Abstract: Described herein are systems and methods for expanding upon the single-distance-based background denotation to seamlessly replace unwanted image information in a captured image derived from an imaging application so as to account for a selected object's spatial orientation to maintain an image of the selected object in the captured image.

Abstract: A system and method for generating a multi-dimensional image of an object in a scene is disclosed. One inventive aspect includes a spectral estimation module configured to convert a two-dimensional (2D) high-resolution light intensity image of the scene to a spectral-augmented image of a selected channel. The system further includes a high-resolution depth image generation module configured to generate a high-resolution depth image of the object based on a three-dimensional (3D) low-resolution depth image of the scene and the spectral-augmented image.

Abstract: Provided are a printing method and apparatus. The printing method includes receiving data regarding a document to be printed from a host, applying a predetermined effect to an object included in the document to be printed, and printing the document including the object to which the predetermined effect is applied. Thus, when a document created by a host and transmitted to a printing apparatus to be printed, cannot be corrected by the host, an effect can be applied to the document by the printing apparatus.

Abstract: A stereo matching section of a stereoscopic image processing unit evaluates a correlation of brightness between a reference pixel block picked up from a right image and a comparison pixel block picked up from a left image and calculates a parallax between these two pixel blocks having the correlation. A region control section changes over the size of these pixel blocks according to the area in which the stereo matching is performed so as to obtain a more accurate three-dimensional recognition.

Abstract: A method of tracking a pose of a moving camera includes receiving a first image from a camera, receiving a sequence of digitized images from said camera, recording, for each of said sequence of digitized images, the pose and 2D correspondences of landmarks, reconstructing a location and appearance of a 2-dimensional texture patch from 2D correspondences of the landmarks by triangulation and optimization, computing back-projection errors by comparing said reconstructed texture patch with said first received image; and reconstructing said location and appearance of said 2-dimensional texture patch from the 2D correspondences of the landmarks of said sequence of digitized images by triangulation and optimization after eliminating those landmarks with large back-projection errors.

Abstract: The claimed subject matter provides a system and/or a method that facilitates simulating a portion 2-dimensional (2D) data for implementation within a 3-dimensional (3D) virtual environment. A 3D virtual environment can enable a 3D exploration of a 3D image constructed from a collection of two or more 2D images, the 3D image is constructed by combining the two or more 2D images based upon a respective image perspective. An analyzer can evaluate the collection of two or more 2D images to identify a portion of the 3D image that is unrepresented by the combined two or more 2D images. A synthetic view generator can create a simulated synthetic view for the portion of 3D image that is unrepresented, the simulated synthetic view replicates a 2D image with a respective image perspective for the unrepresented portion of 3D image.

Abstract: Systems and methods for image segmentation in generating computer models of a joint to undergo arthroplasty are disclosed. Some embodiments may include a method of partitioning an image of a bone into a plurality of regions, where the method may include obtaining a plurality of volumetric image slices of the bone, generating a plurality of spline curves associated with the bone, verifying that at least one of the plurality of spline curves follow a surface of the bone, and creating a 3D mesh representation based upon the at least one of the plurality of spline curve.

Abstract: A method recognizes a face in an image. A morphable model having shape and pose parameters is fitted to a face in an image to construct a three-dimensional model of the face. Texture is extracted from the face in the image using the three-dimensional model. The shape and texture are projected into a bilinear illumination model to generate illumination bases for the face in the image. The illumination bases for the face in the image are compared to illumination bases of each of a plurality of bilinear illumination models of known faces to identify the face in the image.

Abstract: A method generates a three-dimensional, bi-linear, illumination model for arbitrary faces. A large number of images are acquired of many different faces. For each face, multiple images are acquired with varying poses and varying illumination. A three-mode singular value decomposition is applied to the images to determine parameters of the model. The model can be fit to a probe image of an unknown face. Then, the model can be compared with models of a gallery of images of unknown faces to recognize the face in the probe image.

Abstract: Camera motion is determined in a three-dimensional image capture system using a combination of two-dimensional image data and three-dimensional point cloud data available from a stereoscopic, multi-aperture, or similar camera system. More specifically, a rigid transformation of point cloud data between two three-dimensional point clouds may be more efficiently parameterized using point correspondence established between two-dimensional pixels in source images for the three-dimensional point clouds.

Abstract: Capturing and processing facial motion data includes: coupling a plurality of sensors to target points on a facial surface of an actor; capturing frame by frame images of the plurality of sensors disposed on the facial surface of the actor using at least one motion capture camera disposed on a head-mounted system; performing, in the head-mounted system, a tracking function on the frame by frame images of the plurality of sensors to accurately map the plurality of sensors for each frame; and generating, in the head-mounted system, a modeled surface representing the facial surface of the actor.

Abstract: The method provides a visualization technique for rendering multidimensional data points as 2D curves on a 3D plot with the third dimension representing their order in the multidimensional data set. The technique uses colour palettes to render individual data curves, which enables visual analysis of the entire dataset based on the colour characteristics of the resulting image. The method also suggests a technique for: a) visualizing a distance between multidimensional data points; c) showing a linear segment between two multidimensional data points; d) displaying a colour map of an individual multidimensional point or data set; e) displaying a multidimensional data interval.

Abstract: The pose of a photographic image of a portion of Earth may be estimated using human assistance. A 3D graphics engine may render a virtual image of Earth from a controllable viewpoint based on 3D data that is representative of a 3D model of at least a portion of Earth. A user may locate and display a corresponding virtual image of Earth at a viewpoint that approximately corresponds to the pose of the photographic image by manipulating user controls. The photographic image and the corresponding virtual image may be overlaid on one another so that both images can be seen at the same time. The user may adjust the pose of one of the images while overlaid on the other image by manipulating user controls so that both images appear to substantially align with one another. The settings of the user controls may be converted to pose data that is representative of the pose of the photographic image within the 3D model.

Abstract: A method for self-recalibration of a structured light vision system including a camera and a projector. A camera plane and a projector plane are defined, a Homography matrix between the camera plane and the projector plane is computed, and a translation vector and a rotation matrix are determined from Homography-based constraints. A computer vision system implementing the method is also described.

Abstract: An image generation system includes a first image generation section for generating images IL1 and IR1 for the left eye and the right eye, a second image generation section for generating images IL2 and IR2 for the left eye and the right eye by performing correction processing to remove perspective of images in the IL1 and IR1 at a base surface, and a stereoscopic image generation section for generating a stereoscopic image based on the IL2 and IR2.

Abstract: Systems and methods are disclosed for three-dimensional (3-D) characterization and clinical classification of spinal deformity. By choosing three points on frontal and sagittal 2-D images, a 3-D segmented reconstruction of a spine is made available. Two additional bendAg images provide further information for a Lenke classification of the spine under consideration.

Abstract: This invention provides computerized image guidance systems for deep brain stimulation (DBS) surgery and related methods that improve accuracy of positioning of electrodes in the brains of subjects. Image guidance systems in accordance with the present invention incorporate advanced features such as capability of displaying, in any desired plane of view, a digitized three-dimensional neuroanatomical brain map that can be form fitted to a patient's medical images, such as brain MR images, and capability of displaying on the patient's medical images both the contours of anatomic structures from a digitized brain map, and digitized electrode recording data obtained intra-operatively.

Abstract: A method includes generating a first plurality of meshes configured to map a first domain associated with a display surface to a second domain associated with an image capture device configured to capture a first image of the display surface, and generating a second plurality of meshes configured to map the second domain to a third domain associated with a first projector configured to display a second image onto the display surface. A third plurality of meshes is generated using the first plurality of meshes and the second plurality of meshes. The third plurality of meshes is configured to separately map a plurality of color bands between the first domain and the third domain.

Abstract: A method and apparatus for performing 2D to 3D registration includes an initialization step and a refinement step. The initialization step is directed to identifying an orientation and a position by knowing orientation information where data images are captured and by identifying centers of relevant bodies. The refinement step uses normalized mutual information and pattern intensity algorithms to register the 2D image to the 3D volume.

Abstract: A method of estimating three-dimensional camera position information from a series of two-dimensional images that form a panorama employs common features in adjoining image pairs in the series to estimate a transform between the images in the pairs. The common features are subsequently employed to adjust an estimated rotational component of each transform by reducing error between coordinates corresponding to the common features in three-dimensional space in image pairs, on a pair-by-pair basis. A global optimization of the position estimation, used for long sequences of images such as 360 degree panoramas, refines the estimates of the rotational and focal length components of the transforms by concurrently reducing error between all 3D common feature coordinates for all adjoining pairs.

Abstract: A method of reproducing a three dimensional (3D) image by counter-distorting a two dimensional (2D) image prior to vacuum forming. A captured or obtained image of a subject is digitalized into 3D and 2D formats and used to create a 3D surface using a CNC machine. A standardized grid pattern with numerous reference points is printed on a vacuum formable material and vacuum formed on the 3D surface representing a subject. The reference points on the grid are displaced during the vacuum forming process due to the 3D nature of the surface. If the image of the subject were printed on the vacuum formable material, it would appear distorted. The displaced reference points are observed and the data is entered into the inventive software which generates a new image with compensated morphological changes. When the new image is vacuum formed on vacuum formable material under the same conditions, the new image would not appear distorted and would accurately depict the subject in 3D.

Abstract: Three-dimensional (3D) shapes of particles are characterized from a two-dimensional (2D) image of the particles that is obtained using TEM. The 3D shape characterization method includes the steps of obtaining a 2D image of a batch of nanoparticles, determining 2D shapes of the nanoparticles from the 2D image, and deriving six distributions, each of which corresponds to a 2D shape and a 3D shape associated with the 2D shape. The first size distribution is derived from the nanoparticles having the 2D triangle shape. The second and third size distributions are derived from the nanoparticles having the 2D tetragon shape. The fourth, fifth and sixth size distributions are derived from the nanoparticles having the 2D round shape. Based on these six size distributions, three size distributions, each of which corresponds to one of three 3D shape classes, are estimated.

Abstract: In a 3D image generating apparatus 1 depth values (Z-value) of pixels are calculated on the basis of grayscale values of 2D image data. Next, a reverse determination, smoothing, distribution adjustment, local adjustment, and the like are performed on the Z-values. Next, parallaxes of pixels are determined on the basis of the Z-values of the pixels finally obtained, and the pixels are displaced acceding to the parallaxes, so as to generate data of a stereographic image.

Abstract: A method of generating a stereoscopic image is disclosed. The method includes defining at least two, three or more regions in a scene representing a region of interest, a near regions and/or a far region. This is followed by forming an image pair for each region, this image pair containing the information relating to objects in or partially in their respective region. The perceived depth within the regions is altered to provide the ideai or best perceived depth within the region of interest and acceptable or more compressed perceived depths in the other regions. The image pairs are then mapped together to form a display image pair for viewing on a display device.

Abstract: A method and apparatus for reproducing metadata provides a data structure in which metadata whose preferential reproduction is desired can be selected and reproduced. The metadata relevant to a moving image includes a stream data structure including one or more access units each being a data unit which can be independently processed, and each of the access units includes first data to specify an effective period defined with respect to a time axis of the moving image, object area data describing a spatio-temporal region in the moving image, second data including one of or both of data to specify a display method relevant to the spatio-temporal region and data to specify a processing to be performed when the spatio-temporal region is specified, and third data to specify, in a case where one or more access units exist on a same screen in the moving image at a time of reproduction of the metadata, reproduction priority of each of the access units.

Abstract: A method, medium, and apparatus processing depth information of a depth image. The apparatus adaptively presenting information on depth information includes a section determination unit determining which one of plural sections respective depth values for pixels of the 3D image fall within, with the plural sections being defined by a measured limit distance for the 3D image being parsed into the plural sections based on distance based depth resolution information, and an adaptive quantization unit to selectively quantize and represent each depth value based on a respective predefined quantization setting of the one section.

Abstract: The present invention provides a method of generating a pseudo-3D user-adapted avatar by using artificial intelligence based on a method of converting a 2D image to the pseudo-3D image having visual and partial functions of a 3D model, and a method of performing a coordination simulation by applying the pseudo-3D coordination image generated by applying total clothes coordination information derived from the artificial intelligence to a user-adapted avatar. The pseudo-3D user-adapted avatar is generated by receiving primary size information and deriving secondary size information from an algorithm by using the primary size information. The pseudo-3D user-adapted avatar image suitable to the user's body shape is generated from the 2D standard avatar image.

Abstract: A three-dimensional CG manipulation apparatus has a real object, a position and orientation sensor provided to the real object, a support base, a position and orientation sensor provided to the support base, a head-mounted display, a position and orientation sensor provided to the head-mounted display, a sensor information acquisition unit for acquiring information from the sensors, a state determination unit for determining the current state of the real object and support base, a CG data management unit for managing CG data to be displayed, and an image generation unit for generating an image to be displayed on the head-mounted display. In a mixed realty system that presents an image formed by superimposing a virtual CG image on a real object to the user, a manipulation such as replacement or the like can be easily made for the virtual CG image without interrupting the user's operation.

Abstract: The method/device reconstructs/represents multidimensional objects from one- or two-dimensional image data based on recordings of one- or two-dimensional partial image areas, wherein spatial/positions of individual partial image areas are used along with one- or two-dimensional image information of the individual partial image areas to generate one- or two-dimensional image data, wherein a first group of space elements is generated in a multidimensional voxel space from first space elements which contain multidimensional image information and touch/intersect planes or lines of partial image areas by means of the one- or two-dimensional image data, and wherein a second group of space elements is generated in the multidimensional voxel space from second space elements by means of information transformation from the multidimensional image information of the first group of space elements.

Abstract: In accordance with one or more aspects, a plane in a 3D coordinate system in which a 3D model is to be generated based on one or more 2D images is identified. A direction of extrusion for the plane is also identified. Additionally, a user identification of a region of interest on a 2D image is received and projected onto the plane. A location in the 3D model of the region of interest is then automatically identified by extruding the plane along the direction of extrusion until the region of interest in the plane matches a corresponding region of at least one of the one or more 2D images.

Abstract: In an apparatus and method for generating a three-dimensional representation from a two-dimensional image, a memory device stores information for processing a two-dimensional image and for generating a three-dimensional image from the two-dimensional image, a processing device processes a digital representation of an image by generating a two-dimensional image from the digital representation and by generating a three-dimensional image corresponding to the two-dimensional image, and an output device outputs a three-dimensional image and a digital signal representation of the three-dimensional image.

Abstract: Conventionally, there has been a problem that a viewer is tired when playing back images mixedly including 2D images and 3D images, because images change frequently. A storage part stores 2D images and 3D images, an image conversion part that converts the 2D image stored in the storage part into a new 3D image, and an image output part that outputs the 3D image stored in the storage part and the new 3D image converted by the image conversion part. Consequently, it is possible to prevent a viewer from tiring when playing back images mixedly including 2D images and 3D images.

Abstract: The invention relates to a method, system and computer program product for registering 3D image data. It comprises (a) receiving a first 3D image and a second 3D image; (b) determining a rendering transform for applying to each of the first 3D image and the second 3D image; (c) applying the rendering transform to the first 3D image to provide a first 2D projection and to the second 3D image to provide a second 2D projection; and (d) determining an elastic registration for mapping locations of the first 2D projection to homologous locations in the second 2D projection.

Abstract: Provided are a method and apparatus for receiving and generating an image data stream including a three dimensional (3D) image. The method of receiving an image data stream includes receiving an image data stream including at least one of two dimensional (2D) and 3D image data periods; extracting local 3D image parameters, which are parameters of each image data period, from the image data stream; and restoring at least one of 2D and 3D images by using the local 3D image parameters. In the method, each 3D image is composed of at least one of a base image and an additional image, and the local 3D image parameters include stereoscopic arrangement order information representing an arrangement order of the base image and additional image of the 3D image.

Abstract: Provided is a program that is executed by an image processing apparatus including a memory and a processor, and which generates two-dimensional image data obtained by performing perspective projection to a virtual three-dimensional space on a prescribed perspective projection plane. The program causes the processor to perform processes of (a) arranging a viewpoint in the virtual three-dimensional space, generating basic image data by performing perspective projection on the perspective projection plane set in correspondence to the viewpoint, and storing the basic image data in the memory; (b) setting a concentration map showing a concentration value associated with a partial region of the basic image data, and storing the concentration map in the memory; (c) reading texture data from the memory; and (d) generating the two-dimensional image data by synthesizing the texture data with the basic image data at a ratio according to the concentration value set with the concentration map.

Abstract: A method of generating model data representative of a model in a three-dimensional space of an object from input signals representative of a set of images of the object taken from a plurality of respective camera positions includes the steps of displaying a model image derived from the model data and having a plurality of primitives for viewing by a user, receiving at least one primitive selection signal responsive to user actuation of an input whereby each primitive selection signal identifies a respective selected primitive of the model, and defining a plurality of virtual cameras in the three dimensional space having positions and look directions relative to the model which correspond substantially to those of the respective actual cameras relative to the object.

Abstract: A system and method locate a central groove in a document such as a book, magazine, or catalog. In one implementation, scores are generated for points in a three-dimensional image that defines a surface of the document. The scores quantify a likelihood that a particular point is in the groove. The groove is then detected based on the scores. For example, lines may be fitted through the points and a value calculated for the lines based on the scores. The line corresponding to the highest calculated value may be selected as the line that defines the groove.

Abstract: A medical image processing apparatus which performs image processing on a medical input image, includes: a pixel extraction portion for extracting an inappropriate pixel satisfying a predetermined condition in the input image, a replacing pixel information calculation portion for calculating replacing information with which pixel information of the inappropriate pixel is to be replaced, based on pixel information of a predetermined region including the extracted inappropriate pixel or adjacent to the extracted inappropriate pixel and a replaced image generation portion for replacing the pixel information of the inappropriate pixel in the input image with the replacing information and generating a replaced image.

Abstract: A method and system for generating 3D images of faces from 2D images, for generating 2D images of the faces at different image conditions from the 3D images, and for recognizing a 2D image of a target face based on the generated 2D images is provided. The recognition system provides a 3D model of a face that includes a 3D image of a standard face under a standard image condition and parameters indicating variations of an individual face from the standard face. To generate the 3D image of a face, the recognition system inputs a 2D image of the face under a standard image condition. The recognition system then calculates parameters that map the points of the 2D image to the corresponding points of a 2D image of the standard face. The recognition system uses these parameters with the 3D model to generate 3D images of the face at different image conditions.

Abstract: The invention relates to a method for processing of a three-dimensional image data set, wherein the three-dimensional image data set is converted to a data set suitable for a two-dimensional image reproduction. The invention further relates to apparatuses for performing the required calculations and/or for reproduction of the data representations. The invention is particularly appropriate for medical applications of endoscopy, in particular, coloscopy.

Abstract: The present invention relates to a method and a system for creating three-dimensional models of objects from sets of arbitrary three-dimensional entities obtained from target surfaces. It also provides an efficient method for individually refining the alignment of curves to improve the accuracy of the surface model with a linear complexity with respect to the number of curves. The principle behind the invention is that a set of three-dimensional entities, at their approximate positions, creates a field from which the surface can be extracted. The field is constructed in a manner such that the three-dimensional entities are attracted toward the extracted surface. This attraction is used to accurately register each three-dimensional entity with respect to extracted surface. Through iterations, both the field and the entity positions are refined.

Abstract: A program for pasting a predetermined image onto a character of a game in a game machine. The program enables a user to create an image consisting of two-dimensional coordinates and to arrange the image created. The program includes the ability to project the image onto a character, at arbitrary positions, in the vicinity of the character in a three-dimensional virtual space, and for pasting on the character a projected image created by projecting the image onto the character from the projection light source.

Abstract: A plurality of parameters included in a predetermined illumination equation which defines a brightness are acquired for each pixel of an image. For each of the parameters, a homogeneous region including pixels which are similar in value of the parameter is specified. In each of the specified homogeneous region, each of the parameters is converted according to details of the predetermined image conversion. The brightness of each pixel of a second image is determined using the values of the parameters obtained after the conversion.

Abstract: Such processes as compression, storage and reproduction of an image mapped on a three-dimensional coordinate system such as a spherical surface or a cylindrical surface are performed suitably by mapping omnidirectional map information to a two-dimensional image such that the redundancy may be low while the amounts of information is kept equal as far as possible with minimized errors. Preferably, the image is converted into a two-dimensional image in a form determined taking the performance of the omnidirectional video image reproduction side into consideration. The technique can be utilized when mapping information which describes a corresponding relationship between the three-dimensional coordinate system of the original omnidirectional image and the mapped two-dimensional image coordinate system is produced to synthesize an omnidirectional video image from an arbitrary viewpoint direction.

Abstract: The present invention relates to a method for registration of a sequence of 2D image data (5) of a hollow channel (2), in particular of a vessel, recorded with an imaging endoluminal instrument (1) when the relative displacement positions of the instrument (1) in the hollow channel (2) are known, with 3D image data (8) of the hollow channel (2). In the method a three-dimensional path of a central axis (10) of a definable section of the hollow channel (2) is determined from the 3D image data (8), the three-dimensional path of the central axis (10) is converted into a rectilinear path by a first transformation of the 3D image data (8) of the definable section of the hollow channel (2) and transformation parameters required for the first transformation are stored.

Abstract: System and method for constructing a 3D model of an object based on a series of silhouette and texture map images. In the exemplary embodiment an object is placed on a rotating turntable and a camera, which is stationary, captures images of the object as it rotates on the turntable. In one pass, the system captures a number of photographic images that will be processed into image silhouettes. In a second pass, the system gathers texture data. After a calibration procedure (used to determine the camera's focal length and the turntable's axis of rotation), a silhouette processing module determines a set of two-dimensional polygon shapes (silhouette contour polygons) that describe the contours of the object. The system uses the silhouette contour polygons to create a 3D polygonal mesh model of the object. The system determines the shape of the 3D model analytically by finding the areas of intersection between the edges of the model faces and the edges of the silhouette contour polygons.

Abstract: A method of rendering a multi-view image comprising a first output image and a second output image on basis of an input image (102) is disclosed. The method comprises: creating a modulation image (100) comprising irregular shaped objects (106-112); modulating pixel values of a portion of the input image (102) on basis of further pixel values of the modulation image (100), resulting into an intermediate image (104); and generating the multi-view image by means of warping the intermediate image on basis of the disparity data.

Abstract: A system and related method for automatically aligning a plurality of 2D images of a scene to a first 3D model of the scene. The method includes providing a plurality of 2D images of the scene, generating a second 3D model of the scene based on the plurality of 2D images, generating a transformation between the second 3D model and the first 3D model based on a comparison of at least one of the plurality of 2D images to the first 3D model, and using the transformation to automatically align the plurality of 2D images to the first 3D model.

Abstract: A method for deriving three-dimensional measurement information and/or creating three-dimensional models and maps, from single images of at least one three-dimensional object is provided.

Abstract: A system includes a stereoscopic camera to generate images of a document, such as a book, that can be converted to a three-dimensional contour of the document. A second camera take a two-dimensional image of the document. A model is generated that defines a mapping between the three-dimensional contour of the document and a two-dimensional flattened (de-warped) version of the document. The model may be applied to the two-dimensional image taken by the second camera to compensate for warping in the image.