of training data being labeled with a fine-object classification.

A method comprising performing object detection within a set of representations of a hierarchically-structured signal, the set of representations comprising at least a first representation of the signal at a first level of quality and a second representation of the signal at a second, higher level of quality.