Abstract: A system is disclosed for changing a coverage angle of sound produced from a loudspeaker system. The loudspeaker system includes an enclosure that projects sound at a predetermined angle. A sound integrator includes an inner surface positioned adjacent to a mid-range frequency sound source. An outer surface of the sound integrator includes a planar and a curved surface. The surfaces control the angle which sound radiates from the loudspeaker.

Abstract: A portable auxiliary speaker for a playpen or a crib comprising a housing incorporating a loudspeaker, the housing being adapted to receive at least a portion of a framework of a crib or a playpen to mount the housing to the crib or the playpen, wherein the housing includes an input adapted to be operatively coupled to at least one of a radio, a CD player, an MP3 player, a cassette player, a computer, and a DVD player.

Abstract: Digital data is rapidly embedded in color/grayscale digital data by switching between a set of multi-level screens or quantizers. Each screen can be tuned to maximize the quality of the digital data product on the intended display medium, so that the quality of the displayed product does not suffer. The data embedding method/algorithm of the invention generally involves generating a set of multi-level screens, each of which is generated by selecting a set of colors that comprise the colors that can be output by that multi-level screen; screening the input digital medium with the generated multi-level screens using a dither matrix and a set of level matrices; and selecting, for each of select number of pixel locations in the input digital medium, one of the level matrices, based on a message symbol to be embedded at that pixel location, to create an output.

Abstract: A method and system is disclosed for printing an authenticatable image having an embedded image into a receiver having a discernible physical characteristic, such that the printed image can be used to authenticate the receiver which includes scanning the receiver to produce information related to the discernible physical characteristic of the receiver, and providing a carrier which includes information related to the scanned receiver discernible physical characteristic. The method also includes combining the carrier with an input image to form the authenticatable image having the embedded image, and printing the authenticatable image having the embedded image onto the receiver.

Abstract: Provided is a method and apparatus for determining whether an input mage is a film image. The method includes (a) receiving a predetermined number of similarity values of two adjacent fields of the same kind from an image having interlaced fields, (b) classifying the received similarity values into a first group and a second group, (c) converting the similarity values classified in the first group and the second group into values different from each other, and (d) determining whether the image is a film image according to a period of the converted values. Since input similarity values are classified using a grouping, a film image can be detected without setting a threshold value.

Abstract: A landmark used to effectively determine the location of an autonomous vehicle, and a self-localization apparatus and method using the landmark are provided. In the self-localization method, first, first and second outer line information and shape information are extracted from a landmark image received from a camera. Next, a projective invariant is calculated from the shape information and stored in a hash table. Thereafter, the calculated projective invariant is compared with reference projective invariants for a plurality of landmarks stored in a predetermined data storage area in the form of a hash table, thereby determining which landmark corresponds to the landmark image. Then, information on the distance and orientation of the determined landmark with respect to the autonomous vehicle is analyzed in response to the first and second outer line information.

Abstract: To authenticate images taken by image capturing elements (3) of offending vehicles, for example, when exceeding the authorized speed, provided elements are provided for allowing informative data on the offence to be supplied, such as the speed of the vehicle, the date, the time and the place of the offence and various processing methods are provided which enable, during exploitation of the images, detection of whether or not manipulations have been carried out on the images.

Abstract: The present invention provides for making a comparison between a first video frame and a second video frame to determine the extent of a fear reaction in a test animal. Frame comparison logic is configured to quantify any change of a value associated with at least one pixel between the first video frame and the second video frame. A centroid calculator is configured to determine the position of a centroid of a video frame. Brainwaves of a test animal are also simultaneously measured and recorded. A processor correlates, as a matter of time, the recorded brainwaves with the change of status of the pixilated image information as a function of time.

Abstract: The present invention is a velocity detection system and method. In accordance with an embodiment of the invention, a series of still images of moving automobiles are taken at known intervals. An Image processor algorithm is used to determine local features of the moving automobile and in conjunction with known optical formulas, the velocity of the moving object can be determined. Once the velocity is determined, all of the moving automobiles are highlighted with their calculated velocity on a liquid crystal display screen. Images may be exported into flash memory for future reference.

Abstract: An authentication utility may be provided to entities, such as businesses, organizations or even individuals, that require the identification, verification and control of the identity of another entity, for example, an individual, such as a consumer, employee, etc. The authentication utility may also determine and provide the financial and non-financial characteristics of an individual. Before entering into a relationship or transaction, an entity could verify the other party's identity with the authentication utility.

Abstract: To determine the presence or absence of an aperture mask in a funduscopic image output by a fundus camera, and to combine the funduscopic image with an aperture mask image formed in an aperture mask-forming section so as to correspond to a determination result. When an aperture mask determination section 34 determines the absence of the aperture mask image in the funduscopic image and the necessity of the addition, the aperture mask-forming section 35 forms a necessary mask, and an aperture mask combine section 36 combines the funduscopic image with the aperture mask image.

Abstract: A portable data carrier comprises a communication means and a memory with a biometric template which is intended to be compared with a biometric sample for identity check. The biometric template is divided into a private part which is adapted to be exclusively used in the portable data carrier and a public part which is adapted to be transferred, with the aid of the communication means, to an external processing unit and be used therein. Moreover, a processing unit for use in biometric identity check is described, comprising a processor and a communication means. The communication means is adapted to receive a biometric sample and a public part of a biometric template, the processor is adapted to compare the received public part of the template with the biometric sample, and the communication means is further adapted to transfer, when a comparison criterion has been satisfied, at least part of the biometric sample to the portable data carrier for further comparison on the data carrier.

Abstract: Minutiae based fingerprint transactions are validated and authenticated over wireless based communications systems, such as over a Bluetooth wireless based communication system. Minutiae points are unique identification points on a fingerprint where a ridge in the fingerprint joins another ridge or a ridge ends. The combination of any three minutiae points forms a triangle, and the method/algorithm of the present invention uses triangles of minutiae points because triangles are proportional regardless of possible differences in scale of two fingerprints being compared. A first method/algorithm uses a minutiae exchange where triplets of minutiae points are exchanged and form triangles for comparison between an original template of minutiae points and a stored template of minutiae points. A second method/algorithm exchanges three linear equations for three pairs of minutiae points that form triangles for comparison between an original template and a stored template.

Abstract: A plurality of images of portions of a fingerprint surface is generated by measuring structural features the portions of the surface with a sensor array as the surface is moved relative to the array. A two-dimensional image of the fingerprint surface is constructed from a portion of the plurality of images. In one embodiment, a varying voltage is applied to a finger positioned over an exciting electrode and a capacitive sensor array, and the capacitance or impedance through the finger is measured between the electrode and the array to detect variations in capacitance or impedance caused by variations in the structural features of the fingerprint surface.

Abstract: A method and a system for extracting a minutia mapping from a digital image, including dividing the image into regions; defining an orientation of each region based on the general direction of grooves in this region; and for each region: unidirectionally filtering the image portion along a direction perpendicular to the orientation of the region; locating the enters of gravity of the grooves based on the intensity of the filtering results, chaining up the barycenters along the general direction of the region grooves, and interpreting the results of the chaining to determine the presence of minutiae of end type or of branch type.

Abstract: A streaked pattern image analyzing apparatus for use in an analysis of a fingerprint and the like for aiding in the identification as to whether or not an applied first streaked pattern image matches a second streaked pattern image. The apparatus comprises an image distortion modification unit for modifying data on one of the first streaked pattern image and the second streaked pattern image such that a point on a first streaked pattern image which resides on a skeleton thinned from a streak of the streaked pattern image and having a corresponding point on the second streaked pattern image is brought closer to a point on a skeleton of the second streaked pattern image corresponding to the point, and an image display unit for displaying the streaked pattern image modified by the image distortion modifying unit and the other streaked pattern image.

Abstract: In a telemanipulation system for manipulating objects located in a workspace at a remote worksite by an operator from an operator's station, such as in a remote surgical system, the remote worksite having a manipulator with an end effector for manipulating an object at the workspace, such as a body cavity, a controller including a hand control at the control operator's station for remote control of the manipulator, an image capture device, such as a camera, and image output device for reproducing a viewable real-time image, the improvement wherein a position sensor associated with the image capture device senses position relative to the end effector and a processor transforms the viewable real-time image into a perspective image with correlated manipulation of the end effector by the hand controller such that the operator can manipulate the end effector and the manipulator as if viewing the workspace in true presence.

Abstract: One embodiment discloses a computerized method of facilitating cardiac intervention, comprising inputting patient data, creating a computerized interactive model of a heart based on the patient data, wherein the model comprises features, simulating at least one proposed cardiac intervention treatment by adding or deleting features to the model, and determining the effects of the proposed cardiac simulation upon the entire model. Simulations may be repeated to allow the user to determine an optimal cardiac intervention. Additionally, a template may be created from the model to use as a guide during the cardiac intervention.

Abstract: Systems and methods are provided for automatic 3D segmentation of abnormal anatomical structures such as colonic polyps, aneurisms or lung nodules, etc., in 3D medical imaging applications. For example, systems and methods for 3D lesion segmentation implement a centroid-based coordinate transformation (e.g., spherical transformation, ellipsoidal transformation, etc.) to transform a 3D surface of the lesion from an original volume space into, e.g., a spherical or ellipsoidal coordinate space, followed by interpolation of the transformed lesion surface to enable accurate determination of a boundary between a lesion and surrounding normal structures.

Abstract: The method and system for exploiting information from multiple images in a mammographic computer-aided detection application is disclosed. A pair of images is obtained by a CAD system. The images are processed to produce a set of regions of interest (ROIs) to be associated with each image. A ROI is selected from the first image of the pair. This ROI is identified and matched to a ROI in the second image. The single image feature values are obtained by the two ROIs of the image pair. Transforming the image feature value to an integer value produces a pair of integers for each image feature value. The pair of integers defines the element of the pre-determined co-occurrence matrix. An element of a predetermined co-occurrence matrix is selected to provide evidence value for the ROI of the first image.

Abstract: In one exemplary embodiment of the present invention, a method of detecting a desired object at a candidate pixel from an image is provided. The method includes the steps of (a) selecting a representative point in the desired object; (b) determining first representative cross-sections of the desired object by passing first lower dimension planes through the representative point; (c) passing at least one second lower dimension plane through the candidate pixel; (d) using region segmentation to separate the candidate pixel containing second regions from the rest of the pixels in each of the at least one second lower dimension plane; (e) matching at least one of the second regions with at least one of the first cross-sections; (f) determining a match value based on the result of step (e); and (g) using the match value to determine if the desired object is detected at the candidate pixel.

Abstract: A system for obtaining a resultant image and a method to utilize the same are provided. In particular, first and second images of a subject or a portion of the subject are obtained. The first image includes a first portion of the subject and a second portion of the subject, and each of the first image and the second image are different types of images. A first probability that the first portion has a contrast which is greater than a predetermined contrast and a second probability that the second portion has a contrast which is greater than the predetermined contrast then is determined using the second image. For example, the second probability is greater than the first probability. Moreover, the first and second portions of the first image are reconstructed to generate the resultant image. Specifically, the first portion is reconstructed based on the first probability and the second portion is reconstructed based on the second probability.

Abstract: Techniques, hardware, and software are provided for quantification of extensional features of structures of an imaged subject from image data representing a two-dimensional or three-dimensional image. In one embodiment, stenosis in a blood vessel may be quantified from volumetric image data of the blood vessel. A profile from a selected family of profiles is fit to selected image data. An estimate of cross sectional area of the blood vessel is generated based on the fit profile. Area values may be generated along a longitudinal axis of the vessel, and a one-dimensional profile fit to the generated area values. An objective quantification of stenosis in the vessel may be obtained from the area profile. In some cases, volumetric image data representing the imaged structure may be reformatted to facilitate the quantification, when the structural feature varies along a curvilinear axis. A mask is generated for the structural feature to be quantified based on the volumetric image data.

Abstract: An measurement processing apparatus for efficiently measuring geometric data of an image is provided. A reference-image outputting means forms a reference-image based on an image that has been previously measured as well as a setting order data which indicates a suggestion as to the order in which the measuring points should be set and which shows the same setting order in which the measuring points were set for a previously performed measurement of a past-measurement image, and outputs the reference-image and the setting order data to an image display means. While consulting the reference-image and the setting order data displayed on the image display means, an operator can set, by use of a measuring point setting means, the measuring points at the correct positions and in the correct order in the subject image displayed on a display screen, and the geometrical data can be measured automatically and efficiently.

Abstract: A defect inspection apparatus for inspecting an object to be inspected for a defect by processing an image taken from the object, includes: neural networks provided respectively for individual defect types to be classified; a learning unit which makes the neural networks learn based on the corresponding defect types to be classified; and a defect detection unit which classifies and detects defect types using the neural networks that have learned.

Abstract: A stereo disparity between a reference image and a search image for a reference pixel in the reference image is determined by (a) calculating a similarity measure between a reference window including a set of pixels centering on the reference pixel and each of a group of search windows in the search image which is of a same shape with the reference window and displaced from the reference window within a predetermined search range, wherein a matching pixel count, which is the number of pixels in the reference window which are similar in intensity to corresponding pixels in a search window, is used as the similarity measure between the reference window and the search window; and (b) determining a displacement between the reference window and a search window which yields a largest similarity measure as the stereo disparity for the reference pixel.

Abstract: A system and method for efficiently performing a depth map recovery procedure includes an imaging device that is implemented in a single-lens stereo-shutter configuration for simultaneously capturing overlaid images corresponding to a photographic target. A depth map generator is configured to analyze the overlaid images to determine disparity values corresponding to separation distances between matching points in the overlaid images. The depth map generator then utilizes the disparity values to calculate depth values that correspond to locations in the photographic target. The depth map generator may then utilize the foregoing depth values for creating a depth map corresponding to the photographic target.

Abstract: Systems and methods of detecting and correcting redeye in an image are described. In one aspect, pixels of the input image are segmented based on projections of color values of the pixels onto two-dimensional thresholding planes. Candidate redeye pixel areas are identified in the input image based on the segmented pixels of the input image.

Abstract: A system and method for automatically altering an image having pixels is disclosed. An image is segmented into regions and various features of the regions are extracted and used to calculate a confidence factor, or belief value, that a particular region is a main subject of the image. The belief values are assembled into a belief map that is used to define how pixel values are to be altered. Various color and appearance values of the pixel are altered in a predetermined way to emphasize the main subject of the image. The emphasis is applied in a binary fashion or as in a gradient of values. Either the main subject can be emphasized, or the secondary or background subjects can be de-emphasized. The system can be implement on a variety of computer systems.

Abstract: Computer based method and apparatus for evaluating a graphic image file for the presence of objectionable visual content. The graphic image file comprises a number of pixels each having spectral components defined in accordance with a color model (such as RGB). Relative weighting of the spectral components of each pixel is performed to classify each pixel as either not representing human skin or as possibly representing human skin. For those sets of adjacent pixels that possibly represent human skin, a brightness test is performed to determine whether the set of pixels represents a curved surface. A statistical analysis evaluates the run length of each such set of pixels. Display of the graphic image file is allowed or disallowed based on the results of the foregoing analyses. Web pages available from the World Wide Web are further screened for objectionable terms in the associated URLs and text.

Abstract: An image processing method comprises forming a histogram of an entire image, determining a ratio between a reference luminance value and a reference threshold value at a maximum frequency, dividing the image into local areas, forming a histogram of each local area, determining a luminance value at a maximum frequency, multiplying this luminance value by the ratio between the reference luminance value and the reference threshold value to obtain a threshold value of the local area, and performing binarization for the local area using the threshold value. Therefore, it is possible to determine an appropriate threshold value in each local area of a multiple gray-level image, and obtain, using this threshold value, a binarized image which enables accurate separation of an object from a background.

Abstract: A method and apparatus for identifying and reproducing a background of a pixelmap. The method includes dividing the pixelmap into a grid of tiles, determining for each tile a background component and building a representation of a background in the pixelmap using the determined background component for each tile.

Abstract: A method for computerized processing of paper forms includes receiving an electronic image of a paper form containing text information from a client having a telephone. The text information is extracted from the form using an optical character recognition (OCR) process. A field of the extracted text information that is suspected of containing an error is identified, and a first text message is automatically communicated to the telephone asking the client to verify the identified field. A second text message is received in response to the first text message, and the text information in the field is validated or corrected according to the response.

Abstract: An encoder and an encoding method capable of improving the transfer efficiency in an encoding process is provided. The encoder determines the number of removed bit planes in order that the quantity of generated codes per frame is kept constant when performing the encoding process. A predetermined number of bit planes corresponding to those parts of information that seem relatively small to users are removed. Accordingly, the encoder can prevent variation of processing time in a stage before the encoder performs an encoding process.

Abstract: A moving picture coding apparatus includes a prediction coder generating signals to be entropy coded. Each of the signals is generated based on a different prediction mode in the prediction coder. The apparatus also includes a code amount measurer, a mode controller, and an entropy coder. The code amount measurer measures amounts of code of the signals to be entropy coded when the signals each are coded by a first entropy coding method. The mode controller selects one of the prediction modes based on a comparison of the amounts of code. The entropy coder codes the signal generated based on the selected prediction mode by a second entropy coding method having efficiency higher than that of the first entropy coding method.

Abstract: Even in the case of coding the input image by dividing into tiles, a fine image quality adjustment is possible based on the characteristic of each tile. The input image signal is transformed to the coded data through the tile dividing unit 102, the wavelet transforming unit 103, and the entropy coding unit 106, and is stored in the code memory 107. In parallel to this processing, the distortion calculating unit 108 calculates the distortion in each coding pass of each code block, and stores it in the distortion memory 109. On the other hand, the complex tile deciding unit 111 decides whether a particular tile is the complex tile or not. The tile classifying memory 112 stores the decision output. A distortion data outputted from the distortion memory 109 is outputted to the multiplier 110, the multiplier 110 multiplies the distortion data by the weight coefficient selected by the weight coefficient selecting unit 113.

Abstract: A wavelet transform is conducted on an original image (OI). At the moment when the first layer image (WI1) is generated, its LL sub-band component is recorded as an intermediate image (II) in an intermediate image memory (28). The wavelet transform is further conducted and then the third layer image (WI3) is obtained. Thereinafter, the image is processed in a quantizer and so forth and finally a coded image in JPEG 2000 is generated. On the other hand, if an image of a relatively small size is required, the intermediate image II recorded in the intermediate image memory 28 is used as a new original image (40) and coded, instead of the original image (OI).

Abstract: Method and apparatus for encoding image data is described. In an example, a memory stores bit-planes associated with the image data. Each of the bit-planes is partitioned into data units. A bit modeler communicates with the memory and produces modeled data in response to each of the data units for each of the bit-planes. An arithmetic coder communicates with the bit modeler and produces a coded data in response to each of the modeled data produced by the bit-modeler. In another example, the bit-modeler processes at least two of the bit-planes in parallel.

Abstract: An image compressing apparatus divides an image into plural tiles, decomposes each tile into plural sub band by frequency conversion, and conducts bit plane encoding of each sub band for each encoding unit, wherein the image compressing apparatus includes a code discarding unit selectively discarding a code obtained by the bit plane encoding for each encoding unit, and wherein the code discarding unit includes a discard amount setting unit that makes generally even the amount of code discarding in the encoding units that are in mutually adjacent relationship across a tile boundary.

Abstract: A method for encoding, transmitting, and receiving signals utilizes adaptive wavelet packet trees. A transmitter accepts a binary data stream assumed to be random. At the transmitter the data is parsed from a serial bit stream into several parallel streams. Within each of the parallel bit streams symbols are formed from the bits. Signals are created from each symbol by up-sampling. These signals modulate low-pass and high-pass filters that are derived from a wavelet packet transform (the wavelet and scaling functions, or, equivalently the low-pass and high-pass analysis filters). The filters are paired—one high-pass with one low-pass. The steps recited above are recursively repeated log2 N times for a signal of length N. The resulting signal is transmitted to the receiver. At the receiver, the steps recited above are reversed at the receiver to recover symbols, with the up-sampled signal down-sampled to remove inserted zeroes.

Abstract: It is an object to provide a method of coding the position information of a digital map in a small data volume by utilizing a compressing and coding technique. In a coding method of coding data indicative of a shape vector on a digital map, an arithmetic processing is carried out over position information about a node string and a shape which indicate the shape vector to be represented by data having a statistical deviation, and the data having the statistical deviation are coded to reduce a data volume. It is possible to considerably decrease a transmission data volume in the case in which the vector shape of the digital map is to be transferred.

Abstract: In an image encoding apparatus, pattern image cut-out means cuts out partial regions of an image of image data and generates pattern images. At the same time, the pattern image cut-out means outputs position information that is representative of positions on the image data, from which the pattern images are cut out. Rearrangement means receives the generated pattern images, rearranges the pattern images, and outputs the rearranged pattern images. Dictionary generating means generates list information in which the rearranged pattern images are put together in the form of, e.g. a list. Pattern image synthesis means generates a single image (“pattern image synthesis image”) in which the pattern images are combined in order. Encoded data generating means generates and outputs final encoded data, on the basis of the generated pattern image synthesis image and the generated pattern image position information.

Abstract: An image-data compressing apparatus includes: a start-focus-point setting unit that sets a start-focus point; a draw-point presence/absence setting unit that sets a draw-point presence/absence information bit; a draw-start-point information setting unit that sets a draw-start point information bit; a draw-point-number information setting unit that sets a draw-point number information bit; and a start-focus point/draw-point presence/absence setting unit that sets a draw-point presence/absence information bit, wherein, the respective units repeats the process thereof for a plurality of rows corresponding to the dot columns in the binary image data, to thereby obtain a compressed data of the binary image data from a bit string of the bits set by the respective units.

Abstract: In processing a digital image to provide a desired grain appearance, a noise table is formed that represents noise magnitude vs. intensity of the image. A plurality of potential image processing paths are provided. Each path has one or more image transforms. The noise table is modified according to the image transforms in the respective image processing paths to provide a plurality of output noise tables. Noise metrics are generated from each of the output noise tables. The noise metrics each represent the appearance of the image processed by the respective image processing path. An input is then accepted designating one of the paths. The image is processed according to the designated image processing path to provide an output image having desired noise.

Abstract: Motion picture scenes to be colorized are broken into separate elements, backgrounds/sets or motion/onscreen-action. Background and motion elements are combined separately into single frame representations of multiple frames which becomes a visual reference database that includes data for all frame offsets used later for the computer controlled application of masks within a sequence of frames. Each pixel address within the database corresponds to a mask/lookup table address within the digital frame and X, Y, Z location of subsequent frames. Masks are applied to subsequent frames of motion objects based on various differentiating image processing methods, including automated mask fitting of all masks or single masks in an entire frame, bezier and polygon tracing of selected regions with edge detected shaping and operator directed detection of subsequent regions. The gray scale actively determines the mask and corresponding color lookup that is applied in a keying fashion within regions of interest.

Abstract: A method for processing an image to increase sharpness of the image without changing hue characteristics. The method includes performing a transformation process to transform an original image signal into CIE XYZ colorimetric channels, forming a luminance channel Y, applying a filter on the luminance channel Y to obtain a processed luminance channel Y?, computing processed colorimetric channels X? and Z? based on the processed luminance channel Y?, and performing an inverse transformation process to transform the processed colorimetric channels X?Y?Z? into a processed image signal.

Abstract: An image recognition process applied to a photograph is preceded by a pre-processing step which identifies parts of the image which are in focus. The recognition process is then limited to those parts. The pre-processing typically operates by creating a measure of high spatial frequency activity and applying a threshold to them.

Abstract: A method and system for detecting slant edge areas in an image comprising a plurality of pixels, and for preventing zigzagged slant edge artifacts in an image detail enhancement process. Image pixels that belong to a slant image edge are detected and gain suppression factors are determined for the detected pixels. The image is detail enhanced while selectively reducing enhancement of the detected image pixels relative to enhancement of other image pixels based on the gain suppression factors.

Abstract: An economical method of detecting and suppressing ringing artifacts during digital image resizing is presented. The economical method substitutes costly division calculations with cost effective comparator operations. The method also includes improved image sharpening when up-sampling an image.

Abstract: A method for extracting a subset of data from an ordered set of bi-dimensional matrices (data arrays) such as a sequence of pictures or a multi-dimensional matrix, for instance, is implemented by dedicated hardware that may be used each time it is necessary to extract a subset of data from a data array. For each matrix of data, the method calculates very quickly row and column indices of border data of the portion to be extracted, which are obtained by arithmetical operations among row and column indices of vertices of a closed area of interest. The method is implemented in a device for selectively transferring a data stream sampled at a certain bit-rate to a microprocessor unit or to a memory receiving the data stream at a different rate.