Abstract: A method and apparatus for performing target detection. A potential object is detected within a candidate chip in an image. The potential object is verified as a candidate object. The candidate object is classified as one of a candidate target or a background in response to the potential object being verified as the candidate object. The candidate target is verified as a target of interest in response to the candidate object being classified as the candidate target.

Abstract: A method for user recognition, comprising receiving user information from an information unit of a user; detecting the user face in a captured user image; and recognizing the user identity in the captured image according to a predetermined gesture associated with the user information and performed by the user.

Abstract: A method for real-time fusion of a 2D cardiac ultrasound image with a 2D cardiac fluoroscopic image includes acquiring real time synchronized US and fluoroscopic images, detecting a surface contour of an aortic valve in the 2D cardiac ultrasound (US) image relative to an US probe, detecting a pose of the US probe in the 2D cardiac fluoroscopic image, and using pose parameters of the US probe to transform the surface contour of the aortic valve from the 2D cardiac US image to the 2D cardiac fluoroscopic image.

Abstract: The invention relates to an automated decision support system, method, and apparatus for analysis and detection of bacteria in histological sections from tissue biopsies in general, and more specifically, of Helicobacter pylori (HP) in histological sections from gastric biopsies. The method includes image acquisition apparatus, data processing and support system conclusions, methods of transferring and storing the slide data, and pathologist diagnosis by reviewing and approving the images classified as containing bacteria, and more specifically HP findings.

Abstract: According to an embodiment, an image analyzing device includes a first acquirer, a constructor, a first calculator, a second calculator, and a third calculator. The first acquirer is configured to acquire image information on a joint of a subject and bones connected to the joint. The constructor is configured to construct a three-dimensional shape of the bones and the joint, and relation characteristics between a load and deformation in the bones and the joint from the image information. The first calculator is configured to calculate a positional relation between the bones connected to the joint. The second calculator is configured to calculate acting force of a muscle acting on the bones connected to the joint based on the positional relation. The third calculator is configured to calculate first stress acting on the joint based on the three-dimensional shape, the relation characteristics, and the acting force.

Abstract: A method for densitometric analysis of a computed tomography image is provided. The method includes converting CT numbers of each pixel of a cross-sectional computed tomography image of the brain into Hounsfield unit (HU) values; eliminating an artifact from the computed tomography image of which the CT numbers of each pixel have been converted into the HU values, and extracting the brain tissues; and extracting a density distribution of the HU values from the computed tomography image, in which the artifact has been removed and the brain tissues have been extracted.

Abstract: Even when the brightness of an image in a video changes, detection of an object in the background is realized by accurately separating the object in the background from the background of the image. An image processing device in accordance with the present invention executes a process of converting a color space of a processing target image and acquiring color information on the converted color space, a process of calculating, for the target image, an average value of the brightness of color information on a target region that contains an object to be detected, and a process of comparing, for the target region, the brightness of color information on each pixel with the calculated average value, a process of generating a corrected image with corrected brightness/darkness, and a process of extracting the object on the basis of the corrected image (See FIG. 1).

Abstract: A method of processing images captured using a capsule camera is disclosed. According to one embodiment, two images designated as a reference image and a float image are received, where the float image corresponds to a captured capsule image and the reference image corresponds to a previously composite image or another captured capsule image prior to the float image. Automatic segmentation is applied to the float image and the reference image to detect any non-GI (non-gastrointestinal) region. The non-GI regions are excluded in match measure between the reference image and a deformed float image during the registration process. The two images are stitched together by rendering the two images at the common coordinate. In another embodiment, large area of non-GI regions are removed directly from the input image, and remaining portions are stitched together to form a new image without performing image registration.

Abstract: The present invention relate generally to digital watermarking and data hiding. One claim recites an apparatus comprising: electronic memory for storing first color data and second color data, the first color data and the second color data represent data from a color image signal or color video signal, and a digital watermark signal, the digital watermark signal serving to facilitate detection of a watermark message; means for separating the digital watermark signal into first frequency components and second frequency components; means for modifying the first color data by hiding the first frequency components therein; and means for modifying the second color data by hiding the second frequency components therein. Of course, other combinations and claims are provided too.

Abstract: A method of detecting multi-surfaces of an object includes providing an imaging system capable of detecting surfaces of the object. After system parameters are set up, two-dimensional images of the object at multiple Z steps can be acquired. Each surface of the object can then be extracted using two steps. In a first step, the surface can be constructed based on a confidence threshold. In a second step, the surface can be enhanced using an interpolation filter.

Abstract: A device, system, and method for displaying seismic image data may include computing, from a wide-azimuth data set, a discrete data set associated with an image function at a seismic image point. The discrete data set may be mapped onto a continuous curved three-dimensional surface. The mapped data set may be projected onto a continuous planar surface. The projected data may be displayed as a planar disk. A plurality of continuous planar surfaces, each representing a single image point, may be assembled to form a three-dimensional body, representing a seismic gather of image points. The three-dimensional body may be displayed. Other embodiments are described and claimed.

Abstract: A method for generating a virtual radiograph for display on a display device, including providing an image generation system having a processing circuit including a processor and a memory device, the image generation system coupled to the display device. The method further including retrieving three-dimensional image data of an anatomy stored in the memory and retrieving a three-dimensional bone model corresponding to a portion of the anatomy stored in the memory. The method further including associating the three-dimensional bone model with the three-dimensional image data such that the three-dimensional bone model defines first boundary containing a first bounded volume within the three-dimensional image data corresponding to the portion of the anatomy, and performing a volume ray casting process on the three-dimensional image data.

Abstract: A data processing method for determining the relative orientation of an object coordinate system of an anatomical object in a global co-ordinate system, comprising the steps of: acquiring a reference direction dataset representing a first reference direction of a line between a first anatomical landmark of a reference object and a second anatomical landmark of the reference object, and a second reference direction of a line between a third anatomical landmark of the reference object and a fourth anatomical landmark of the reference object, wherein the first and second reference directions are given in a reference coordinate system and the reference object corresponds to the anatomical object; acquiring an object direction dataset representing a first object direction of a line between the first anatomical landmark of the anatomical object and the second anatomical landmark of the anatomical object, and a second object direction of a line between the third anatomical landmark of the anatomical object and the f

Abstract: A method, apparatus and computer program product are provided for generating map data based on construction designs. In the context of a method, the method includes receiving a construction design, performing optical character recognition to detect characters within the construction design, extracting design features within the construction design, and generating map data based on the detected characters, and the extracted design features.

Abstract: A method of detecting multi-surfaces of an object includes providing an imaging system capable of detecting surfaces of the object. After system parameters are set up, two-dimensional images of the object at multiple Z steps can be acquired. Each surface of the object can then be extracted using two steps. In a first step, the surface can be constructed based on a confidence threshold. In a second step, the surface can be enhanced using an interpolation filter.

Abstract: In an example embodiment a method, apparatus and computer program product are provided. The method includes extracting a first set of target-object regions and at least one set of non-target object regions from a plurality of regions of a video content based at least on likelihood information. A plurality of unlabeled regions of the video content are classified based on the first set of target-object regions and the at least one set of non-target object regions to generate a second set of target object regions that is denser than the first set of target object regions. A model is learned for modelling at least one of the target object and non-target objects of the video content based at least on the second set of target object regions. The target object in the video content is segmented based on the model and the second set of target object regions.

Abstract: The technology of the present disclosure includes computer-implemented methods, computer program products, and systems to filter images before transmitting to a system for optical character recognition (“OCR”). A user computing device obtains a first image of the card from the digital scan of a physical card and analyzes features of the first image, the analysis being sufficient to determine if the first image is likely to be usable by an OCR algorithm. If the user computing device determines that the first image is likely to be usable, then the first image is transmitted to an OCR system associated with the OCR algorithm. Upon a determination that the first image is unlikely to be usable, a second image of the card from the digital scan of the physical card is analyzed. The optical character recognition system performs an optical character recognition algorithm on the filtered card.

Abstract: A method for recognizing directional structures on a window pane of a vehicle is described. The method includes carrying out an assessment of image points of an image of the window pane, which image points are disposed along an evaluation path, a course of the evaluation path being dependent on an expected orientation of the directional structures on the window pane. The method further includes recognizing a directional structure based on the assessment.

Abstract: A method of displaying a pathological microscopic image is provided. The method includes causing a display device to display a first area and a second area of a microscopic image, wherein the first area of the microscopic image is configured to be displayed in a first resolution and the second area of the microscopic image is configured to be displayed in a second resolution, and wherein the first resolution is lower than the second resolution; and causing the display device to display a first part of the first area in a first color different from an intrinsic color of the microscopic image, wherein the first part of the first area corresponds to the second area of the microscopic image, and wherein the first color includes one or more colors. An information processing apparatus, a non-transitory computer-readable medium, and an information processing system are also provided.

Abstract: An imaging system of a vehicle is provided herein. A camera is configured to capture images of a rear vehicle scene containing a trailer attached to the vehicle. A device is configured to remove contaminants on a lens of the camera. A controller is configured to analyze the captured images and activate the device based on the image quality of the captured images and a motion of the trailer relative to the vehicle.