11543 results about "Image generation" patented technology

Depth maps are generated from a monoscopic source images and asymmetrically smoothed to a near-saturation level. Each depth map contains depth values focused on edges of local regions in the source image. Each edge is defined by a predetermined image parameter having an estimated value exceeding a predefined threshold. The depth values are based on the corresponding estimated values of the image parameter. The depth map is used to process the source image by a depth image based rendering algorithm to create at least one deviated image, which forms with the source image a set of monoscopic images. At least one stereoscopic image pair is selected from such a set for use in generating different viewpoints for multiview and stereoscopic purposes, including still and moving images.

Disclosed herein is a method of creating a customized arthroplasty jig. The method may include: generating two-dimensional MRI images of a patient's joint area to undergo arthroplasty; electronically orienting the two dimensional MRI image slices to account for the patient's joint area being randomly physically oriented in a scanning area of a MRI machine; generating a three-dimensional bone image of at least a portion of a bone of the patient's joint area from the generated two-dimensional MRI images; using the three-dimensional bone image to generate data pertaining to the customized arthroplasty jig, wherein the data includes bone surface information; providing the data to at least one manufacturing device; and employing the bone surface information to cause the at least one manufacturing device to create a surface on the arthroplasty jig configured to matingly receive a surface of the bone.

We describe a road vehicle contact-analogue head up display (HUD) comprising: a laser-based virtual image generation system to provide a 2D virtual image; exit pupil expander optics to enlarge an eye box of the HUD; a system for sensing a lateral road position relative to the road vehicle and a vehicle pitch or horizon position; a symbol image generation system to generate symbology for the HUD; and an imagery processor coupled to the symbol image generation system, to the sensor system and to said virtual image generation system, to receive and process symbology image data to convert this to data defining a 2D image for display dependent on the sensed road position such that when viewed the virtual image appears to be at a substantially fixed position relative to said road; and wherein the virtual image is at a distance of at least 5 m from said viewer.

An image generating apparatus comprising: a camera or a plurality of cameras; space reconstructing means for mapping the input image from said camera, into a predetermined space model of a predetermined three-dimensional space; point-of-view converting means of synthesizing an image viewed from an arbitrary virtual point of view in said predetermined three-dimensional space by referencing to said space data mapped by said space reconstructing means; and displaying means of displaying the image converted by said point-of-view converting means.

Methods and apparatuses to generate stereoscopic views for image guided surgical navigation. One embodiment includes transforming a first image of a scene into a second image of the scene according to a mapping between two views of the scene. Another embodiment includes generating a stereoscopic display of the scene using a first image and a second image of a scene during a surgical procedure, where a position and orientation of an imaging device is at least partially changed to capture the first and second images from different viewpoints. A further embodiment includes: determining a real time location of a probe relative to a patient during a surgical procedure; determining a pair of virtual viewpoints according to the real time location of the probe; and generating a virtual stereoscopic image showing the probe relative to the patient, according to the determined pair of virtual viewpoints.

A method and system of compensation for intra-operative organ shift of a living subject usable in image guide surgery. In one embodiment, the method includes the steps of generating a first geometric surface of the organ of the living subject from intra-operatively acquired images of the organ of the living subject, constructing an atlas of organ deformations of the living subject from pre-operatively acquired organ images from the pre-operatively acquired organ images, generating a second geometric surface of the organ from the atlas of organ deformations, aligning the second geometric surface of the organ to the first geometric surface of the organ of the living subject to determine at least one difference between a point of the first geometric surface and a corresponding point of the second geometric surface of the organ of the living subject, which is related to organ shift, and compensating for the intra-operative organ shift.

This invention comprises a method and system for displaying free-space, full color, high-resolution video or still images while simultaneously enabling the user to have real-time direct interaction with the visual images. The system comprises a self-generating means for creating a dynamic, non-solid particle cloud by ejecting atomized condensate present in the surrounding air, in a controlled fashion, into an invisible particle cloud. A projection system consisting of an image generating means and projection optics, projects an image onto the particle cloud. Any physical intrusion, occurring spatially within the image region, is captured by a detection system and the intrusion information is used to enable real-time user interaction in updating the image. This input/output (I/O) interface provides a display and computer link, permitting the user to select, translate and manipulate free-space floating visual information beyond the physical constraints of the device creating the image.

A near-eye display projects virtual images from an image generator to an eyebox within which the virtual images can be seen by a viewer. A first optical path conveys image-bearing light from the image generator to a selectively reflective powered optic and a second optical path conveys the image-bearing light along a line of sight from the selectively reflective powered optic to the eyebox. First and second selectively reflective surfaces fold the first optical path with respect to the second optical path to locate the image generator out of the line of sight to the eyebox. The image generator is effectively inclined to the line of sight to the eyebox for reducing a thickness of the near-eye display. The selectively reflective powered optic is oriented normal to local overlapping portions of the first and second optical paths at the selectively reflective powered optic.

An image processing apparatus for generating a three-dimensional model of a three-dimensional object from an image displaying the object in two dimensions includes a three-dimensional model generator operable to generate the three-dimensional model of the object from the image, and an extender operable to extend a lateral region of the three-dimensional model in a depth direction orthogonal to the two dimensions.

A method for determining if a set of images in a large collection of images are near duplicates is described. The method includes processing the set of images, generating an image signature for each image in the set of images, and comparing the generated image signatures. The method can be used in clustering and ranking of images.

A method for generating customized photo album pages for a collection of digital images comprises the steps of: (a) obtaining a plurality of digital images; (b) automatically grouping the images into one or more image sets based on at least one of grouping by events and grouping by people present in the images; (c) automatically profiling the images within each image set according to image content, thereby relating a particular image set to one or more design themes; (d) providing a database of design elements that may be used to generate customized photo album pages; (e) utilizing the design themes generated by the profiling step to automatically suggest one or more design elements from the database of design elements; and (f) automatically generating a customized photo album page layout for each image set by applying one or more of the suggested design elements to the page layout.

The invention relates to a method and an apparatus for generating a depth map from a digital monoscopic color image. The method includes the following general steps: a) obtaining a first color component of the MCI, said first color component corresponding to partial color information of the MCI; and, b) assigning depth values to pixels of the MCI based on values of the first color component of respective pixels for forming the depth map for the MCI. In one embodiment, the depth values are generated by adjusting and/or scaling of pixel values of the Cr chroma component of the monoscopic source color image in the Y′CbCr color system.

Images with enhanced resolution are created with a display device comprising a non-transmissive light valve including addressable pixels, a light source that directs light to the light valve, and a lens positioned between the light valve and the light source, the lens directing light from the light source to the pixels on the light valve and the light valve directing light to viewing optics. The light valve is an integrated circuit ferroelectric liquid crystal device (ICFLCD), or other light valve arrays such as a digital light processor (DLP) display, having an array of addressable pixels. Such light valves may be mounted in a head mounted display.

A road skeleton estimation system generates an estimate as to a skeleton of at least a portion of a roadway ahead of a vehicle. The road skeleton estimation system includes an image receiver and a processor. The image receiver is configured to receive image information relating to at least one image recorded ahead of the vehicle. The processor is configured to process the image information received by the image receiver to generate an estimate of the skeleton of at least a portion of the roadway ahead of the vehicle.

To provide a sub-picture unit generation apparatus for generating a plurality of sub-picture units that compose a sub-picture stream which is interleaved with a video stream into a system stream, each sub-picture unit including a subtitle image that is to be superimposed on moving images reproduced from the video stream. The sub-picture unit generation apparatus includes an attribute storage unit for storing a display attribute that shows a base position for arranging each subtitle image, a character string storage unit for storing a plurality of subtitle character strings, a subtitle image generation unit for generating a subtitle image from one of the plurality of subtitle character strings stored in the character string storage unit, a display position determination unit for determining a display position of the subtitle image according to the display attribute, and a sub-picture unit generation unit for generating a sub-picture unit that includes the subtitle image and display position data showing the determined display position.

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. The pseudo-3D coordination image is generated, from the standard 2D image by using coordination-related information, by an artificial intelligence algorithm, and in response to a corrected pseudo-3D user-adapted avatar image, the generated pseudo-3D coordination image is displayed.

A video game character or avatar is generated using images of the player so that the on-screen avatar being controlled by the player appears like the player. Answers to a questionnaire or a psychological profile are provided by the player to determine characteristics that the player views as desirable, which are used to generate a final version of the avatar. Iterations of the avatar appearance are generated from the initial appearance to the final, more desirable appearance. Using the avatar, as play of the game proceeds the player's avatar begins as a character appearing like themselves and gradually becomes a character that is more as they would like to appear. The avatar increases the emotional impact of games by providing strong visual and psychological connections with the player. The avatar may instead begin from an initial character that does not appear similar to the player. The iterations may make the avatar gradually less appealing or with other changes in appearance, in some embodiments.

A 3D image generation and display system facilitating the display of high-quality images in a Web browser comprises means for creating 3D images from a plurality of different images and computer graphics modeling and generating a 3D object from these images that has texture and attribute data; means for converting and outputting the 3D object as a 3D description file in a 3D graphics descriptive language; means for extracting a 3D object and textures from the 3D description file, setting various attribute data, and editing and processing the 3D object to introduce animation or the like and assigning various effects; means for generating various Web-based 3D objects from the 3D data files produced above that are compressed to be displayed in a Web browser and generating behavior data to display 3D scenes in a Web browser with animation; and means for generating an executable file comprising a Web page and Web-based programs such as scripts, plug-ins, and applets for drawing and displaying 3D scenes in a Web browser.

A background image generator 51 renders a first 3D model representing a landscape to generate a background image, an image generator 52 generates a second 3D model to be located between a camera viewpoint and the first 3D model, an image adhering unit 53 selects a specified range of the background image and adheres the background image within the selected range as a texture to the second 3D model, and a combined image generator 54 renders the second 3D model having the background image within the specified range adhered thereto and combines the rendered model with the background image to generate a combined image.

Character data including an image generation program, image data, a sound program, and sound data, which are previously determined for each of characters used in a game, is stored in a game device 10. A controller 12 having a built-in tilt sensor 12c is connected to the game device, and operated by a player performing a tilt operation. The image generation program and the sound program concurrently process the image data and the sound data, respectively, using the same tilt data output from the tilt sensor. As a result, an image and sound of the character are concurrently changed in accordance with the tilt operation of the controller. Thus, it is possible to provide the game device enhancing the realism and the staging effects of the game.

A method of generating one or more new digital images using an original digitally-acquired image including a selected image feature includes identifying within a digital image acquisition device one or more groups of pixels that correspond to the selected image feature based on information from one or more preview images. A portion of the original image is selected that includes the one or more groups of pixels. The technique includes automatically generating values of pixels of one or more new images based on the selected portion in a manner which includes the selected image feature within the one or more new images.