Abstract: A system for validating motion estimation comprising a field unit (110) for obtaining a deformation vector field (DVF) estimating the motion by transforming a first image at a first phase of the motion into a second image at a second phase of the motion, a metric unit (120) for computing a metric of a local volume change at a plurality of locations, and a conformity unit (130) for computing a conformity measure based on the computed metric of the local volume change at the plurality of locations and a local property of the first or second image defined at the plurality of locations. Based on the value of the conformity measure, the DFV estimating the motion is validated. Experiments show that the conformity measure based on the computed metric of a local volume change at a plurality of locations and the local property of the first or second image, defined at the plurality of locations, does not necessarily favor a large weight for the outer force to provide a more accurate registration.

Abstract: A recognition system includes an acquisition module configured to acquire an image data generated by an image sensor, a first generation module configured to generate a graphical user interface which contains the image data, and an input module configured to detect an input on the graphical user interface, the input indicating a position designation on the image data. The recognition system further includes a second generation module configured to overlap a frame-line on the image data of the graphical user interface based on the position designation detected by the input module, and a calculation module configured to calculate one or more feature values of an object image within the frame-line.

Abstract: To provide an image reconstruction device capable of creating an image with image quality matching the operator's request when a cross-sectional image is reconstructed through a repeated calculation, the image reconstruction device which performs a repeated calculation on the basis of a difference between calculated projection data and measured projection data, the calculated projection data being obtained by performing a forward projection calculation on a reconstructed image which is reconstructed based on the measured projection data, includes an input section to which an image quality parameter which is considered to be important by an operator is input, a weight calculation section that calculates a weighting coefficient on the basis of the image quality parameter, and a repeated calculation section that performs a repeated calculation on the basis of a value obtained by weighting and adding a pixel value obtained in the previous iteration to a pixel value obtained from now using the weighting coefficien

Abstract: The invention relates to a real time-capable analysis of a sequence of electronic images for estimating the pose of a movable object captured by means of the images. The invention further relates to implementing the invention in software and, in this connection, to a computer-readable medium that stores commands, the execution of which causes the method according to the invention to be carried out. The invention proceeds from a skeleton model, which is described by a small number of nodes in 3D space and permits a good data compression of the image information when the co-ordinates of the nodes describe at any time the position of predetermined parts of the moving object. The skeleton model simultaneously represents previous knowledge of the object, by defining e.g. node pairs and optionally also node triplets in the skeleton model that describe cohesive object parts or optionally object surfaces, which are contained in the measured 2½-D image information, i.e. are visible to the camera.

Abstract: A method of generating an image by using multi-energy radiation data and an apparatus therefor is provided. The method includes receiving multi-energy radiation data including a plurality of pieces of radiation data indicating an inner portion of a subject with respect to a plurality of radioactive rays in different energy bands, respectively, generating, based on the received multi-energy radiation data, radiation data of a radioactive ray in an energy band that is different from the different energy bands, and generating a radiation image of the subject based on the generated radiation data.

Abstract: Systems and methods are provided for ensuring that printed output for a print job matches the expected output for a print job. The system comprises a control unit and a comparison unit. The control unit receives a print job and modifies the print job by adding a tag to each logical page of the print job, and to transmit the modified print job to a printer. The control unit further generates target images for the logical pages of the print job. The comparison unit receives printed pages of the job from the printer. For each printed page of the job, the comparison unit identifies a tag on the printed page, identifies a target image corresponding with the tag on the printed page, and compares an image of the printed page to the target image to detect discrepancies between the printed page and the target image.

Abstract: The pose of an implant represented in a medical image is determined from the medical image. The x-ray image of the implant is compared to a database of the implant viewed at different poses (e.g., viewed from different directions). The implant pose associated with the best match indicates the pose of the implant in the x-ray image.

Abstract: A method and apparatus for processing an ultrasound image are provided. The method includes determining similarities between a first two-dimensional (2D) ultrasound image, among 2D ultrasound images of a three-dimensional (3D) ultrasound image, and the 2D ultrasound images. The method further includes generating a predetermined number of similar ultrasound images with respect to the first 2D ultrasound image based on the similarities. The method further includes generating 3D volume data based on the predetermined number of the similar ultrasound images. The method further includes removing noise from the 3D volume data. The method further includes generating another 3D ultrasound image based on the noise-removed 3D volume data.

Abstract: A system for processing an image data volume acquired with a medical imaging acquisition device 100 from a body comprising a needle is provided. It has been realized it is advantageous to display 150 a plane intersecting the image data volume showing the needle to a user of the system. This allows better positioning of the needle. The system comprises a needle-plane determination 110 module for determining a plane being parallel to and intersecting a representation in the image data volume of the needle and being parallel to a viewing direction. The needle plane determination module may make use of pixel processing and/or spectral transformation, in particular the Gabor transform.

Abstract: Systems and methods for initializing motion tracking of human hands within bounded regions are disclosed. One embodiment includes: a processor; reference and alternate view cameras; and memory containing a plurality of templates that are rotated and scaled versions of a base template. In addition, a hand tracking application configures the processor to: obtain reference and alternate view frames of video data; generate a depth map; identify at least one bounded region within the reference frame of video data containing pixels having distances from the reference camera that are within a specific range of distances; determine whether any of the pixels within the at least one bounded region are part of a human hand; track the motion of the part of the human hand in a sequence of frames of video data obtained from the reference camera; and confirm that the tracked motion corresponds to a predetermined initialization gesture.

Abstract: A method of processing input digital image data representing an image into output digital image data, comprising: providing (100) input image data; providing and initializing (200) a level set function representation for approximating the output digital image data; providing (300) a speed function; determining (400) a propagation direction trend map relating to image points of the level set function, said map comprising one or more trend directions associated with said image points so that each one of said image points has an associated trend direction; updating (500, 520) the level set function using the speed function and the propagation direction trend map, so that the speed function is excluded from contributing in the updating of the level set function in image points for which the speed of the speed function is not in the associated trend direction; and providing (700) the output digital image data based on the level set function.

Abstract: With respect to projection data covering a plurality of sites, in order to create a medical image in which a uniform noise reduction effect is achieved for all sites within the projection data, an arithmetic device (5) determines one or more of proper subsets on the basis of scanning conditions and reconstruction conditions (step 2). Next, the arithmetic device (5) calculates a penalty-term weight for each proper subset on the basis of a detector output weight corresponding to a set element contained in the proper subset (step 3). Then, the arithmetic unit (5) performs an iterative approximation by using the penalty-term weight for each proper subset (step 4).

Abstract: A video processing device includes a content analyzer that receives a video signal and generates content recognition data based on the video signal, wherein the content recognition data is associated with at least one timestamp included in the video signal. A metadata search device generates time-coded metadata in response to content recognition data and in accordance with the at least one time stamp. A metadata association device generates a processed video signal from the video signal, wherein the processed video signal includes the time-coded metadata.

Abstract: Systems and methods for tracking human hands using parts based template matching within bounded regions are described. One embodiment of the invention includes a processor; an image capture system configured to capture multiple images of a scene; and memory containing a plurality of templates that are rotated and scaled versions of a finger template. A hand tracking application configures the processor to: obtain a reference frame of video data and an alternate frame of video data from the image capture system; identify corresponding pixels within the reference and alternate frames of video data; identify at least one bounded region within the reference frame of video data containing pixels having corresponding pixels in the alternate frame of video data satisfying a predetermined criterion; and detect at least one candidate finger within the at least one bounded region in the reference frame of video data.

Abstract: Methods to generate, and devices to use, an adaptive tone curve generation operation are disclosed. Tone curves so generated have been found to produce stable tone mapping in a wide range of operational environments, including during multi-exposure fused images (e.g., during high dynamic range image fusion). In general, techniques are disclosed that use a content-load histogram in combination with image capture device noise information to adaptively bound a tone curve's slope and, therefore, the resulting tone curve. As used here, a content-load histogram is a histogram that captures spatial, color or other information carried by an image's pixels at various gray levels.

Abstract: A system and method for reducing image noise and artifacts in coronary computed tomography angiography includes acquisition of CT images at multiplicity of CT slices arranged in such a fashion throughout the phases of the cardiac cycle as to utilize the majority of the X-ray radiation to which the myocardium exposed during the cycle. The acquired imaging data is processed with the use of a TAF filter to reduce the amount of noise and artifacts associated with the CT's system operating at low tube current. The TAF filter is configured to adapt the filtering strength in time domain according to temporal variations of the same anatomical location as identified in its corresponding CT slices.

Abstract: A behavioral recognition system may include both a computer vision engine and a machine learning engine configured to observe and learn patterns of behavior in video data. Certain embodiments may be configured to detect and evaluate the presence of sea-surface oil on the water surrounding an offshore oil platform. The computer vision engine may be configured to segment image data into detected patches or blobs of surface oil (foreground) present in the field of view of an infrared camera (or cameras). A machine learning engine may evaluate the detected patches of surface oil to learn to distinguish between sea-surface oil incident to the operation of an offshore platform and the appearance of surface oil that should be investigated by platform personnel.

Abstract: Embodiments of the present invention relate to systems, computer-implemented methods, and computer program products for capturing elements of a negotiable instrument and generating a thumbnail image of the negotiable instrument for use in image recreation. In some embodiments, a method is provided that includes: (a) receiving an image of the negotiable instrument, wherein the image of the negotiable instrument comprises one or more elements that are used for processing the negotiable instrument; (b) capturing, using the image capture device, images of one or more elements of the negotiable instrument; (c) generating a thumbnail image of the negotiable instrument based at least partially on an image of the negotiable instrument; and (d) storing the images of the one or more elements of the negotiable instrument and the thumbnail image of the negotiable instrument in the database.

Abstract: Objects, such as road signs, may be detected in real-time using a camera or other image capture device. As images are received through the camera, candidate signs are first detected. The detection of candidate signs employs constant-time normalized cross correlation, including generation of intermediate images and integral images, and applying a template of concentric, different sized shapes over the integral images. From the pool of candidate signs, false positives may be separated out using shape classification to identify actual road signs.

Abstract: An apparatus and method process magnetic resonance image (MRI) data and other data from a subject, including image data corresponding to at least one of angiographic data, four-dimensional blood flow, neurological blood flow, abdominal blood flow, and peripheral blood flow in the subject, and applies a compressed sensing (CS) reconstruction method utilizing a complex difference of the image data as a sparsifying transform for imaging of at least one of blood flow and magnetic resonance angiography to output a reconstructed image of the blood flow and magnetic resonance angiography, in the subject with increased processing speed and having high accuracy. The apparatus receives the MRI data of the fluid flow from an MRI device. The processor operates predetermined software, receives the MRI data, and applies the CS reconstruction method to generate the reconstructed image. An output device outputs the reconstructed image of the fluid flow.