Abstract: An image processing apparatus includes an extraction unit configured to extract a region where light is depolarized from a polarization-sensitive tomographic image of a subject, and a display control unit configured to display, on a display unit, a region determined as a region invading a predetermined layer of the subject, in a part of the region where light is depolarized.

Abstract: A method and system for contrast inflow detection in a sequence of fluoroscopic images is disclosed. Vessel segments are detected in each frame of a fluoroscopic image sequence. A score vector is determined for the fluoroscopic image sequence based on the detected vessel segments in each frame of the fluoroscopic image sequence. It is determined whether a contrast agent injection is present in the fluoroscopic image sequence based on the score vector. If it is determined that a contrast agent injection is present in the fluoroscopic image sequence, a contrast inflow frame, at which contrast agent inflow begins, is detected in the fluoroscopic image sequence based on the score vector.

Abstract: An information processing device includes a conversion unit that performs conversion such that an area including a feature point and the periphery thereof in a specific target is set as a first area and, when one pixel in the first area is set as a reference pixel, an area including the reference pixel and pixels in the periphery thereof is set as a second area, and, based on a comparison result of the feature amount of the reference pixel and the feature amount of another pixel in the second area, the feature amount of another pixel is converted for each pixel in the second area, and a calculation unit that calculates a feature amount to be used in an identification process for identifying the specific target by performing computation for the value of each pixel in the second area which is obtained from the conversion for each reference pixel.

Abstract: Disclosed is a library apparatus capable of indicating an availability state of a slot according to the availability state of the slot that a magazine has. The storage library apparatus 1 rotates the first position P that indicates a usable state of a slot 7 by a first protection lever 4 being pushed by a accessor 3 which can convey, contacts against in a stopper 6, accordingly, is fixed by a lock component 5 and is fixed to the lock component 5 by rotating a second position R that indicates the unusable state of a slot 7.

Abstract: The present disclosure is directed to a parallel face detection and tracking system. In general, embodiments consistent with the present disclosure may be configured to distribute the processing load associated with the detection and tracking of different faces in an image between multiple data processors. If needed, processing load balancing and/or protective features may be implemented to prevent the data processors from becoming overwhelmed. In one embodiment, a device may comprise, for example, a communication module and at least one processing module. The communication module may be configured to receive at least image information that may be processed by a plurality of data processors in the data processing module. For example, each of the data processors may be configured to detect faces in the image information and/or track detected faces in the image information based on at least one criterion.

Abstract: In one embodiment, a social networking system automatically tags one or more users to an image file by creating a list of potential matches, and selecting a subset of potential matches based on location, asking a first user to confirm the subset of potential matches, and tagging one or more matched users to the image file.

Abstract: Aspects of depth map generation and post capture focusing and re-focusing are described. According to one embodiment, a depth map is generated. The depth map may include a mapping among relative depth values in a field of view of an image based on a difference between pixels of a first image and pixels of a second image. An edge map may also be generated by identifying edges in at least one of the first image or the second image. Using the depth map and the edge map, the relative depth values in the depth map may be smoothed using the edge map. In this manner, certain discontinuities in depth values may be smoothed within edge-bounded regions defined by the edge map. The depth map may be used for focusing and re-focusing, for example, or for object extraction, scene understanding, or gesture recognition, among other imaging processes.

Abstract: An object (e.g., a driver's license) is tested for authenticity using imagery captured by a consumer device (e.g., a mobile phone camera). Corresponding data is sent from the consumer device to a remote system, which has secret knowledge about features indicating object authenticity. The phone, or the remote system, discerns the pose of the object relative to the camera from the captured imagery. The remote system tests the received data for the authentication features, and issues an output signal indicating whether the object is authentic. This testing involves modeling the image data that would be captured by the consumer device from an authentic object—based on the object's discerned pose (and optionally based on information about the camera optics), and then comparing this modeled data with the data sent from the consumer device. A great variety of other features and arrangements are also detailed.

Abstract: An over sampled image sensor in which the pixel size is small enough to provide spatial oversampling of the minimum blur size of the sensor optics is disclosed. Image processing to detect targets below the typical limit of 6× the temporal noise floor is also disclosed. The apparatus is useful in detecting dimmer targets and targets at a longer range from the sensors. The inventions exploits signal processing, which allows spatial temporal filtering of the superpixel image in such manner that the Noise Equivalent Power is reduced by a means of Superpixel Filtering and Pooling, which increases the sensitivity far beyond a non-oversampled imager. Overall visual acuity is improved due to the ability to detect dimmer targets, provide better resolution of low intensity targets, and improvements in false alarm rejection.

Abstract: A method and system for model-based fusion of multi-modal volumetric images is disclosed. A first patient-specific model of an anchor anatomical structure is detected in a first medical image acquired using a first imaging modality, and a second patient-specific model of the anchor anatomical structure is detected in a second medical image acquired using a second imaging modality. A weighted mapping function is determined based on the first patient-specific model of the anchor anatomical structure and the second patient-specific model of the anchor anatomical structure using learned weights to minimize mapping error with respect to a target anatomical structure. The target anatomical structure from the first medical image to the second medical image using the weighted mapping function. In an application of this model-based fusion to transcatheter valve therapies, the trachea bifurcation is used as the anchor anatomical structure and the aortic valve is the target anatomical structure.

Abstract: A non-invasive method for measuring blood flow in principal vessels of a heart of a subject is provided. The method includes illuminating a region of interest in the heart with a coherent light source, wherein the coherent light source has a wavelength of from about 600 nm to about 1100 nm; sequentially acquiring at least two speckle images of the region of interest in the heart during a fixed time period, wherein sequentially acquiring the at least two speckle images comprises acquiring the at least two speckle images in synchronization with motion of the heart of the subject; and electronically processing the at least two acquired speckle images based on the temporal variation of the pixel intensities in the at least two acquired speckle images to generate a laser speckle contrast imaging (LSCI) image and determine spatial distribution of blood flow rate in the principal vessels and quantify perfusion distribution in tissue in the region of interest in the heart from the LSCI image.

Abstract: An inspection apparatus performs position adjustment between a reference image and an target image in a band region of a predetermined band size by using information of a feature point in the band region having the predetermined band size and information of a feature point in a region adjacent to the band region, and performs inspection of the printed document based on the comparison of the reference image and the target image.

Abstract: Embodiments of the disclosure provide for systems and methods for creating metadata associated with a video data. The metadata can include data about objects viewed within a video scene and/or events that occur within the video scene. Some embodiments allow users to search for specific objects and/or events by searching the recorded metadata. In some embodiments, metadata is created by receiving a video frame and developing a background model for the video frame. Foreground object(s) can then be identified in the video frame using the background model. Once these objects are identified they can be classified and/or an event associated with the foreground object may be detected. The event and the classification of the foreground object can then be recorded as metadata.

Abstract: In an emergable watermark superimposing method for superimposing a superimposition image on either a cover still image or a still image formed from a cover moving image, when an image after the superimposition image is superimposed thereon is converted, or a screen which displays thereon the image after the superimposition image is superimposed is photographed, the superimposition image is superimposed so as to be more emphasized.

Abstract: Systems and method can be employed to automatically extract radiation dose information from medical images, particularly a plurality of heterogeneous CT images including those from legacy CT scanners. A report including the extracted radiation dose information can be generated, and alerts can be sent to reduce the possibility of overexposures.

Abstract: A method and apparatus are provided for optimizing one or more object detection parameters used by an autonomous vehicle to detect objects in images. The autonomous vehicle may capture the images using one or more sensors. The autonomous vehicle may then determine object labels and their corresponding object label parameters for the detected objects. The captured images and the object label parameters may be communicated to an object identification server. The object identification server may request that one or more reviewers identify objects in the captured images. The object identification server may then compare the identification of objects by reviewers with the identification of objects by the autonomous vehicle. Depending on the results of the comparison, the object identification server may recommend or perform the optimization of one or more of the object detection parameters.

Abstract: The method for building an outdoor map for a moving object according to an exemplary embodiment of the present invention includes: receiving a real satellite image for an outdoor space to which the moving object is to move; calculating pixel information including sizes of length and width pixels and a physical distance of one pixel in the real satellite image; measuring a reference position coordinate for a reference position selected from the real satellite image; and linking a pixel number corresponding to the reference position, the reference position coordinate, and the pixel information to the real satellite image in order to build the outdoor map for the moving object, and further includes creating information on a road network in which the moving object navigates based on the pixel number corresponding to the reference position, the reference position coordinate, and the pixel information.

Abstract: In a magnetic resonance method and system for automatic generation of a selective MR image from a first MR image (corresponding to raw data acquired at a first echo time after excitation pulses) and a second MR image (corresponding to raw data acquired at a second echo time after the same excitation pulses), wherein at least one raw data measurement point was measured in the absence of gradient fields, a time constant prevailing in the depicted imaging space is calculated from the measurement data measured during readout of the raw data measurement point measured in the absence of gradient fields. Weighting factors for the first and/or the second MR image are determined depending on this time constant. The selective MR image is generated by weighting the first and/or second MR image with the calculated weighting factors and subtraction of the weighted MR images from one another.

Abstract: In one embodiment, a method for identifying areas in a document image is provided. The method comprises generating binarized and gradient images based on the document image; and performing a classification operation to classify areas in the document image into one of a noise area and a picture area based on attributes computed on the binarized and gradient images.

Abstract: A method, including: registering a new image volume with a composed image volume, wherein the new image volume and the composed image volume overlap each other in an overlap region, the composed image volume includes at least two image volumes that overlap each other, and each voxel in the composed image volume includes a weight; determining a deformation between the new image volume and the composed image volume; updating the weights of the voxels in the composed image volume that are overlapped by the new image volume; performing an alpha morphing on the overlap region using the updated weights and the deformation; obtaining a blend region of the overlap region by performing an alpha blending using results of the alpha morphing and the updated weights; and incorporating the blend region into the composed image volume to obtain a new composed image volume.