Abstract: There is provided an information processing apparatus, an information processing method, and a recording medium that can estimate a three-dimensional position of a targeted point more accurately. The information processing apparatus includes: a targeted point estimation unit configured to identify probability maps indicating existence probabilities of a targeted point in a plurality of projection directions, on the basis of an input image; and a synthesis unit configured to identify a three-dimensional position of the targeted point on the basis of the probability maps in the plurality of projection directions.

Abstract: Systems and method are described for determining a malignancy of a nodule. A medical image of a nodule of a patient is received. A patch surrounding the nodule is identified in the medical image. A malignancy of the nodule in the patch is predicted using a trained deep image-to-image network.

Abstract: According to various embodiments, an electronic device may include a first light emitter comprising first light emitting circuitry configured to output light of a first wave bandwidth, a second light emitter comprising second light emitting circuitry configured to output light of a second wave bandwidth, a camera including an image sensor configured to arrange one or more first pixels for sensing the light corresponding to the first wave bandwidth and the second wave bandwidth and one or more second pixels for sensing the light corresponding to the second wave bandwidth, and a processor. The processor may be configured to control the electronic device to output the first wave bandwidth light using a first light source and the second wave bandwidth light using a second light source, and a control circuit electrically coupled to the image sensor and connected to an application processor through a designated interface.

Abstract: Devices and techniques are generally described for object co-segmentation in image data using a semantic filter. In various examples, first image data and second image data may be received. First semantic feature data may be determined for the first image data and second semantic feature data may be determined for the second image data. Filtered semantic feature data corresponding to the first semantic feature data may be generated by filtering the first semantic feature data and the second semantic feature data in a semantic feature space. A determination may be made that a first pixel corresponds to a first class of an object, where at least one object of the first class is represented in the first image data and the second image data.

Abstract: A system generates a user hand shape model from a single depth camera. The system includes the single depth camera and a hand tracking unit. The single depth camera generates single depth image data of a user's hand. The hand tracking unit applies the single depth image data to a neural network model to generate heat maps indicating locations of hand features. The locations of hand features are used to generate a user hand shape model customized to the size and shape of the user's hand. The user hand shape model is defined by a set of principal component hand shapes defining a hand shape variation space. The limited number of principal component hand shape models reduces determination of user hand shape to a smaller number of variables, and thus provides for a fast calibration of the user hand shape model.

Abstract: A computer implemented method for assessing an arterio-venous malformation (AVM) may include, for example, receiving a patient-specific model of a portion of an anatomy of a patient; using a computer processor to analyze the patient-specific model for identifying one or more blood vessels associated with the AVM, in the patient-specific model; and estimating a risk of an undesirable outcome caused by the AVM, by performing computer simulations of blood flow through the one or more blood vessels associated with the AVM in the patient-specific model.

Abstract: An image conversion unit includes a selector and a plurality of image converters. Each image converter is formed from an estimator of machine learning type, and estimates, based on an image acquired under a first observation condition and as a reference image, an image which is presumed to be acquired under a second observation condition. When a particular reference image is selected from among a plurality of reference images displayed on a display, a second observation condition corresponding to the selected reference image is set in an observation mechanism as a next observation condition.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating and providing matching fonts by utilizing a glyph-based machine learning model. For example, the disclosed systems can generate a glyph image by arranging glyphs from a digital document according to an ordering rule. The disclosed systems can further identify target fonts as fonts that include the glyphs within the glyph image. The disclosed systems can further generate target glyph images by arranging glyphs of the target fonts according to the ordering rule. Based on the glyph image and the target glyph images, the disclosed systems can utilize a glyph-based machine learning model to generate and compare glyph image feature vectors. By comparing a glyph image feature vector with a target glyph image feature vector, the font matching system can identify one or more matching glyphs.

Abstract: Systems and methods for automatic enrollment and identity verification based upon processing a captured image of a document are disclosed herein. Various embodiments enable, for example, a user to enroll in a particular service by taking a photograph of a particular document (e.g., his driver license) with a mobile device. One or more algorithms can then extract relevant data from the captured image. The extracted data (e.g., the person's name, gender, date of birth, height, weight, etc.) can then be used to automatically populate various fields of an enrollment application, thereby reducing the amount of information that the user has to manually input into his mobile device in order to complete the enrollment process. In some embodiments, a set of internal and/or external checks can be run against the data to ensure that the data is valid, has been read correctly, and is consistent with other data.

Abstract: Methods, computer programs, and systems for detecting disease in vasculature. The method includes obtaining images of the vasculature. The method includes extracting vessel measurements from the obtained images. The method includes determining features of the vasculature in the obtained images based on the extracted vessel measurements. The method includes applying artificial intelligence algorithms to determine if the disease is present in the vasculature based on these vascular features.

Abstract: Example embodiments that analyze images to characterize aspects of the images rely on a same neural network to characterize multiple aspects in parallel. Because additional neural networks are not required for additional aspects, such an approach scales with increased aspects.

Abstract: A method includes obtaining multiple images captured by pixel sensors of an image sensor, analyzing, using neural network circuitry integrated in the image sensor, the multiple images for object detection, generating, for each of the multiple images using the neural network circuitry integrated in the image sensor, neural network output data related to results of the analysis of the multiple images for object detection, and transmitting, from the image sensor, the neural network output data for each of the multiple images and image data for a subset of the multiple images instead of image data of each of the multiple images.

Abstract: A face verifying method and apparatus. The face verifying method includes detecting a face region from an input image, generating a synthesized face image by combining image information of the face region and reference image information, based on a determined masking region, extracting one or more face features from the face region and the synthesized face image, performing a verification operation with respect to the one or more face features and predetermined registration information, and indicating whether verification of the input image is successful based on a result of the performed verification operation.

Abstract: Methods and systems are provided for defining and determining a formal and verifiable mobile document image quality and usability (MDIQU) standard, or Standard for short. The Standard ensures that a mobile image can be used in an appropriate mobile document processing application, for example an application for mobile check deposit. In order to quantify the usability, the Standard establishes 5 quality and usability grades. A mobile image capture device can capture images. A mobile device can receive information associated with one or more image quality assurance (IQA) criteria; evaluating the images to select an image satisfying an image quality criteria based on the received information; and in response to the image satisfying the image quality score, sending the selected image to determine a set of image quality assurance (IQA) scores.

Abstract: A method, computer system, and a computer program product for generating a location tag for a piece of visual data using deep learning is provided. The present invention may include receiving the piece of visual data. The present invention may also include analyzing the received piece of visual data using a neural network. The present invention may then include retrieving a location for the analyzed piece of visual data from the neural network. The present invention may further include generating a plurality of metadata for the retrieved location associated with the analyzed piece of visual data, wherein the generated plurality of metadata includes the location tag.

Abstract: Embodiments of a method and system described herein enable capture of video data streams from multiple, different video data source devices and the processing of the video data streams. The video data streams are merged such that various data protocols can all be processed with the same worker processors on different types of operating systems, which are typically distributed. In an embodiment the multiple video data sources comprises at least one mobile device executing a video sensing application that produces a video data stream for processing by video analysis worker processes. The processes include automatically detecting moving objects in a video data stream, and further tracking and analyzing the moving objects.

Abstract: Certain embodiments detect human-object interactions in image content. For example, human-object interaction metadata is applied to an input image, thereby identifying contact between a part of a depicted human and a part of a depicted object. Applying the human-object interaction metadata involves computing a joint-location heat map by applying a pose estimation subnet to the input image and a contact-point heat map by applying an object contact subnet to the to the input image. The human-object interaction metadata is generated by applying an interaction-detection subnet to the joint-location heat map and the contact-point heat map. The interaction-detection subnet is trained to identify an interaction based on joint-object contact pairs, where a joint-object contact pair includes a relationship between a human joint location and a contact point. An image search system or other computing system is provided with access to the input image having the human-object interaction metadata.

Abstract: Embodiments of a method and system described herein enable capture of video data streams from multiple, different video data source devices and the processing of the video data streams. The video data streams are merged such that various data protocols can all be processed with the same worker processors on different types of operating systems, which are typically distributed. In an embodiment the multiple video data sources comprises at least one mobile device executing a video sensing application that produces a video data stream for processing by video analysis worker processes. The processes include estimating a queue wait time.

Abstract: An image processing device includes a processor to detect motion of objects in an observation area on the basis of a captured image. The processor also calculates amounts of each detected motion, and calculates a propagation speed, a propagation direction, or both, of the motion for pulsations of the objects.

Abstract: A method for estimating the speed of movement of a first video camera when it captures a current image of a three-dimensional scene, includes storing a reference image corresponding to an image of the same scene captured by a second video camera in a different pose, the reference image including pixels. The method also includes storing the current image, the current image including pixels containing the measurement of a physical quantity measured by that pixel, that physical quantity being the same as the physical quantity measured by the pixels of the reference image. The method further includes storing for each pixel of the reference image or of the current image the measurement of a depth that separates that pixel from the point of the scene photographed by that pixel, estimating the pose of the first camera, and estimating the speed of movement of the first camera.