Abstract: A computer readable medium storing thereon a program for encoding the conformation of a given curve is provided. The encoding program includes: a point selection module for selecting representative points on a given curve; an arrangement module for putting an elemental structure block which consists of a trunk and branches; a branch selection module for selecting a branch from each of the blocks arranged above; an adjustment module for adjusting spacial orientation of the elemental structure blocks arranged above, just after selection of the most appropriate branch of a block (current block) and before selection of the most appropriate branch of the block assigned to the next representative point (next block); and a code generator module for generating data which describe the conformation of the curve, using the code of the selected branches of the elemental structure blocks assigned to the representative points of the curve.

Abstract: An image processor obtains character images included in input image and the character codes for identifying the characters represented by the character images, classifies the character images included in the input image into a plurality of character image groups based on the obtained character codes, determines typical image patterns constituting the input image based on the character images classified in the character image groups, assigns indices for identifying the image patterns to the determined image patterns, and codes the occurrence position information of the character images included in the input image and the indices of the image patterns corresponding to the character images so as to be associated with each other.

Abstract: A method of navigation in three-dimensional, electronic image data sets is disclosed, whereby the image data sets contain three-dimensional image data subsets. The method includes optically representing at least one two-dimensional projection of an image data set that includes a two-dimensional subprojection of at least one image data subset, optically highlighting the at least one two-dimensional subprojection, receiving a user input directed to the selection of a certain subprojection, and optically representing, in accordance with said user input, at least one additional two-dimensional projection of the image data set that includes a two-dimensional projection of the selected image data subset. The method can be used for an image data set that is formed by fusion of at least two source image data sets. The source image data sets can especially comprise computer tomography and a positron-emission tomography image data set.

Abstract: Devices, systems and methods for determining capabilities of an on-line sensor are disclosed. The exemplary method may comprise the following acts. The method may generate an image of a sample texture with known characteristics. The method may transfer the image to an on-line sensor. The method may also analyze data generated by the on-line sensor to determine measured characteristics. The method may compare the measured characteristics to the known characteristics.

Abstract: A method of measurement of proximity of a second contour to a first contour, comprises for each point of the first contour, a step of association with a point of the second contour determined as the closest, and a step of pairing each point of the second contour with one or zero points of the first contour, by determining the point of the first contour which is closest from among the set of points of the first contour that are associated with said point of the second contour. A method of automatic identification of targets applies this proximity measurement process to determine the measure of proximity of a template contour, applied as second contour, to an image contour, applied as first contour.

Abstract: An image monitoring system uses wireless communications to transmit images for security monitoring. The system includes a central controller (105) and a plurality of digital still camera units (110) operatively connected to the central controller (105). At least one of the camera units (110) includes an image sensor (215), a motion detector (220) that causes the image sensor (215) to receive image data when motion is detected, a micro controller (205), and a first nonvolatile memory operatively connected to or included in the micro controller (205). The micro controller (205) determines whether received image data should be transmitted to the central controller (105), and the central controller (105) determines whether received image data should be transmitted to a monitoring station (115). The camera units (110) may further be used as standalone units as replacements for motion detectors in existing security systems.

Abstract: An album creating apparatus according to the present invention includes an object extracting section that extracts an object from a moving image, an object acceleration computing section that computes acceleration of the object extracted from the object extracting section to a background based on a change of position in a plurality of continuous moving-image constituting images, a timing specifying section that specifies a timing in which the acceleration computed from the object acceleration computing section is larger than a predetermined reference acceleration, and a representative image extracting section that extracts a moving-image constituting image included in a predetermined time range centered on the timing specified by the timing specifying section as a representative image.

Abstract: A computer model of a physical structure (or object) can be generated using context-based hypothesis testing. For a set of point data, a user selects a context specifying a geometric category corresponding to the structure shape. The user specifies at least one seed point from the set that lies on a surface of the structure of interest. Using the context and point data, the system loads points in a region near the seed point(s), and determines the dimensions and orientation of an initial surface component in the context that corresponds to those points. If the selected component is supported by the points, that component can be added to a computer model of the surface. The system can repeatedly find points near a possible extension of the surface model, using the context and current surface component(s) to generate hypotheses for extending the surface model to these points.

Abstract: Systems and methods for sketching reality are described. In one aspect, a set of vector primitives is identified from a 2-D sketch. In one implementation, the 2-D sketch is hand-drawn by a user. A 2.5D geometry model is automatically generated from the vector primitives. The 2.5D geometry model is automatically rendered and presented to a user. In one implementation, the user provides 2-D sketch-based user inputs to modify one or more of lighting position, lighting direction, lighting intensity, texture, color, and geometry of the presentation.

Abstract: An article confirmation method has reading irreproducible fine characteristics from a genuine article, reading irreproducible fine characteristics from an article to be confirmed, comparing the irreproducible fine characteristics between the genuine article and the article to be confirmed, and determining authenticity of the article to be confirmed based on a comparison result.

Abstract: An image processing apparatus for processing an image includes the following elements. A repeating-component extracting unit extracts repeating components, which are repeatedly appearing, similar components in the image, from the image. A repeating-component location adjusting unit adjusts the location of the repeating components by equally locating the repeating components extracted by the repeating-component extracting unit at regular intervals on a screen. An area interpolator interpolates a representative value of an image without the repeating components into some of the areas forming the image in which the location of the repeating components is not adjusted. A feature information generator generates feature information indicating the repeating components in the image interpolated by the areas interpolator and a feature of the location of the repeating components.

Abstract: A method for determining a translation of a three-dimensional pre-operative image data set to obtain a registration of the three-dimensional image data with a patient positioned in a projection imaging system. In one embodiment the user identifies an initial three-dimensional organ center from projections and extreme contour landmark points of the object on a set of projections. A set of contour points for the image object in each of a plurality of three-dimensional cross-section planes; is obtained and the points projecting nearest to the user-identified landmark points are selected. A three-dimensional grid having a predetermined number of intervals at a predetermined interval spacing centered at the user-identified organ center is defined. The three-dimensional image data contour points as centered onto each grid point are projected for evaluation and selection of the grid point leading to contour points projecting nearest to the user-identified landmark points.

Abstract: A method for inspecting component surfaces by a scanning test system, with the activation of the test system taking place such that, based on a known region of the component surface, an estimation of the component shape is performed, the estimation at the edge of the known region is drawn up at least for one part of the edge, this estimation is used for the calculation of the path for the scanning system, the inspection during scanning is implemented along this path and the deviation from the true component shape is measured so that the exact shape of the component is known along this path.

Abstract: To perform progressive mesh segmentation suitable of interactive applications a high speed with high precision. An image processing device 10 includes an image information input unit 1 for inputting three-dimensional image information to be processed in the format of an incidence graph, an incidence graph evaluation unit 2 for evaluating and sorting the edges of the input incidence graph, an image region mesh growing unit 3 for extracting pairs of image regions sandwiching edges in the sorted order and evaluating and performing mesh growing thereof based on a statistical processing algorithm, and a minute node processing unit 4 for processing minute regions remaining as a result of the image region mesh growing.

Abstract: A system and method for implicitly computing signed distance values in a graphics application. In one embodiment, rather than storing numerous distance values along a given raster scan line, only two values are stored for each interval defining the intersection of the raster scan line with the shape. These two values represent the interior of the object to be rendered along a given grid line. In another embodiment each grid line may be parameterized (e.g., from 0 to 1). Each intersection interval may then be represented by the parameter value at an entry point of the surface and an exit point of the surface, along the given grid line.

Abstract: A method, apparatus, system, and program for image processing are provided to perform operations of recognizing, reproducing, and enhancing an image, particularly one having character, symbol, or line-segment portions. An image obtainer obtains a multivalue image of color or grayscale. A brightness image generator generates a brightness image of the multivalue image, representing brightness values of respective pixels of the multivalue image. A topographic feature image generator generates a topographic feature image of the multivalue image, having a topographic feature corresponding to the brightness values. A topographic feature adder generates a binary image of the multivalue image, by using information contained in the topographic feature.

Abstract: A method for measurement of a cutting tool is provided. The method comprises positioning the cutting tool on a moveable stage, performing a first rotary scan of a first section of the cutting tool to generate a first scanning point cloud, segmenting the first scanning point cloud, performing a second rotary scan of the first section based on the segmentation of the first scanning point cloud, and extracting the parameters of the first section based on the second rotary scan of the first section. A system for extracting parameters of a cutting tool is also presented.

Abstract: A method and electronics circuit for processing very high resolution images or very high frame rate images in real time. Each pixel within a frame of pixels is compared to the neighboring pixels within the frame to determine if the pixel is part of a blob group. If the pixel is part of the blob group, the characteristics of the pixel are added to the statistics for the blob group. When a pixel overlaps two target blob groups, the two blob groups are combined to form one blob group. When the end of the frame is reached information about the blob groups in the frame is made available.

Abstract: With the present invention, data continuity is used at the time of converting an input image into high-quality image data with higher quality than the input image data, to obtain processing results which are more accurate and have higher precision. A class tap extracting unit (902) and prediction tap extracting unit (906) extract a class tap and prediction tap based on data continuity of multiple perimeter pixels corresponding to a pixel of interest in the input image, detected by a data continuity detecting unit (901).

Abstract: The size distributions corresponding to the three-dimensional (3D) shapes of particles are estimated from a 3D-to-2D projection matrix and a two-dimensional (2D) image of the particles that is obtained using TEM. Two different methods to generate a 3D-to-2D projection matrix are described. The first method determines the matrix coefficients assuming equal probability for all high-symmetry projections. The second method employs a large set of 3D-to-2D projection matrices with randomly generated coefficients satisfying the high-symmetry projection constraint. The second method is a general method to determine 3D-to-2D projection matrices based on the assumption that certain high-symmetry projections are present for the system under investigation.

Abstract: The invention relates to a finder pattern for detection and location of at least one target feature in a target object. The finder pattern includes at least two triads arranged in predetermined locations in the target object, wherein each triad includes a first blob, a second blob, and a third blob, wherein each blob has substantially the same area and is positioned in a predetermined location in the target object. The locations of the first and second blobs are substantially equidistant from the third blob, and the locations of the first, second, and third blobs are not collinear. The invention further relates to a method for detecting a finder pattern in a target object, and a computer readable medium having instructions stored therein for detecting a finder pattern in a target object, which, when executed by a processor of a computing device, cause the computing device to carry out the steps of the method.

Abstract: The present invention describes a process for enhancing optical recognition of text in scanned documents. Prior to performing optical recognition for identification of text in scanned documents, a preprocessing algorithm identifies locations of noncontiguity in character strokes. The gaps created by noncontiguous character strokes are selectively filled with non-white or black pixels for enhanced character recognition. The process may assess noncontiguity on a bit-by-bit basis or, to reduce the number of operations, on a byte-by-byte basis.

Abstract: A method detects roads in an aerial image of ground topology by determining low-level features, such as intensities and gradients, for each pixel in the aerial image, determining middle-level features, such as an orientation for each pixel from the low-level features, and determining high-level features from the middle-level features. Each high-level feature is assigned a probability, and the probabilities of the high-level features for each pixel are normalized and aggregated to a single probability that the pixel is associated with a road.

Abstract: A method for processing particle images are described that include: receiving image information obtained by capturing an image of a particle; determining the circumferential length and number of inflection points in the contour of a particle image based on the received image information; and calculating the degree of irregularity of the particle based on the determined circumferential length and number of inflection points.

Abstract: The present invention relates to a method for determining the orientation of text, so that the text can be correctly read. In one embodiment, the method analyzes the “open” portions of text characters to determine in which direction the open portions face. By determining the respective densities of characters opening in each direction (e.g., right or left), the method can establish in which direction the text as a whole is orientated. The present invention may be adapted for use in automated mail processing, to determine the orientation of checks in automated teller machine envelopes, or the orientation of scanned or copied documents, or documents sent via facsimile, or to determine the orientation of digital photographs that include text (e.g., road signs, business cards, driver's licenses, etc.), among other applications. A fast, substantially automatic determination of text orientation according to the present invention will reduce the labor expense and processing delay required for manual orientation.

Abstract: A system and method facilitating activity (e.g., dithering/half toning and/or noise) detection is provided. The invention includes an activity detection system having a connected component analyzer and an activity detector. The invention provides for the quantity of connected component(s) in and/or intersecting a region surrounding a pixel to be determined. The activity detector provides an activity map output based, at least in part, upon the quantity of connected component(s) in and/or intersecting the region. The invention further provides for an optional image processor. In one example, if the quantity exceeds a first threshold, dithering/half toning is detected and appropriate action can be taken. Additionally, if the quantity is less than a second threshold, noise is detected and appropriate action can be taken.

Abstract: A digital image interpolation method is disclosed which a projection point (x, y) of the original image corresponding to a pixel of the transformed image first is determined. According to neighboring pixels (m, n) of the projection point, Gauss weights Wi then are determined. Lastly, according to the Gauss weights Wi and the corresponding color value Vi of the neighboring pixels, a color value f (x, y) of the projection point is computed. Via an interpolation method using Gauss weight, the computation time is reduced while qualitatively improving the image processing.

Abstract: The present invention relates to a method for post-processing a 3D digital video signal, said digital video signal having a plurality of views with associated disparity maps. The invention is characterized in that said method comprises a first step of generating a projected disparity map from an original disparity map, and a second step of filling holes within said projected disparity map, the first step comprising the sub-step of removing isolated projected pixels on said projected disparity map by filtering them.

Abstract: By a method of detecting a branch point, the branch point in a random line pattern of neovascularization or the like is detected accurately and efficiently. After a binary image is obtained from an original image, noise filling is performed for removing a noise in a line element to provide a filled image. The filled image is thinned to provide in a thinned image including the line element having its width change to one pixel. Plural previously-registered branch patterns are collated with the thinned image, and consequently, the branch point at which the line element of the random line pattern branches off is detected.

Abstract: A process for detection of straight-line segments in a stream of digital data that are representative of an image (m, n) in which the contour points of said image each defined by the modulus and the orientation ? of their gradient in relation to a horizontal axis are identified. The stream of digital data is stored in the form of two successive lines, each of n points P(i, j), for each of the lines the n points of said line are extracted successively, and for each point Pc(i, j) extracted, the so-called current point, the three points having inferior coordinates Pa(i?1, j?1), Pb(i, j?1), Pd(i?1, j) directly neighboring said current point are extracted, successively the value of the orientation of the current point Pc is compared with that of the neighboring points Pa, Pb and Pd. The values of the orientations of the points Pb and Pd are compared, the result of a comparison is validated if the points are contour points and if the values of their orientation are close.

Abstract: An Euler number representation of a binary image is calculated. The binary image is considered as a series of partial images. The Euler number for each partial image is calculated using properties of runs of zeros and ones in the pixel matrix, and the results are combined together. The operations may be performed sequentially or in parallel. The calculations may be performed using discrete logic components for on-chip VLSI implementations.

Abstract: A method for determining a number of balls in a projection space comprises determining a projection of a portion of a ball grid array, determining at least one local maximum of the projection space for a given threshold, and determining at least a distance between adjacent maximum. The method further comprises determining an inter-peak histogram of the distances, determining an inter-ball distance for each pair of adjacent balls that has the maximum value of the inter-peak distance histogram corresponding to the pair of adjacent balls, and determining a position of a first ball and a position of a last ball. The method comprises verifying the position of the first ball and the position of the last ball based on a general inter-ball distance, and determining the number of balls.

Abstract: Method and system of detecting and analyzing the presence of a logo in one or more datastreams. In the method, at least one video datastream of an event is first received. Next, one or more regions of interest (ROIs) for the logo in one or more images comprising the at least one datastream are identified. The one or more ROIs are analyzed to detect if the logo is present in the ROI. If so, the detection of the presence of the logo is used in making either a broadcasting decision or an advertising decision.

Abstract: A method and a system for determining temperature and/or emissivity of an object by remote sensing are described. Based on the concept of temperature and emissivity determination, there are also developed a method and a system for the detection and recognition of an object that includes a plurality of sub-objects. The method for the detection and recognition of an object comprises acquiring, inter alia, electromagnetic radiation data of electromagnetic radiation emitted from a selected region in at least two spectral bands, recording and storing the required electromagnetic radiation data, deriving descriptive maps constituted by pixels of the selected region from the stored data and classifying the pixels of said descriptive maps of said selected region by pattern recognition processor means.

Abstract: Methods, apparatus and data structures for identifying, processing and interpreting bi-level connected component objects found within graphic images. The disclosure includes methods for generating lumped graph representations (4100) of the targeted objects (3000) and for using these to recognize the objects as known objects in a reference dictionary (10010). To implement this method, a bi-level connected component object (3000) is identified within an image (2010) and the object is represented as a plurality of pixel runs (3100-3430) of a given binary value. A lumped graph representation (4100) which captures characteristic topological features of the object is created based upon the connectivity data of the pixel runs in the object. This information is then used to recognize the object (3000) by comparing the lumped graph feature vectors with feature vectors of known objects stored in the dictionary (10010).

Abstract: A method, system and computer readable-storage medium for generating an identification code from a fingerprint image exhibiting a plurality of features. The method includes establishing a reference point from the plurality of features, generating at least one metric from the reference point and at least one of the plurality of features and forming the identification code from the at least one metric. Changes in the temperature and humidity of a finger when the image is taken at different times will result in minor variations of the measured features which, upon quantization, result a metric that is invariant from one fingerprint image to the next, for the same finger. This lowers the false rejection rate to an acceptable level. Meanwhile, the metric is sufficiently unique for a given set of features such that the probability of assigning the same metric to two different fingers is lowered to an acceptable level.

Abstract: A system and method for object inspection detects and reports object and/or object feature shapes from an acquired image of an inspected sample-object using both edge-based and grey level-based data. Such systems and methods are particularly useful for detecting objects and/or object features whose appearances are relatively unknown prior to inspection.

Abstract: Techniques for converting images defined by halftone bitmaps to continuous tone (CT) representations can better preserve geometric information from the original halftone bitmaps, enhancing the accuracy of CT proofs produced by lower resolution proofers such as inkjet and electrophotographic devices. The conversion techniques may involve the application of different conversion processes to text/linework and image regions of the bitmaps. For example, the conversion process for image regions may involve application of bandwidth limitation to remove halftone dot structures prior to downsampling. On the contrary, the conversion process for text/linework regions may exclude bandwidth limitation in order to preserve sharpness of text and linework.

Abstract: A method and apparatus for extracting three-dimensional data of an object using an electron microscope are provided.

Abstract: A process for detection of straight-line segments in a stream of digital data that are representative of an image (m, n) in which the contour points of said image each defined by the modulus and the orientation &thgr; of their gradient in relation to a horizontal axis are identified. The stream of digital data is stored in the form of two successive lines, each of n points P(i, j), for each of the lines the n points of said line are extracted successively, and for each point Pc(i, j) extracted, the so-called current point, the three points having inferior coordinates Pa(i−1, j−1), Pb(i, j−1), Pd(i−1, j) directly neighbouring said current point are extracted, successively the value of the orientation of the current point Pc is compared with that of the neighbouring points Pa, Pb and Pd. The values of the orientations of the points Pb and Pd are compared, the result of a comparison is validated if the points are contour points and if the values of their orientation are close.

Abstract: Stroke information from pen-down to pen-up being one unit is grouped automatically so that editing thereafter can be performed efficiently. Grouping of stroke information is determined in accordance with a predetermined rule of grouping each time stroke information is input or with timing indicated by a user. Strokes input within a predetermined time interval and stroke information input at a position within a predetermined distance interval are assumed to be the same group, and in the editing thereafter, a collective pointing and processing on a plurality of grouped strokes becomes possible.

Abstract: Method and system of detecting and analyzing the presence of a logo in one or more datastreams. In the method, at least one video datastream of an event is first received. Next, one or more regions of interest (ROIs) for the logo in one or more images comprising the at least one datastream are identified. The one or more ROIs are analyzed to detect if the logo is present in the ROI. If so, the detection of the presence of the logo is used in making either a broadcasting decision or an advertising decision.

Abstract: A computer method and system for converting a pixmap representing a drawing into a set of points or vectors representing the drawing. Closed loops of points or vectors are traced around boundaries between edge and non-edge pixels in the pixmap; each loop is identified as defining an outer perimeter or as defining a hole associated with some particular outer perimeter; and, for each outer perimeter, an ink art region is defined by an outer perimeter minus any areas defined by any associated holes. Color art vectorization may be created interior to ink art regions. Interior ink art regions may be formed at branches in the drawing. Boundaries may be smoothed and filtered. Drawings may be sized, scaled, or rotated. Vectorization may be extended to color and gray scale drawings.

Abstract: According to an example embodiment, the present invention is directed to pixel-data processing that includes scanning a first 2×2 line in each of a series of immediately adjacent pixel blocks, prior to scanning a second 2×2 line in each of the series of pixel blocks. Each scanned line is then processed for motion compensation in a manner that addresses challenges, including those discussed above, related to buffer size requirements, power consumption requirements and latency.

Abstract: By a method of detecting a branch point, the branch point in a random line pattern of neovascularization or the like is detected accurately and efficiently. After a binary image is obtained from an original image, noise filling is performed for removing a noise in a line element to provide a filled image. The filled image is thinned to provide in a thinned image including the line element having its width change to one pixel. Plural previously-registered branch patterns are collated with the thinned image, and consequently, the branch point at which the line element of the random line pattern branches off is detected.

Abstract: Method for acquiring a three-dimensional shape or image of a scene, wherein a predetermined pattern of lines is projected onto the scene and the shape is acquired on the basis of relative distances between the lines and/or intersections of the lines of the pattern.

Abstract: A method determines a compactness ratio for data sets by first measuring a combined compactness value for a union of the data sets, and second, by measuring an individual compactness value for each one of the data set. The combined compactness value is then divided by a sum of the individual compactness values to determine the compactness ration of the data sets.

Abstract: A method of estimating the dot frequency of an area of a band of an image. The band is divided into small areas, and within each area, each column is processed, pixel by pixel. If a pixel is encountered that is not of the same type as a neighbor, it is assigned a new identification. If a current pixel is the same as the one above or to the left, it is given the same identification. If the pixel is the same as the one above and to the left, the two identifications are merged. At the end of each column two numbers are calculated, one is the number of separate identifications there are in the column, the other is the number of identifications that are in use since the beginning of the entire image. For each area, the dot frequency is the number of separate identifications in the first column plus the number of identifications used in the image up to the last column minus the number of identifications in use at the end of the first column of the band.

Abstract: An adaptive multiscale method approximates shapes with continuous or uniformly and densely sampled contours, with the purpose of sparsely and nonuniformly discretizing the boundaries of shapes at any prescribed resolution, while at the same time retaining the salient shape features at that resolution. In another aspect, a fundamental geometric filtering scheme using the Constrained Delaunay Triangulation (CDT) of polygonized shapes creates an efficient parsing of shapes into components that have semantic significance dependent only on the shapes' structure and not on their representations per se. A shape skeletonization process generalizes to sparsely discretized shapes, with the additional benefit of prunability to filter out irrelevant and morphologically insignificant features.

Abstract: There is provided a contact failure inspection system and method for semiconductor devices and a method of manufacturing semiconductor devices. Using digitized values for electron signals detected using a scanning electron microscope, contacts can be inspected to identify failures such as non-open contact holes. The contact failure inspection is performed by comparing the electron signal value detected from a unit area including at least one contact hole with values representative of the electron signal corresponding to a normal contact.