Abstract: The present invention provides an apparatus which displays a plan wiring diagram and three-dimensional layout diagram by associating them with each other so that they can be viewed easily. A apparatus for displaying wiring includes a first storage for storing an image of a plan wiring diagram which shows parts and wirings and a second storage for storing a three-dimensional layout of an apparatus which incorporates the parts and the wirings, and a third storage for storing intermediate images transitional between a starting image in the plan wiring diagram and an ending image of a shape of the corresponding wiring in the three-dimensional layout. A processor displays the plan wiring diagram on the display device by retrieving the plan wiring diagram from the first storage based on a user's selection, and retrieves the intermediate images of a wiring from the third storage when the wiring is selected from the plan wiring diagram and displays transitions to the shape shown in the three-dimensional layout.

Abstract: A system for providing paper models over a wide area computer network includes a user computer that communicates with a model server via the Internet. The model server includes a database of paper model files, e.g., the pieces of the models and assembly instructions. The corresponding method allows a user to access the model server via the Internet and download paper models. The paper models are printed at a printer connected to the user computer. A user can then assemble the paper models following the assembly instructions.

Abstract: An application may feature a number of application states among which a process shifts during execution of the application. A user or software developer may wish to define one or more transitions to be rendered between a first application state and a second application state, but the application development environment and operating system may provide only a limited number of general-purpose transitions. Instead, a pluggable architecture may be devised to permit a user or software developer to provide a custom transition, and to specify the rendering of the custom transition between application states. The pluggable architecture may therefore enable the user or software developer to define new transitions that are more relevant and complementary of the application states in transit.

Abstract: The present invention relates to an apparatus and method for creating a three-dimensional caricature, and more particularly, to an apparatus and method for creating a three-dimensional caricature having a high degree of similarity to user's face by precisely extracting feature point information on facial features and modifying a three-dimensional polygon face basic model based on the feature point information using an ASM technique specialized for faces. The method comprises the steps of detecting the positions of eyes from an input facial image and normalizing the size of the facial image, detecting each initial position for facial features from the normalized facial image, loading ASMs in the normalized facial image so as to correspond to the detected initial position and then extracting feature points for the facial features, and creating a three-dimensional polygon face caricature by modifying the three-dimensional polygon face basic model according to coordinate values of the extracted feature points.

Abstract: A computer readable storage medium comprises executable instructions to display a first visualization associated with a first set of data. A display transformation from the first visualization into a second visualization is animated by morphing selected polygons in the first visualization into corresponding polygons in the second visualization while fading the first visualization into the second visualization.

Abstract: Techniques for providing visual feedback to illustrate the effects of editing operations are provided. This visual feedback may be provided in the form of an animated image that visually represents the pre-operation data gradually “morphing” into the data as affected by an operation. The data may be digital signal data that represents a recording of sound, for example. In response to a user's activation of a particular editing operation that affects the data, a resulting visual representation is generated. The resulting visual representation represents the data in the post-operation state, after the effects of the particular editing operation have been applied to the data completely. However, before the resulting visual representation is displayed, intermediate, interpolated visual representations of the data are generated and displayed.

Abstract: A method and system for surfacing of particle systems is proposed to achieve high surface resolutions and low execution times, comprising partitioning particles into sub-blocks, each sub-block associated linear data arrays, sequentially accessing each array to composite the particles into a respective sub-volume using estimates of grid stencils derived from particle kernels, performing random-access into the sub-volumes, processing each linear array, and lexicographically pushing the corresponding sub-volume into a DT-Grid to convert the sub-volume to a narrow band level set. Further steps to improve the temporal coherence of resulting surface, to reduce artifacts from sparsely sampled regions of space, to enhance artistic expression, and for flexible post processing can be performed.

Abstract: A caricature generating system and method. The caricature generating system comprises an edge tracing and stroking unit, a posterizing and texturing unit, an image blending unit, a facial image adjusting unit, a cartoon theme composition unit, a styling parameters database comprising a plurality of styling parameters including the control parameters for edge tracing, stroking, posterizing, and texturing, a face adjusting parameter database comprising a plurality of face adjusting parameter set, and a cartoon theme database comprising a plurality of cartoon themes, thereby creating a caricature from a facial image. The styling parameters (including the control parameters for edge tracing, stroking, posterizing, and texturing), created manually or by a software, comprise oil paint, pastel, a wax crayon, marker pen, pen drawing, tempera paint, glue color paint, halftone, watercolor paint, block print, woodcut, color pencil, charcoal and their combinations.

Abstract: A representation of an object in a live event is detected in an image of the event. A location of the object in the live event is translated to an estimated location in the image based on camera sensor and/or registration data. A search area is determined around the estimated location in the image. A direction of motion of the object in the image is also determined. A representation of the object is identified in the search area by detecting edges of the object, e.g., perpendicular to the direction of motion and parallel to the direction of motion, performing morphological processing, and matching against a model or other template of the object. Based on the position of the representation of the object, the camera sensor and/or registration data can be updated, and a graphic can be located in the image substantially in real time.

Abstract: A method of registering two images using a graphics processing unit includes providing a pair of images with a first and second image, calculating a gradient of the second image, initializing a displacement field on the grid point domain of the pair of images, generating textures for the first image, the second image, the gradient, and the displacement field, and loading said textures into the graphics processing unit. A pixel buffer is created and initialized with the texture containing the displacement field. The displacement field is updated from the first image, the second image, and the gradient for one or more iterations in one or more rendering passes performed by the graphics processing unit.

Abstract: A user provides a plurality of video frames for processing, and selects a cartoon color palette. The color of all selected pixels within all selected video frames is changed to that of the closest match in color within the cartoon color palette and is stored in a memory. Optionally, the user may create a custom cartoon color palette, and may select less than all of the pixels in any given video frame for processing.

Abstract: An image morphing method is suitable for generating an intermediate image sequence. First, a control point CP={(pi,qi)}i=1 . . . N is specified and marked in a source image Is({right arrow over (x)}) and a destination image Id({right arrow over (x)}?). Next, an edge gradient parameter (Ise({right arrow over (x)}), Ide({right arrow over (x)}?) is computed according to the source image Is({right arrow over (x)}) and the destination image Id({right arrow over (x)}?). Next, a total objective function E(Df,Db) is computed according to the above-mentioned control point CP and edge gradient parameter (Ise({right arrow over (x)}), Ide({right arrow over (x)}?)). The above-mentioned intermediate image sequence is generated by using the total objective function E(Df,Db). The present invention utilizes the edge gradients of the source image Is({right arrow over (x)}) and the destination image Id({right arrow over (x)}?) to enhance the constraint of image morphing. Thus, the image morphing effect is promoted.

Abstract: A system, method, apparatus and product for designing, on a display device, a geometric shape is disclosed. The method comprises the steps of displaying an initial set of similarly structured model exemplars on a display device, selecting a chosen set of models from the initial set of similarly structured model exemplars to apply to a model mix, mixing the set of models to form a currently displayed shape, providing on the display device at least one selectable feature for manipulating the currently displayed shape, and applying at least one constraint of the selectable feature to the currently displayed shape to update the currently displayed shape into a new geometric shape design.

Abstract: A method of displaying information on a mobile terminal. The method includes displaying an object on a screen of the mobile terminal, receiving at least two least two input signals corresponding to the displayed object, and animating the displayed object based on the at least two signals corresponding to the displayed object. In addition, the at least two input signals include a) first and second touching signals of the screen of the mobile terminal, b) touching and tilting signals of the mobile terminal, or c) a first proximity signal and a second proximity signal of the mobile terminal.

Abstract: A method of generating a morphing sequence utilizing a computer, the method comprising the step of user-defining respective components in a source object and a target object respectively, wherein each component comprises a plurality of local features of respective source and target meshes representing the source and target objects, and user-defining corresponding components between the source object and the target object. The method may further comprise the step of computer-deducing correspondences between components in the source and target objects based on the user-defined correspondences between other components.

Abstract: A method, apparatus, and article of manufacture provide the ability to manipulate an image transformation over time. A source image is selected from a first frame and a destination image is selected from a second frame. A first animation axis that defines a first two-dimensional transformation of the source image over time and a second animation axis that defines a second two-dimensional transformation of the destination image over time are both determined. The transformation of the source image to the destination image is manipulated by manipulating the second axis. Further, input from a user may be accepted for adjusting a coarseness of a lattice structure that controls an accuracy and affect of points with respect to each other during the transformation process. Lastly, the correspondence or mapping between sample points on the source and destination images may be manipulated over time.

Abstract: An image processing apparatus comprises: a predicted information storage section which stores predicted information that indicates an operation content predicted for an image of a target operation; a predicted image generating portion which generates a predicted image which corresponds to the image of the target operation based on a predicted information; a control section which detects whether input operation content matches the operation contents in the predicted information; and a display control section which displays a predicted image generated by the predicted image generating portion when the control section detects the matching of the operation contents.

Abstract: A method and apparatus for modifying, or morphing, a video image. A video feed is received which include an image of a person's face. A number of facial features are detected from the video feed. One or more of those facial features are selected and modified, with the modification being applied to the video feed to produce a morphed image. For example, the morphing can produce fun effects such as oversized or too small eyes, lips, etc.

Abstract: Provided is a method and apparatus for dynamic cross fading. Specifically, an embedded system can display an image produced from a blend of other images. Initially, a first image and a second image are stored in a buffer in a display controller. Then, the display controller extracts pixels from corresponding locations in the first image and the second image. The pixels are combined with weights associated with each image to perform the cross fade calculation. Consequently, the result from the cross fade calculation is transmitted to a display unit connected to the display controller for viewing. The result can also be fetched during a refresh of a panel in the display unit. In either case, the result is transmitted to a display pipe during dynamic cross fading. Thus, any images stored in the buffer remain unchanged.

Abstract: An average face composition is produced by computer graphic methods surveying average facial features, skin color, lip color and eye color among plural faces representing different human races. Enquiries are performed among a plurality of different people to receive their replies to questions on the obtained faces on which various cosmetics were furnished. The collected comments were analyzed to prepare color maps, whereby necessary information and images were established to enable selection of suitable cosmetics.

Abstract: A method for authoring and displaying a virtual tour of a three-dimensional space which employs transitional effects simulating motion. An authoring tool is provided for interactively defining a series of locations in the space for which two-dimensional images, e.g., panoramas, photographs, etc., are available. A user identifies one or more view directions for a first-person perspective viewer for each location. For pairs of locations in the series, transitional effects are identified to simulate smooth motion between the pair of locations. The authoring tool stores data corresponding to the locations, view directions and transitional effects for playback on a display. When the stored data is accessed, a virtual tour of the space is created that includes transitional effects simulating motion between locations. The virtual tour created can allow a viewer to experience the three-dimensional space in a realistic manner.

Abstract: The present invention consists of a method comprising the steps of displaying an image representing a source value; displaying an image representing a destination value; and displaying a transition image; wherein the transition image is a function of the source value and the destination value. Additionally, the present invention consists of an apparatus comprising: a graphics display device; a memory; a timing unit; and a processing unit coupled to the memory, the timing unit and the graphics display device; wherein the processing unit is configured to provide a transition from a first static value to a second static value; wherein the transition is a function of the first static value and the second static value.

Abstract: A method and system uses geometry-driven feature point analysis to synthesize images including for example facial expressions. Given the feature point positions (geometry) of an expression, the method automatically synthesizes the corresponding expression image, which has photorealistic and natural looking expression details.

Abstract: An approach for morphing between planar shapes is disclosed. Correspondences are established between perceptual feature points that are extracted from both source and target shapes. A similarity metric between two feature points is defined using the intrinsic properties of their local neighborhoods. The optimal correspondence is found by an efficient dynamic programming technique. This approach treats shape noise by allowing the discarding of small feature points, which introduces skips in the traversal of the dynamic programming graph. Intermediate shapes are obtained by interpolating the overall shapes constructed by feature points and the detailed information of the shapes respectively.

Abstract: Locality based morphing in a computer graphics system provides efficient techniques for simulating or animating position-based changes including but not limited to deformations. Two models are provided: a model unaffected by a destructive or other process, and a further model that has been totally affected by the process. Position information is used to specify particular parts of the model to morph. Morphing is selectively applied on a spatially localized basis so that only parts of the object are morphed whereas other parts of the object remain unmorphed. Such techniques can be used for example to simulate or animate progressive damage to a target such as an enemy robot.

Abstract: As characters move, building are rotated and deformed, then, a powerful expression as if the characters moved lively and freely in three-dimensional space. The game machine stores a first image plane for displaying a ground, a second plane for displaying images of upper surfaces of solid bodies of buildings, a third image plane for displaying the background in the graphic memory. A sprite image to be pasted on side surfaces of the buildings and other solid bodies is stored in the graphic memory. Thereby, realistic image expression is realized by displaying solid bodies with the same height.

Abstract: A method and system of distorting an image, particularly but not solely designed for magnifying parts of an image more than the remainder of the image. The method comprises the steps of maintaining in computer memory a set of base data values representing an image to be subjected to a transformation function; calculating a non identity approximation of the transformation function; retrieving from computer memory one or more of the base data values; calculating an intended magnification value (Mc) for one or more of the retrieved base data values; calculating an estimated magnification value (Ms) for one or more of the retrieved base data values; storing in computer memory the estimated magnification values as a set of transformed data values representing the transformed image; calculating the difference (ME) between the intended magnification value(s) and the estimated magnification value(s); and repeating steps (c) to (g) until ME is less than a predefined threshold.

Abstract: The present invention relates to an apparatus and method for generating mosaic images, wherein photographed content is displayed as a still image by a digital TV display or video monitor for an extended period of time. The apparatus of the present invention includes an animation analyzer for output of a motion vector of an input image, a coefficient calculator for calculating transformation and warping coefficients, a means for offsetting illumination differences, and storage for mosaic images. The present invention can advantageously be used for calculating a more accurate transformation coefficient, thereby generating mosaic images with minimal distortion.

Abstract: A method of displaying digital images comprises the steps of using a processor to determine an extent of similarity between a first image part and a second image part, displaying a first image part from a viewpoint and transitioning to displaying a second image part from a viewpoint, the second image part being selected at least partly based on a determined extent of similarity between the first image part and the second image part, in which the viewpoint of an image part is moved either during the transition or after the transition takes place. An appropriate system is provided.

Abstract: A system and method for interactively generating a family of mesh models is provided for use in engineering analysis. The system includes a user computer system having a memory, a processor, a user input device and a display device. The system also includes a remotely located computer system having a processor, a memory, and a data storage means and in communication with the user computer system. The system further includes a computer-generated geometric mesh base model stored in the data storage means, a computer-generated mesh feature stored in the data storage means, and a new mesh model including the base mesh model with a mesh feature that is stored in the data storage means. The method includes the steps of selecting a base model from a model library maintained in the data storage means. The method also includes the steps of creating a mesh feature that is defined by a modifiable set of parameters and saving the mesh feature in a mesh feature library maintained in the data storage means.

Abstract: A method for displaying visual information on a display screen of a computer, comprising the steps of scaling the visual information to produce a scaled representation to fit on the display screen the scaled representation containing the entire content of the visual information; selecting a region of interest within the scaled representation; applying a transformation to the scaled representation to improve the visual detail in the region of interest; and, displaying the transformed presentation on the display screen.

Abstract: Deformations are applied to a model using a subdivision surface. Given a wrap and model, a subdivision surface is calculated from the wrap. The model is then bound to the subdivision surface. When the wrap is deformed, the subdivision surface is recalculated. The model is then deformed based on changes in the subdivision surface. Binding parameters may be assigned to control vertices in the wrap to control the application of the deformation to the surface.

Abstract: Computerized techniques are provided for linking digitized images of serial sections of a biological tissue sample. Linked, digitized images of the serial section are displayed on a display and manipulation of one digitized image causes other digitized images to be similarly manipulated. To link digitized images, a copy of a digitized image of one serial section is positioned over a digitized image of another serial section. The digitized image of the other serial section is visible through the copy. The copy is registered to the digitized image of the other serial section.

Abstract: A system and method for automatically modeling a three dimensional object, such as a face, from a single image. The system and method according to the invention can construct one or more three dimensional (3D) face models using a single image. Although use of a frontal image simplifies the processing, the system and method according to the invention can also generate a 3D model from a non-frontal image (e.g., an image where the object to be modeled has an out of plane rotation, such a face that is turned to one side to some extent). The system is fully automatic. It is fast compared to the other modeling systems. Furthermore, it is very robust. It can be used to construct personalized models for games, on-line chat, and so on. It can also be used as a tool to generate a database of faces with various poses which are needed to train most face recognition systems.

Abstract: A method and apparatus for modifying, or morphing, a video image. A video feed is received which include an image of a person's face. A number of facial features are detected from the video feed. One or more of those facial features are selected and modified, with the modification being applied to the video feed to produce a morphed image. For example, the morphing can produce fun effects such as oversized or too small eyes, lips, etc.

Abstract: Apparatuses and methods are presented that use a direct synthesis approach using layers in order to directly generate a virtual view from a pair of images. In one embodiment, a range space is discretized into a plurality of layers. For each layer, the first input image and the second input image are warped to the layer. A matching score is then determined for each pixel in the new view based on the warped input images. For each pixel in the virtual view, a best layer is determined. After the best layer has been determined, the color of the pixel in that layer is used for that pixel in the generated view.

Abstract: A system and method of modifying a portrait image. The method comprises the steps of: sensing a stimulus; selecting at least one modification in response to the sensing the stimulus; mapping the selected at least one modification to the first portrait image to generate a second digital still portrait image; and displaying, on the display, the second portrait image.

Abstract: A system for generating a target pixel in a target grid from a plurality of source pixels in a source grid, said system comprising, a filter controller for determining a first distance between said target pixel and a source pixel to the left of said target pixel, and a second distance between said target pixel and a source pixel to the right of said target pixel; a left portion lookup circuit for determining filter coefficients for a left portion of said target pixel in accordance with said first difference; a right portion lookup circuit for determining filter coefficients for a right portion of said target pixel in accordance with said second difference; and a filter reconstruction unit for creating a filter in accordance with said left and right portion filter coefficients, said created filter for generating said target pixel from said plurality of source pixels.

Abstract: A transition in an MPEG sequence including anchor pictures and bidirectionally predicted (B) pictures is encoded by a) coding first and second anchor pictures and b) coding a transition in the sequence by inserting B pictures into the bitstream to create the transition from the first anchor picture to the second anchor picture.

Abstract: Efficient, real-time rendering of an output image is implemented using one or more input images and morph maps that include data defining characteristics of each pixel in the output image. The input images can include textures and other graphic data for a surface of an object. Any of a number of different known techniques are used to produce the data included in a morph map for rendering a scene. The morph map is implemented for a rectangular area M (x, y) and associates a set of Mj(x, y) data with each pixel position in the rectangular area, where j is a positive integer providing an index to one of the sets of pixel data associated with a pixel position. A set of up to seven parameters are included in the Mj(x, y) data for each pixel position. Using the morph map, a real-time rendering engine performs a transformation when the displayed scene must be modified in response to a user interaction or in response to some software program event.

Abstract: A method constructs a variable multilinear model representing a class of deformable surfaces. First, meshes of deformable surfaces are acquired. The meshes include vertices. The meshes have different identities and different expressions. The meshes can be obtained from images of human faces, where facial features, such as eyes, eyebrows, cheeks, nose, mouth and chin, form the deformable surfaces. The meshes are stored in a memory as elements of a data tensor. The data tensor is selectively flattened to matrices composed of column vectors. An imputative incremental singular value decomposition is applied to each matrix to generate a set of orthogonal bases. Then, the orthogonal bases are applied to the data tensor, via tensor multiplication, to construct a core tensor, which is the variable multilinear model representing the class of surfaces.

Abstract: An image transformation method for translating a non-linear 2D geometrical transformation into two separable 1D geometrical transformations first determines the inverse of the 2D geometrical transformation to form an inverse 2D geometrical transformation. Then the method converts the inverse 2D geometrical transformation into an analytical inverted 2D geometrical transformation and separates the analytical inverse 2D geometrical transformation into first and second 1D geometrical transformations. The method then represents said inverse 2D geometrical transformation and first and second 1D geometrical transformations as tensor spline surfaces and then compares an evaluation of said first and second 1D geometrical transformations at each pixel with an evaluation of the analytical inverse 2D geometrical transformation at each pixel. If the error evaluation does not meet a predetermined level of performance then the separation and transformation steps are repeated.

Abstract: There are provided an image generating system and program which can generate an image of an object variable in its state depending on an impacted position, in real-time with less amount of data and reduced load in computation. The image generating system generates an image of an aggregate object formed by a plurality of part objects. The image generating system comprises: an object determination section (120) which determines part objects within a predetermined area in the aggregate object as objects to be changed in display form when an impact is applied to the aggregate object and the impacted position is included within the predetermined area; and an image generation section (160) which changes at least one of shape, color, position, rotation angle, direction, moving direction and moving speed of the part objects determined as objects to be changed and generates an image. The aggregate object may be formed by assembling a plurality of part objects having different shapes without any gaps.

Abstract: A method and computer program product for generating a warping effect in an image having a plurality of regions, each associated with a distortion vector. The method includes defining a path segment vector in response to user movement of a brush cursor; modifying one or more distortion vectors having originations covered by the cursor based on the path segment vector; and repeating defining and modifying to produce a warping effect.

Abstract: The present invention provides a method for morphing different geometric shapes while not using algebraic characteristics and overcoming inefficiency of Minkowski sum computation. The method for geometric shape morphing by using direction map so as to smoothly morph more than two different geometric shapes includes the steps of: a) extracting each direction map of the geometric shape; b) merging the direction maps; c) scaling the merged direction map by group; and d) generating a polygon by using an inverse function of a direction map.

Abstract: A virtual makeover system and method are disclosed which allows users to apply beauty products to a personal photographic image, thereby creating a digitally enhanced image. The system includes a product catalog, a palette database, and an image database, all of which may be accessed by a user via a communications network or stored on the hard drive of a user's computer. Users can upload digital photographs of themselves or others, or can retrieve an image from the image database, and outline various features in the photograph. The user may apply selected beauty products available in the product catalog to the various features.

Abstract: A system performs refraction mapping for an image having an object, the object being viewed along at least one line of sight and at least partially through a boundary of first and second at least semi-transparent media. The boundary defines at least one normal vector at one or more intersections of the line of sight and the boundary. The system includes: a perspective transformation unit operable to project a three-dimensional version of the object on a two-dimensional texture plane using a perspective view transformation algorithm to obtain texture addresses of the object, the texture plane being perpendicular to the line of sight and the transformation being performed without regard to refraction; and a refraction determination unit operable to obtain at least one refraction vector for at least one of the texture addresses, a given refraction vector being a function of a component of the at least one normal vector that is parallel to the texture plane.

Abstract: A method and system for circularly symmetric anisotropic filtering over an extended elliptical or rectangular footprint in single-pass digital image warping are disclosed. The filtering is performed by first finding and adjusting an ellipse that approximates a non-uniform image scaling function in a mapped position of an output pixel in the input image space. A linear transformation from this ellipse to a unit circle in the output image space is determined to calculate input pixel radii inside the footprint and corresponding filter coefficient as a function of the radius. The shape of the footprint is determined as a trade-off between image quality and processing speed. In one implementation, profiles of smoothing and warping components are combined to produce sharper or detail enhanced output image. The method and system of the invention produce natural output image without jagging artifacts, while maintaining or enhancing the sharpness of the input image.

Abstract: Upon calculating a FEM model of a new model vehicle as a structure to be analyzed using that of an existing vehicle as a prototype structure, a computer sets a plurality of corresponding reference points on the outline of the new model vehicle and the FEM model of the existing vehicle, changes a mesh model included in the FEM model of the existing vehicle to the outer shape of the new model vehicle on the basis of that mesh model and the correspondence between these reference points, and merges additional information contained in the FEM model of the existing vehicle and its associated state with respect to the deformed mesh model, thus calculating the FEM model of the new model vehicle.

Abstract: In order to generate, on a display screen, a natural-looking deformed image obtained by intentionally distorting an original image, a buffer 21 comprises an original image storage section 210 which stores an original image, and a model storage section 211 which stores a 3-D model, comprising a plurality of polygons, and having a shape in which at least a portion of a plane is distorted in 3-D space. A drawing processor 10 comprises an image pasting section 100, which reads an original image from the original image storage section 210, reads a 3-D model from the model storage section 211, and pastes the above original image, as a texture, onto the above 3-D model, and a deformed image drawing section 101, which, by writing to a frame buffer 213, draws on a monitor 22 a deformed image, which is an image of the above 3-D model onto which an original image has been pasted, as seen from a prescribed camera viewpoint.