Abstract: A methodology is described to reduce the complexity of filters for face recognition by reducing the memory requirement to, for example, 2 bits/pixel in the frequency domain. Reduced-complexity correlations are achieved by having quantized MACE, UMACE, OTSDF, UOTSDF, MACH, and other filters, in conjunction with a quantized Fourier transform of the input image. This reduces complexity in comparison to the advanced correlation filters using full-phase correlation. However, the verification performance of the reduced complexity filters is comparable to that of full-complexity filters. A special case of using 4-phases to represent both the filter and training/test images in the Fourier domain leads to further reductions in the computational formulations. This also enables the storage and synthesis of filters in limited-memory and limited-computational power platforms such as PDAs, cell phones, etc.

Abstract: There is provided a method and apparatus for encoding and decoding motion vectors. Motion vectors are encoded through the steps of: (a) predicting motion vectors of a type identical to that of a present block and obtaining predictive motion vectors with respect to neighbor blocks having motion vectors of a type different from that of the present block among a plurality of neighbor blocks adjacent to the present block; (b) calculating a representative value of the motion vectors of the type identical to that of the present block from the motion vectors of the neighbor blocks and the predictive motion vectors; (c) calculating a difference value between the calculated representative value and the motion vector of the present block; and (d) encoding the calculated difference value. The motion vectors can be more efficiently encoded even when they refer to different reference pictures.

Abstract: Technology is provided for changing one or more image attributes pertaining to depth perception in a two-dimensional image to emphasize the perceived stereoscopy of the two-dimensional image and achieve a sensation upon viewing the two-dimensional image that is close to a sensation perceived from viewing a binocular stereoscopic image. Binocular stereoscopic image data including image data from two perspectives, for right vision and left vision, are input. A user selects the preferred one of the right vision image data and the left vision image data using an image selection unit, a planar image generating unit extracts the selected image data from the binocular stereoscopic image data, and an image output unit outputs the extracted planar image data.

Abstract: White balance normalization of a high dynamic range image is performed by identifying a first image adaptation point for a relatively lighter portion of the image and a second image adaptation point for a relatively darker portion of the image. A first white point adjustment for the lighter portion of the image is performed using the first image adaptation point and a second white point adjustment for the darker portion of the image is performed using the second image adaptation point. Thus, multiple illumination sources can be taken into account in rendering a high dynamic range image, providing a more visually appealing rendered image.

Abstract: A CPU executes a process for building an image, which is projected on three planes such as XY, YZ, and XZ planes mutually intersecting in three-dimensional space, of a three-dimensional image obtained by stacking in a direction of an optical axis a plurality of two-dimensional confocal images, which are obtained by changing the focal position of an objective lens against a sample in the direction of the optical axis of the objective lens. Then, a target region implemented by integrating pixels, whose points projected on the three planes are included in regions respectively specified for the three planes, among pixels configuring each of the two-dimensional confocal image.

Abstract: The invention is a method by which information and communication pertinent to an object is provided based on imagery of the object. A digital image of the object is captured and the object is recognized from a plurality of objects in a database. An information address corresponding to the object is then used to access information and initiate communication pertinent to the object.

Abstract: A method for processing a stereo image is provided which includes the steps of setting a specified area of a base window with reference to a point for obtaining a corresponding point in the base image; setting a reference window having the same size as that of the base window in the reference image; evaluating the difference between the base window and the reference window while scanning the reference window along an epipolar line; determining the position of the reference window having the minimum difference as a stereo corresponding point; measuring parallax from the difference between the position of the base window and the position of the reference window; calculating the reliability of the corresponding point (parallax) by first reliability based on the sharpness of the peak of the evaluation-value distribution of the difference of patterns between the base window and the reference window and second reliability based on the shape of the peaks; and outputting the value of the reliability of the parallax t

Abstract: A recording medium having recorded thereon information related to coded data of an image sequence; wherein the information related to coded data of an image sequence is a set of coded frame information of a plurality of frames of an image sequence; wherein the coded frame information includes: information related to a difference image between an image of a current frame and a prediction image of the current frame, the prediction image being synthesized by performing motion compensation, information related to motion vectors estimated in performing the motion compensation, and rounding method information specifying either a positive rounding method or a negative rounding method for interpolating intensity values of pixels in performing the motion compensation when the input image is coded as a P frame, wherein no rounding method information is included in the coded frame information when the input image is coded as a B frame.

Abstract: A system is provided for selecting a foreground region of an image, given a set of pixels defining the boundary of the foreground region of the image. The system includes a component to determine a foreground value (F) and opacity value (?) for each pixel on the set wherein ? is determined via a subpixel edge-offset to facilitate a separation the foreground region from background portions of the image. The foreground value (F) and opacity value (?) are then employed to smoothly mix the foreground region of the image with a subsequent image background region.

Abstract: A recording medium having recorded thereon information related to coded data of an image sequence; wherein the information related to coded data of an image sequence is a set of coded frame information of a plurality of frames of an image sequence; wherein the coded frame information includes: information related to a difference image between an image of a current frame and a prediction image of the current frame, the prediction image being synthesized by performing motion compensation, information related to motion vectors estimated in performing the motion compensation, and rounding method information specifying either a positive rounding method or a negative rounding method for interpolating intensity values of pixels in performing the motion compensation when the input image is coded as a P frame, wherein no rounding method information is included in the coded frame information when the input image is coded as an I frame.

Abstract: A projection set of geodesic lines which are parallel with each other on a curved surface of a paper face is extracted from an image in which a paper face has been imaged by an image-pickup device, using the paper face contents as a clue; and also a projection set of ruling lines which form a ruled surface corresponding to the curved surface of the paper face is extracted from the projection set of geodesic lines. Then, the curved surface of the paper face is estimated from the projection set of the geodesic lines and ruling lines, and distortion of the image is corrected based on this curved surface of the paper face. If this is done, correspondence with various types of diverse distortions becomes possible, and distortion correction can be performed even when only one part of the paper face appears in the image.

Abstract: Apparatus, systems and methods for providing a multi-feature, programmable tap filter architecture for image processing are disclosed. In one implementation, a system includes an image data source for providing image pixel data, an image filtering coefficient source for providing a plurality of image filtering coefficient sets, and image processing logic capable of at least filtering the image pixel data using one or more image filtering coefficient sets specified by one or more indicators. The processing logic being also capable of blending adjacent and/or non-adjacent tap filter outputs to generate blended tap filter outputs.

Abstract: An image display apparatus includes: a display displaying an image with a predetermined number of pixels; an image holding unit holding an original image composed of a number of pixels larger than a number of pixels that is displayable on the display; and an object judgment unit judging whether or not an object is included in the original image held in the image holding unit, and generating object information related to the object in a case where the object is included in the original image. The image display apparatus also includes a display image generation unit extracting at least a part of an object area from the original image based on the original image specified by the user as well as on the object information corresponding to the original image, and generating a display image composed of a number of pixels corresponding to the number of pixels that is displayable on the display.

Abstract: An image coder including: a memory to store a reference image which is a previously decoded image; a block matching section to estimate motion vectors between an input image to be coded and the reference image, to synthesize a prediction image of the input image using the motion vectors and the reference image, and to generate a difference image by calculating a difference between the input image and the prediction image; and a multiplexer to produce coded information of the input image including information related to the difference image and the motion vectors, wherein the prediction image is synthesized by calculating intensity values at points where no pixels actually exist in the reference image by interpolation, wherein the interpolation is done using a positive rounding method or a negative rounding method when the input image is coded as a P frame, wherein the coded information of the input image coded as P frames includes information specifying the rounding method used in the interpolation, and where

Abstract: Digital media and contextual data relating to the digital media are archived by a system for archiving family history. The system includes a storage medium, a network interface, and a control processor. The storage medium stores the digital media and contextual data. The network interface communicates with a network to send and receive digital media and contextual data. The control processor operates a relational database for organizing the contextual data by arranging the contextual data within contextual tables.

Abstract: A computerized method of video analysis including receiving image data for a plurality of video frames depicting a scene that includes at least one of a plurality of background features. Each video frame includes s a plurality of image regions and at least one video frame has an object within at least one of the image region. A plurality of background classifications is provided that correspond to one of the background features in the scene. At least one image region is assigned a background classification based at least in part on the location of the object relative to the image region.

Abstract: An interpolation method based on edge detection includes: generating a measurement value of an edge direction according to a first pixel set and a second pixel set, wherein the first pixel set comprises at least a first pixel, the second pixel set comprises at least a second pixel, the first pixel and the second pixel are on opposite sides of the target location and define the edge direction, and the measurement value represents a measure of variance between the first pixel set and the second pixel set; according to the above step, generating a plurality of measurement values corresponding to a plurality of edge directions respectively; identifying a minimum measurement value from the plurality of measurement values; and calculating a value of the target pixel according to pixels of the first and second pixel sets corresponding to the minimum measurement value.

Abstract: Processes and apparatus for personalizing video through partial image replacement are disclosed. Personalization may include partial or full replacement of the image of an actor, an object or both. Personalization may also include insertion or replacement of an object, and full or partial replacement of the background and/or sound track. A video preparation process may be used to create a library of personalization-ready videos.

Abstract: An image processing apparatus decomposes an image into frequency components of at least two frequency bands, and generates a basic conversion table used to change values of the frequency components. The image processing apparatus sets an expansion/contraction ratio of the basic conversion table on the basis of a pixel value range which is determined on the basis of the image. The basic conversion table is changed based on the set expansion/contraction ratio.

Abstract: An apparatus and methods for processing video data are described. The invention provides a representation of video data that can be used to assess agreement between the data and a fitting model for a particular parameterization of the data. This allows the comparison of different parameterization techniques and the selection of the optimum one for continued video processing of the particular data. The representation can be utilized in intermediate form as part of a larger process or as a feedback mechanism for processing video data. When utilized in its intermediate form, the invention can be used in processes for storage, enhancement, refinement, feature extraction, compression, coding, and transmission of video data. The invention serves to extract salient information in a robust and efficient manner while addressing the problems typically associated with video data sources.