Intelligent multi-scale image parsing determines the optimal size of each observation by an artificial agent at a given point in time while searching for the anatomical landmark. The artificial agent begins searching image data with a coarse field-of-view and iteratively decreases the field-of-view to locate the anatomical landmark. After searching at a coarse field-of view, the artificial agent increases resolution to a finer field-of-view to analyze context and appearance factors to converge on the anatomical landmark. The artificial agent determines applicable context and appearance factors at each effective scale.

A machine learning image processing system performs natural language processing (NLP) and auto-tagging for an image matching process. The system facilitates an interactive process, e.g., through a mobile application, to obtain an image and supplemental user input from a user to execute an image search. The supplemental user input may be provided from a user as speech or text, and NLP is performed on the supplemental user input to determine user intent and additional search attributes for the image search. Using the user intent and the additional search attributes, the system performs image matching on stored images that are tagged with attributes through an auto-tagging process.

An image classification method is provided. The method includes: inputting a to-be-classified image into a plurality of neural network models; obtaining data output by multiple non-input layers specified by each neural network model to generate a plurality of image features corresponding to the plurality of neural network models; respectively inputting the plurality of corresponding image features into linear classifiers, each of the linear classifiers being trained by one of the plurality of neural network models for determining whether an image belongs to a preset class; obtaining, using each neural network model, a corresponding probability that the to-be-classified image comprises an object image of the preset class; and determining, according to each obtained probability, whether the to-be-classified image includes the object image of the preset class.

The present disclosure is directed toward systems and methods that enable more accurate digital object classification. In particular, disclosed systems and methods address inaccuracies in digital object classification introduced by variations in classification scores. Specifically, in one or more embodiments, disclosed systems and methods generate probability functions utilizing digital test objects and transform classifications scores into normalized classification scores utilizing probability functions. Disclosed systems and methods utilize normalized classification scores to more accurately classify and identify digital objects in a variety of applications.

The present invention includes computer vision based driver assistance devices, systems, methods and associated computer executable code (hereinafter collectively referred to as: “ADAS”). According to some embodiments, an ADAS may include one or more fixed image/video sensors and one or more adjustable or otherwise movable image/video sensors, characterized by different dimensions of fields of view. According to some embodiments of the present invention, an ADAS may include improved image processing. According to some embodiments, an ADAS may also include one or more sensors adapted to monitor/sense an interior of the vehicle and/or the persons within. An ADAS may include one or more sensors adapted to detect parameters relating to the driver of the vehicle and processing circuitry adapted to assess mental conditions/alertness of the driver and directions of driver gaze. These may be used to modify ADAS operation/thresholds.

A camera is positioned to obtain an image of an object. The image is input to a neural network that outputs a three-dimensional (3D) bounding box for the object relative to a pixel coordinate system and object parameters. Then a center of a bottom face of the 3D bounding box is determined in pixel coordinates. The bottom face of the 3D bounding box is located in a ground plane in the image. Based on calibration parameters for the camera that transform pixel coordinates into real-world coordinates, a) a distance from the center of the bottom face of the 3D bounding box to the camera relative to a real-world coordinate system and b) an angle between a line extending from the camera to the center of the bottom face of the 3D bounding box and an optical axis of the camera are determined. The calibration parameters include a camera height relative to the ground plane, a camera focal distance, and a camera tilt relative to the ground plane. A six degree-of-freedom (6DoF) pose for the object is determined based on the object parameters, the distance, and the angle.

The present application describes a system (100) and method for detecting and labeling structures of interest. The system includes a current patient study database (102) containing a current patient study (200) with clinical contextual information (706). The system also includes an image metadata processing engine (118) configured to extract metadata for preparing an input for an anatomical structure classifier (608), a natural language processing engine (120) configured to extract clinical context information (706) from the prior patient documents, an anatomical structure detection and labeling engine (718), and a display device (108) configured to display findings from the current patient study. The anatomical structure detection and labeling engine (718) is configured to identify and label one or more structures of interest (716) from the extracted metadata and clinical context information (706). The processor (112) is also configured to aggregate series level data. The method detects, label and prioritize anatomical structures (710). Specifically, once patient information is received from the current patient study (108), the labeled anatomical structures (710) and the high risk anatomical structures (714) are combined to form an optimized prioritized list of structures of interest (716).

There are provided a focusing point determining method and apparatus. The focusing point determining method comprises: obtaining a view-finding image within a view-finding coverage; identifying a significance area in the view-finding image; and extracting at least one focusing point from the identified significance area. By identifying the significance area in the view-finding image and extracting at least one focusing point from the identified significance area, the focusing point determining method and apparatus can ensure accuracy of a selected focusing point to a certain extent, so as to ensure accuracy of focusing.

Example lane detection systems and methods are described. In one implementation, a method receives an image from a front-facing vehicle camera and applies a geometric transformation to the image to create a birds-eye view of the image. The method analyzes the birds-eye view of the image using a neural network, which was previously trained using side-facing vehicle camera images, to determine a lane position associated with the birds-eye view of the image.

For image quality scoring of an image from a medical scanner, a generative model of an expected good quality image may be created using deep machine-learning. The deviation of an input image from the generative model is used as an input feature vector for a discriminative model. The discriminative model may also operate on another input feature vector derived from the input image. Based on these input feature vectors, the discriminative model outputs an image quality score.