An image classification method is provided to an electronic device. The method includes: receiving a target image and a reference image about the target image, the target image being a medical image; determining a first image feature of the target image and a second image feature of the reference image; fusing the first image feature and the second image feature to determine a to-be-classified image feature; and determining, by using the to-be-classified image feature, a probability that the target image belongs to a preset category.

A gesture language recognition method is provided. In the method, a first video is obtained. Gesture features are extracted from frames of images in the first video. Gesture change features are extracted from the frames of the images in the first video. Gesture language word information is extracted from fused features that are determined based on the gesture features and the gesture change features. The gesture language word information is combined into a gesture language sentence according to context information corresponding to the gesture language word information.

A driving assistance device according to an embodiment includes a hardware processor and a memory, in which the hardware processor is configured to execute: acquiring image data captured in a vehicle and sensor data relating to a driving operation; converting an image in each frame included in the image data into an image feature amount indicated by the image; combining the image feature amount and the acquired sensor data; performing, based on the combined data, a learning process for a driving assistance information learning model used when a target value relating to the driving operation by a driver of the vehicle is generated from the image feature amount included in the combined data; and generating, when new image data captured in the running vehicle is acquired, the target value relating to the driving operation based on the image feature amount converted from the acquired new image data and the driving assistance information learning model.

A fundus image processing method comprising: receiving a collected fundus image; identifying the fundus image via a first neural network to generate a first feature set of the fundus image; identifying the fundus image via a second neural network to generate a second feature set of the fundus image, wherein the first feature set and the second feature set indicate different lesion attributes of the fundus image; combining the first feature set and the second feature set to obtain a combined feature set of the fundus image; and inputting the combined feature set into a classifier to obtain a classification result.

A spoofing detection apparatus comprises obtaining, from an image capture apparatus, a first image frame that includes the face of a subject person obtained when a light-emitting apparatus is emitting light and a second image frame that includes the face of the subject person obtained when the light-emitting apparatus is turned off, extracting, from the first image frame, information specifying a face portion of the subject person, and extract, from the second image frame, information specifying a face portion of the subject person, extracting a portion that includes a bright point formed by reflection in an iris region of an eye of the subject person, from the first image frame, extracts a portion corresponding to the portion that includes the bright point, from the second image frame, and calculates a feature that is independent of the position of the bright point, and determining authenticity of subject person based on the feature.

A computer-implemented method for determining image similarity includes determining, by a first neural network, a first feature value associated with a first characteristic of a first product based on an image of the first product. The method also includes determining, by a second neural network, a second feature value associated with a second characteristic of the first product based on the image of the first product. The method further involves calculating a first vector space distance between the first feature value and a third feature value associated with the first characteristic of a second product, and calculating a second vector space distance between the second feature value and a fourth feature value associated with the second characteristic of the second product. Additionally, the method includes determining a similarity value based on the first vector space distance and the second vector space distance.

A UI for a HMD system includes a HMD configured to be worn by a surgeon. A tracker is configured to track head gestures by the surgeon. A footswitch is configured to detect foot motion inputs by the surgeon. A computer couples to the HMD, the tracker, and the footswitch. A user interface includes the HMD, tracker, and footswitch. The use interface is configured to: provide to the computer the head gesture in association with the foot motion input, and display an image relating to a surgical procedure on the HMD. The computer is configured to: apply the head gesture received in association with the foot motion input to perform a first action on the HMD system when the HMD system is in a first system mode, and perform a second action on the HMD system when the HMD system is in a second system mode.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using a surfel map to generate a prediction for a state of an environment. One of the methods includes obtaining surfel data comprising a plurality of surfels, wherein each surfel corresponds to a respective different location in an environment, and each surfel has associated data that comprises an uncertainty measure; obtaining sensor data for one or more locations in the environment, the sensor data having been captured by one or more sensors of a first vehicle; determining one or more particular surfels corresponding to respective locations of the obtained sensor data; and combining the surfel data and the sensor data to generate a respective object prediction for each of the one or more locations of the obtained sensor data.

A vehicle includes one or more cameras that capture a plurality of two-dimensional images of a three-dimensional object. A light detector and/or a semantic classifier search within those images for lights of the three-dimensional object. A vehicle signal detection module fuses information from the light detector and/or the semantic classifier to produce a semantic meaning for the lights. The vehicle can be controlled based on the semantic meaning. Further, the vehicle can include a depth sensor and an object projector. The object projector can determine regions of interest within the two-dimensional images, based on the depth sensor. The light detector and/or the semantic classifier can use these regions of interest to efficiently perform the search for the lights.

A method of determining footprint identity using a dimension reduction algorithm according to an embodiment includes: pre-processing to process three-dimensional (3D) image data about footprints of a first person and a second person and convert the 3D image data into one-dimensional (1D) data about the footprints of the first person and the second person; calculating a distribution of cross-correlation coefficients between two pieces of 1D data about footprints of the first person (SC: same footwear correlation) and a distribution of cross-correlation coefficients between the 1D data about the footprints of the first person and the second person (DC: difference footwear correlation); and calculating a likelihood ratio based on the SC and the DC to determine the degree of correspondence between the footprints of the first person and the second person.