Abstract: Presented herein is a unified decoder architecture. A system comprises a video decoder, instruction memory, and a host processor. The video decoder decodes the video data encoded with the particular standard. The instruction memory stores a first set of instructions and a second set of instructions. The first set of instructions are for decoding encoded video data according to a first encoding standard. The second set of instruction are for decoding encoded video data according to a second encoding standard. The host processor provides an indication to the video decoder indicating the particular encoding standard. The video decoder executes the first set of instructions if the indication indicates that the particular encoding standard is the first encoding standard and executes the second set of instructions if the indication indicates that the particular encoding standard is the second encoding standard.

Abstract: A method of processing an image includes selecting, for each of a plurality of picture element values in at least a portion of the image, one among a plurality of offset values. For each of the plurality of picture element values, an index value is obtained based on (A) the selected offset value and (B) a portion of the picture element value. For each of the plurality of picture element values, an entry is retrieved from a lookup table according to the corresponding index value.

Abstract: A method for classifying an input character, the method comprising the steps of, in a processing system, for a plurality of character models, decomposing the input character into one or more segments in accordance with a segmentation scheme associated with the character model, and evaluating the one or more segments against a segment model associated with the character model, by using fuzzy logic rules to produce a score indicative of the conformity with the segment model, the method further including selecting the character model that produced the highest score, and classifying the input character as a character associated with the character model that produced the highest score.

Abstract: A known face guided imaging method applied for an electronic imaging device uses the scale of a known face sensed in a previous frame to define a scale range of a searching window, which adds a scale constraint into the searching window so as to search a current frame horizontally and vertically in the searching window to perform a face searching loop for a face. The invention simply sends a corresponding image patch within the scale range to a face detector for the face detection, and the searching space is constrained in a small group of scale ranges without the need of detecting the whole image of various different scales within the scale range, and thus the invention effectively reduces the huge quantity of computing values required for the detection process and greatly enhances the speed and efficiency of the face detection.

Abstract: Under the present invention, an image is progressively blurred to yield a set of (progressive) scaling levels. Once blurred, the edges of the image are detected so that each image segment can be identified on each scaling level. Once the segments are identified, like segments (i.e., segments having a like edge/Gaussian operator) on successive scaling levels are linked to yield a lattice structure that represents the perceptual organization of the image.

Abstract: Systems and methods according to the present invention provide techniques to reliably detect edges, lines and quadrilaterals, especially those with low local contrast, in color images. Edges can be detected using a color gradient operator is based on color distance with a non-linear weight determined by the consistency of local gradient orientations, thereby significantly improving the signal/noise ratio. In detecting lines, a variant of the Gradient Weighted Hough Transform can be used employing both the edge strength and orientation. Multiple non-overlapping quadrilaterals can be detected using a process which includes quality metrics (for both individual quadrilaterals and for a set of non-overlapping quadrilaterals) and a graph-searching method.

Abstract: A process includes: generation of knowledge of the anatomical object to be separated from neighboring objects and identification of high level features (e.g., prior knowledge that includes: a mean shape template of the vertebra; and, high level features, e.g., readily identifiable boundary regions between the vertebrae neighboring objects, such as neighboring vertebra and rib structures); and the subsequent use of this prior knowledge to level set.

Abstract: A method for analyzing medical image includes obtaining a plurality of surface fronts on an object, such points being disposed in a three dimensional volume in the object; varying the volume of each one of the points such volumes combining into a common volume; and terminating the process when the common volume reaches boundaries of the object.

Abstract: Computed axial tomography images of different respiratory phases of lungs are obtained, where the intensity of the image measures lung density. One image is deformed to the coordinate space of the other image, and the differences between the intensity values of the other image as compared to the mapped image are evaluated as measures of ventilation.

Abstract: A surveillance system receives video data of a monitored scene and identifies flows of motion in the scene. Specifically, a video camera communicates with a video recognition system, which identifies a flow motion region of a monitored scene and determines characteristics of the identified flow motion region.

Abstract: An accelerometer captures multiple frames of image information and uses the image information to generate acceleration data related to an object. In particular, multiple image frames are used to determine relative movement between a target and an image collection system. The relative movement between the target and the image collection system is tracked over time to generate acceleration data related to the object.

Abstract: The invention provides for a technique of extracting information from signals by allowing a user to select a classifier and a figure of merit for quantifying classification quality; select a transform to generate features from input data; use a recursive process of functional dissipation to generate dissipative features from features that are generated according to the transform; search for one or more dissipative features that maximize the figure of merit on a training set; and classify a test set with the classifier by using one or more of the dissipative features. Functional dissipation uses the transforms recursively by generating random masking functions and extracting features with one or more generalized matching pursuit iterations. In each iteration, the recursive process may modify several features of the transformed signal with the largest absolute values according to a specific masking function.

Abstract: A method for using computer-aided diagnosis (CAD) for digital tomosynthesis mammograms (DTM) including retrieving a DTM image file having a plurality of DTM image slices; applying a three-dimensional gradient field analysis to the DTM image file to detect lesion candidates; identifying a volume of interest and locating its center at a location of high gradient convergence; segmenting the volume of interest by a three dimensional region growing method; extracting one or more three dimensional object characteristics from the object corresponding to the volume of interest, the three dimensional object characteristics being one of a morphological feature, a gray level feature, or a texture feature; and invoking a classifier to determine if the object corresponding to the volume of interest is a breast cancer lesion or normal breast tissue.

Abstract: The present invention provides a method for presenting at least one medical imaging study in a Picture Archiving and Communication System (“PACS”). The method includes selecting at least one comparison imaging study from a plurality of historical imaging studies by comparing at least one image data attribute associated with a current imaging study with at least one image data attribute associated with each of the plurality of historical studies. The relevant historical studies are automatically selected as comparison imaging studies.

Abstract: A method and apparatus for producing data for making dental prostheses, wherein the data can be produced on the basis of a model (2) which comprises individual segments (3a, 3b, 3c, . . . ), such as representing a tooth, a preparation, a gingival area, a tooth gap or a small group of teeth, from different directions in space, and a storing device for storing the shape data obtained thereby, and—second shape data (12) of only the one segment (3a, 3b, 3c, . . . ), only part of the segment (3a, 3b, 3c, . . . ) being scanned, and the segment (3a, 3b, 3c, . . . ) being arranged in a fixed orientation relative to a reference, and b) a comparing device for comparing the first and second shape data (1, 12) to determine the orientation of the first shape data (1) relative to the reference.

Abstract: A method of dental microscopic procedure, using a digital surgical scope, includes steps for selecting a function of the digital surgical scope to perform, obtaining the corresponding images from the image data taking device or the image data processing/storing device, processing the images by the image data processing/storing device, and displaying the images on the displays. The dental surgical procedure is done by seeing the images displayed on the screen. The digital surgical scope includes a microscope lens assembly for magnifying an optical image of an object and an in-line illumination device for illuminating the object along the same optical axis and from the same direction of the microscope lens assembly. The image data processing/storing device is for manipulating the image taken by the microscope lens assembly and the image data taking device.

Abstract: A mole analysis program generates a digital signature for a first mole, based on a digital image of first, second, and third moles. The program may then determine whether the first mole matches a previously imaged mole, based on the digital signature for the first mole and baseline data with baseline signatures for previously imaged moles. In response to determining that the first mole matches a previously imaged mole, the program may automatically determine whether the first mole has changed. In various embodiments, the digital signature may include angle entries for the digital signature and/or distance entries for the first signature. An angle entry may represent an angle between two lines to connect the first mole with the second mole and the third mole. A distance entry may correspond to the distance between the first mole and the second mole. Other embodiments are described and claimed.

Abstract: The present invention relates to a method and an apparatus for processing images of irregularly shaped objects, such as biological specimens, in particular of human or animal origin, or images thereof. The metric quantification of a biological body part or tissue or of an abnormal material spot or aggregate contained therein is also performed by means of the invention method. In particular, the present invention relates to a method for processing images of irregularly shaped objects, comprising a stage of acquisition of a digital image of said object, a stage of image elaboration (IMAEL) for quantifying said digital image to 1 bit and a stage of metrical processing of said 1-bit quantized image, wherein said stage of metrical processing comprises: —) a stage of object's metrical quantification (QUANT) for determining Euclidean perimeter P and/or area A of said object; —) a stage of dimensional calculation (DIM-CLC) for calculating a fractal-corrected perimeter Pf and/or area Af of said object.

Abstract: A method of detecting irregularities in a digitized image includes selecting a volume of interest in an image, growing a surface from a point in said volume of interest, determining the local gradient of each point on said surface, and applying a local filter to said gradient, determining a histogram of filtered gradients, and detecting an irregularity by selecting those points corresponding to gradient histogram values above a threshold value.

Abstract: Provided are an information processing apparatus, method, program and storage medium whereby prescribed additional information such as a digital watermark can be embedded directly in encoded data, and later extracted, without decoding data that has been compressed and encoded by the JPEG scheme, etc. First, encoded data, which is information that has been encoded, is input from an encoded data input unit (101). An embed coefficient is selected in an embed coefficient selector (102) block by prescribed block, and a code transformation unit (103) replaces the encoded data by different encoded data, which corresponds to the input encoded data, input using a transformation table (104), whereby a digital watermark is embedded.