A method of identifying, with a camera, an object in an image of a scene, by determining the distinctiveness of each of a number of attributes of an object of interest, independent of the camera viewpoint, determining the detectability of each of the attributes based on the relative orientation of a candidate object in the image of the scene, determining a camera setting for viewing the candidate object based on the distinctiveness of an attribute, so as to increase the detectability of the attribute, and capturing an image of the candidate object with the camera setting to determine the confidence that the candidate object is the object of interest.

A method of detecting objects of interest in a vehicle image processing system comprising: a) capturing an image on a camera; b) providing a plurality of potential candidate windows by running a detection window at spatially different locations along said image, and repeating this at different image scaling relative to the detection window size; c) for each potential candidate window applying a candidate selection process adapted to select one or more candidates from said potential candidate windows; d) forwarding the candidates determined form step c) to a convolutional neural network (CNN) process; e) processing the candidates to identify objects of interest; characterized wherein the candidate input into the convolutional neural network (CNN) process have been resized by step b).

A computer-implemented method of grouping faces in large user account for creating an image product includes adding the face images obtained from an image album in a user's account into a first chunk; if the chunk size of the first chuck is smaller than a maximum chuck value, keeping the face images from the image album into the first chunk; otherwise, automatically separating the face images from the image album into a first portion and one or more second portions; keeping the first portion in the first chunk; automatically moving the second portions to subsequent chunks; automatically grouping face images in the first chunk to form face groups; assigning the face groups to known face models associated with the user account; and creating a design for an image-based product based on the face images in the first chunk associated with the face models.

A machine learning model is trained by defining a scenario including models of vehicles and a typical driving environment. A model of a subject vehicle is added to the scenario and sensor locations are defined on the subject vehicle. A perception of the scenario by sensors at the sensor locations is simulated. The scenario further includes a model of a parked vehicle with its engine running. The location of the parked vehicle and the simulated outputs of the sensors perceiving the scenario are input to a machine learning algorithm that trains a model to detect the location of the parked vehicle based on the sensor outputs. A vehicle controller then incorporates the machine learning model and estimates the presence and/or location of a parked vehicle with its engine running based on actual sensor outputs input to the machine learning model.

A page orientation component of an image processing device receives an image of a document, transforms the image to a binarized image by performing a binarization operation on the image, and identifies a portion of the binarized image that comprises one or more rows of textual content. The page orientation component identifies a plurality of horizontal runs of white pixels and a plurality of vertical runs of white pixels in the one or more rows of textual content in the portion of the binarized image. The page orientation component generates a first histogram for the plurality of horizontal runs of white pixels, and a second histogram for the plurality of vertical runs of white pixels, and determines an orientation of the one or more rows of textual content in the image based on the first histogram and the second histogram.

Aspects of the technology described herein relate to techniques for guiding an operator to use an ultrasound device. Thereby, operators with little or no experience operating ultrasound devices may capture medically relevant ultrasound images and/or interpret the contents of the obtained ultrasound images. For example, some of the techniques disclosed herein may be used to identify a particular anatomical view of a subject to image with an ultrasound device, guide an operator of the ultrasound device to capture an ultrasound image of the subject that contains the particular anatomical view, and/or analyze the captured ultrasound image to identify medical information about the subject.

A method and system for detecting eye corners using neural network classifiers is described. After an eye image is received, the eye image may be processed by at least two neural network classifiers including an inner eye corner neural network classifier and an outer eye corner neural network classifier. The neural network classifiers provide periocular information including a distance or coordinates of an eye corner location from a center of an iris of the eye, and an outcome of whether the eye corner is an inner eye corner or an outer eye corner. Output from the various neural network classifiers are combined to generate a decision on the location of eye corners in an eye image.

A method or system is capable of detecting operator behavior (“OB”) utilizing a virtuous cycle containing sensors, machine learning center (“MLC”), and cloud based network (“CBN”). In one aspect, the process monitors operator body language captured by interior sensors and captures surrounding information observed by exterior sensors onboard a vehicle as the vehicle is in motion. After selectively recording the captured data in accordance with an OB model generated by MLC, an abnormal OB (“AOB”) is detected in accordance with vehicular status signals received by the OB model. Upon rewinding recorded operator body language and the surrounding information leading up to detection of AOB, labeled data associated with AOB is generated. The labeled data is subsequently uploaded to CBN for facilitating OB model training at MLC via a virtuous cycle.

Embodiments of the invention(s) described herein enable a system that may rely on a biometric identifier entry validation system. The validation system “learns” the use pattern of a user. The validation system uses biometric methods such as facial recognition, palm veins, and thumb prints as an entry or passage token. When enough data has been collected, the validation system sends the user's biometric identifier to the use location within a bounded time frame when it expects a regular user to arrive at that location and within that time frame. In this manner the biometric identifier becomes a biometric token that replaces the need to use a form of fare media. Thus, the validation system becomes more efficient and recognizes a user faster after collecting data of a user for a short time. The validations system can record and interpret historic data. With this data, the validation system knows, on average, when to expect that passenger to arrive and where.

An approach is provided for classifying objects that are present at a geo-location and providing an uncluttered presentation of images of some of the objects in an application such as a map application. The approach includes determining one or more regions of interest associated with at least one geo-location, wherein the one or more regions of interest are at least one textured three-dimensional representation of one or more objects that may be present at the at least one geo-location. The approach also includes processing and/or facilitating a processing of the at least one textured three-dimensional representation to determine at least one two-dimensional footprint and three-dimensional geometry information for the one or more objects. The approach further includes causing, at least in part, a generation of at least one two-dimensional image representation of the one or more regions of interest by causing, at least in part, a projection of three-dimensional texture information of the at least one textured three-dimensional representation onto the at least one two-dimensional footprint. The approach also includes causing, at least in part, a classification of the one or more objects based, at least in part, on the at least one two-dimensional image representation and the three-dimensional geometry information.