Embodiments for analyzing images by one or more processors are described. An image is received. An object appearing in the image is detected. A scene graph is generated for the object. At least one transformational matrix is determined for the object. The at least one transformational matrix is associated with rendering the object as the object appears in the image based on the scene graph.

Methods, systems and computer program products for flagging abnormal videos are provided. Aspects include training an image recognition model based on a plurality of images that depict one or more of a plurality of subjects. Aspects also include generating a normal subject relationship graph representing normal relationships between the plurality of subjects by applying the image recognition model to a plurality of training videos and a test subject relationship graph representing test relationships between subjects depicted in a test video by applying the image recognition model to the test video. Each normal relationship is associated with a strength value. Responsive to determining that a difference between a strength value associated with a first normal relationship and a strength value associated with a corresponding first test relationship exceeds a predetermined threshold, aspects include flagging the test video as being abnormal.

Computer vision systems and methods for machine learning using a set packing framework are provided. A minimum weight set packing (MWSP) framework is parameterized by a set of possible hypotheses, each of which is associated with a real valued cost that describes the sensibility of the belief that the members of the hypothesis correspond to a common cause. Using MWSP, the system then selects the lowest total cost set of hypotheses, such that no two selected hypotheses share a common observation. Observations that are not included in any selected hypothesis, define the set of false observations can be thought of as false observations/noise. The system can be utilized to support one or more trained computer models in performing computer vision on input data in order to generate output data.

A method for automated routing of pictures taken on mobile electronic devices to a digital picture frame including a camera integrated with the frame, and a network connection module allowing the frame for direct contact and upload of photos from electronic devices or from photo collections of community members. The integrated camera is used to automatically determine an identity of a frame viewer and can capture gesture-based feedback. The displayed photos are automatically shown and/or changed according to the detected viewers. The photos can be filtered and cropped at the receiver side. Clustering photos by content is used to improve display and to respond to photo viewer desires.

Techniques for time-correlated ink are described. According to various embodiments, ink input is correlated to content. For instance, ink input received during playback of a video is timestamped. According to various embodiments, ink input displayed over content is removed after input ceases. Further, ink input is displayed during playback of the portion of content to which the ink input is time correlated.

The present disclosure is directed to systems and methods for classifying biomedical images. A feature classifier may generate a plurality of tiles from a biomedical image. Each tile may correspond to a portion of the biomedical image. The feature classifier may select a subset of tiles from the plurality of tiles by applying an inference model. The subset of tiles may have highest scores. Each score may indicate a likelihood that the corresponding tile includes a feature indicative of the presence of the condition. The feature classifier may determine a classification result for the biomedical image by applying an aggregation model. The classification result may indicate whether the biomedical includes the presence or lack of the condition.

A computing platform may receive video, audio, and/or biometric information of one or more people. The computing platform may identify the people based on a comparison of the video, audio, and/or biometric information to stored information in one or more user profiles each associated with the people. For example, the computing platform may compare multiple types of biometric information, including fingerprint, retina scan, facial features, and the like, as part of a process for identifying the people. The computing platform may further determine one or more interactions between the people, and, based on the interactions, determine and/or identify a relationship between the people. The identified relationships may further be used for confirming identifies of the people. Based on the identifications (e.g., biometric, video, audio, relationships), the computing platform may further provide access for the people to one or more services.

A multiple-wavelength image analysis electro-optical system for detecting a disabled ship and persons overboard of the present invention is a multiple-wavelength image analysis electro-optical system for detecting a disabled ship and persons overboard configured to have an input part 10 provided with an ultra-low light camera 3, a short-wavelength infrared image sensor 5, a medium-wavelength infrared image sensor 7, and a long-wavelength infrared image sensor 9; a signal processing part 20 for receiving and processing data of the input part 10; a display part 30 for receiving and displaying data of the signal processing part 20; a storage part 40 for storing data of the signal processing part 20 and the display part 30; and a control part 90 provided with a camera control board 50 and a drive control board 60 for controlling the input part 10, signal processing part 20, the display part 30 and the storage part 40.

An apparatus is provided. The apparatus receives a video feed and processes the video feed in real-time as the video feed is received. The apparatus performs object detection and recognition on the video feed to detect and classify objects therein, performs activity recognition to detect and classify activities of at least some of the objects, and outputs classified objects and classified activities in the video feed. The apparatus generates natural language text that describes the video feed, produces a semantic network, and stores the video feed, classified objects and classified activities, natural language text, and semantic network in a knowledge base. The apparatus generates a graphical user interface (GUI) configured to enable queries of the knowledge base, and presentation of selections of the video feed, classified objects and classified activities, natural language text, and semantic network.

Embodiments for analyzing images by one or more processors are described. An image is received. An object appearing in the image is detected. A scene graph is generated for the object. At least one transformational matrix is determined for the object. The at least one transformational matrix is associated with rendering the object as the object appears in the image based on the scene graph.