Abstract: An electromagnetic transducer such as an audio loudspeaker, whose diaphragm assembly and motor both have a highly elongated shape in which the long dimension is at least 3× greater than the short dimension. The diaphragm may be obround, and the motor's magnetic air gap may comprise a pair of elongated, parallel, linear gaps. A novel “boxcar” device is used to hold the bobbin and voice coil in an obround shape, maintaining the parallel, linear shape of their elongated sides. The lower suspension may be disposed only at the ends of the motor, enabling the narrowest possible configuration.

Abstract: A digital watermark embedding apparatus of the present invention includes: a block dividing unit for dividing an input image into plural pixel blocks; a digital watermark information spreading unit for obtaining an embedding series having a length corresponding to a number of divided pixel blocks; a block-by-block embedding unit for selecting at least a frequency from predetermined plural frequencies according to a term value of the embedding series corresponding to a position of a pixel block in the image, amplifying amplitude of a waveform pattern corresponding to the selected frequency with an embedding strength value, and superimposing the waveform pattern in which the amplitude is amplified on the pixel block; and an image outputting unit for outputting an image on which a corresponding waveform pattern is superimposed on each pixel block by the block-by-block embedding unit.

Abstract: There are described methods and apparatus for assessing sediments generated in liquid-based systems. The methods involve optically obtaining information to enable height and, thus, volume data relating to sediments to be measured. Although single samples of liquid-based systems may be processed the methods are particularly suited to processing multiple samples to obtain data relating to sediments at a high rate. The apparatus includes automated handling equipment to enable samples to be moved between workstations and relative to associated optical equipment that is used to obtain information relating to the sediments.

Abstract: A method for inserting data, including a predetermined number of symbols, into an image sequence of at least one image comprising a predetermined number of lines each containing a predetermined number of pixels, comprising the steps of generating a set of functions with a comb-shaped spectrum inserted in an image sequence spectrum and including a respective function for each symbol of the information to be inserted, phase shifting each function of the set of functions by a value representing a respective symbol of the data to be inserted, superimposing the phase-shifted functions, and combining the pixels of the image sequence with a result obtained by superimposing phase-shifted functions.

Abstract: A smoke detecting method is provided. The smoke detecting method includes steps of (a) capturing a video segment for a object and a background; (b) analyzing if an image of the object is moving; (c) analyzing a chrominance variance of the moving object with a corresponding background; (d) analyzing at least one of an edge blur of the image of the background and a flickering frequency of the moving object with its corresponding background; (e) comparing analyzed results obtained from the steps (b)-(d) to a smoke feature; and (f) determining if the moving object is a smoke.

Abstract: Method and arrangement for recognizing objects in mail item images, their position and reading their postal information The following operations are performed: Converting the color image produced in the relevant color camera (11) into a gray level image having a resolution higher than that of the color camera (11) and suitable for reading the postal information in the automatic reading devices, Converting the color image produced in the relevant color camera (11) into a color image having a resolution lower than the camera resolution but sufficient for recognizing objects and their positions, Determining and identifying the objects present in the relevant lower resolution color image including their position, the assignment of the objects to postal information categories being performed on the basis of structural rules established in an upstream teaching phase, Automatic reading of the required postal information in the gray level images of the relevant identified objects.

Abstract: A method for detecting and identifying a traffic sign in a computerized system mounted on a moving vehicle. The system includes a camera mounted on the moving vehicle. The camera captures in real time multiple image frames of the environment in the field of view of the camera and transfers the image frames to an image processor. The processor is programmed for performing the detection of the traffic sign and for performing another driver assistance function. The image frames are partitioned into the image processor into a first portion of the image frames for the detection of the traffic sign and into a second portion of the image frames for the other driver assistance function. Upon detecting an image suspected to be of the traffic sign in at least one of said image frames of the first portion, the image is tracked in at least one of the image frames of the second portion.

Abstract: A gaze position tracking method and apparatus for simply mapping one's gaze position on a monitor screen are provided. The gaze position tracking apparatus includes an image capturing module, and an image processing module. The image capturing module illuminates infrared rays to a user's eyes, reflects an illuminated eye image at 45°, and captures the 45° reflected eye image. The image processing module obtains a pupil center point of the illuminated eye image by performing a predetermined algorithm, and maps the pupil center point on a display plane of a display device through a predetermined transform function.

Abstract: A picked-up image receiver receives a plurality of picked-up images taken by image pickup apparatuses provided in a plurality of positions on a road, respectively, via a wireless network. A reference image acquisition unit acquires a reference image to be compared respectively with the plurality of picked-up images received by the receiver, where reference image are taken by an image pickup apparatus installed in a vehicle. A matching processor locates at least one position on the road by performing pattern matching between the reference image acquired by the acquisition unit and each of the plurality of picked-up images received by the receiver.

Abstract: The invention relates to a device for determining visibility distance in a landscape. The device comprises a camera for taking an image of said landscape; means for storing said image; means for associating each pixel of the image with information representative of the distance between the camera and the point in the landscape corresponding to said pixel, thereby obtaining a map of distances; means for processing the image to detect whether a pixel of the image presents contrast greater than a predetermined value relative to at least some adjacent pixels; means for applying said processing for detecting contrast successively to the pixels of the image beginning from the pixel corresponding to the greatest distance and continuing to the first pixel found to satisfy the contrast condition; and means for associating said pixel with distance information from said map of distances.

Abstract: Provided are a location awareness apparatus using a camera and a method thereof. The apparatus includes: an image capturing unit for photographing a position identification tag using a camera; a distance measuring unit for measuring a distance to a position identification tag; an incident angle measuring unit for measuring a photographing angle at a visual point; an image analyzing unit for reading the photographed image from the image capturing unit, and requesting location information corresponding to the read information to a position recognition server; and a location awareness unit for estimating a current location using the distance to the position identification tag, the photographing angle of the position identification tag, and the location information corresponding to the read information by the image analyzing unit.

Abstract: A method is described for determining a description of motion of a moving mobile camera to determine a user input to an application. The method may involve capturing a series of images from a moving mobile camera and comparing stationary features present in the series of images. Optical flow analysis may be performed on the series of images to determine a description of motion of the moving mobile camera. Based on the determined motion, a user input to an application may be determined and the application may respond to the user input, for example, by updating a user interface of the application.

Abstract: A system for visualizing a print job includes a print job simulator which applies a print job model to print job image data to generate an image which simulates a rendered image of the print job if the print job were to be printed on a specific marking device. The system also includes a display in communication with the print job simulator for displaying the simulation image. The modified image data displayed on the display enables a customer to see a defect in the print job which would appear if the print job were to be rendered on the specific marking device. The print job model may be derived, at least in part, from information derived from the marking device, such as information derived from image data acquired by scanning a test image which has been rendered by the marking device.

Abstract: A method and apparatus to detect a print location error using print dots. The method includes transforming values of pixels of a first image into frequency domains, where a plurality of print dots are arranged at predetermined intervals in the first image; transforming values of pixels of a second image, where the second image is obtained by actually printing the first image using an inkjet head; detecting 2D (2-dimensional) cross power spectral densities of the frequency-domain values of the first and second images; calculating 2D cross correlation values by transforming the 2D cross power spectral densities into time domain; and detecting error coordinates representing the distances between the print dots of the second image and the first image from the time-domain cross correlation values.

Abstract: Biometric identification and/or authentication method for identifying and/or authenticating the user (1) of a terminal (2), wherein said user is identified and/or authenticated by means of personal involuntary eye movement patters being determined with an eye-movement detection module (20). The user is identified and/or authenticated for example by means of characteristics of the personal trajectory (51) of the eyes on an image being determined.

Abstract: The present invention provides an information processing apparatus including combination generating means for getting a first feature quantity of N dimensions, N being an integer of at least two, from first information prepared for execution of learning and use the first feature quantity of N dimensions to generate at least two of a first feature quantity combination that are not greater than N dimensions of the first feature quantity; and learning processing executing means for computing a correlation coefficient between the plurality of first feature quantity combinations generated by the combination generating means and a learning model feature quantity matching each dimension of the plurality of first feature quantity combinations and, by use of the first correlation coefficient, classify the first information, thereby executing learning processing for classifying predetermined second information.

Abstract: In an information processing apparatus, an acquisition unit acquires information of a predetermined type, and a reliability information producing unit produces reliability information indicating reliability of the information of the predetermined type on the basis of a deviation from a predetermined standard condition. A storage unit stores the reliability information indicating the reliability of the information of the predetermined type produced by the reliability information producing unit, in association with the information of the predetermined type.

Abstract: A face image processing apparatus, includes: a face region detecting unit configured to detect a face feature point of a person from a plurality of images picked up by a plurality of imaging units respectively, to detect a face region; a face feature extracting unit configured to extract a face feature from an image of the face region detected by the face region detecting unit; a person recognizing unit configured to calculate a similarity measure based on a face feature of a specific person being previously registered and the face feature extracted by the face feature extracting unit to recognize the person; and an output apparatus which outputs a recognition result in the person recognizing unit.

Abstract: A personal identification device including: an image pickup unit; a light source which emits the light adapted to be transmitted through a finger and incident on said image pickup unit; an image operating unit which generates a pattern from an image picked up by said image pickup unit and matching the pattern of said image with a pattern registered in advance; a storage which holds said registered pattern; a guide unit which indicates the position where the image of said finger is picked up; and a detection unit which detects a contact between said finger and said guide unit.

Abstract: A method of analyzing a lesion in a medical digital image using at least one point contained within a lesion to be analyzed includes propagating a wave-front surface from the point(s) for a plurality of steps; partitioning the wave-front surface into a plurality of wave-front parts wherein each wave-front part is associated with a different portion of the wave-front surface corresponding to a previous propagation step; and analyzing at least one feature associated with each wave-front part to classify anatomical structures associated with the lesion and normal anatomy within the medical digital image.

Abstract: Methods and systems for converting dissimilar raw data collected primarily from one or more imaging devices into standard formats, organizing the formatted data into a hierarchical arrangement to facilitate efficient memory storage and subsequent retrieval, generating an imaging presentation, and recording that presentation onto portable media are shown. The imaging presentation can be subsequently viewed by a user by accessing the portable media using a platform-independent interface.

Abstract: A system and method enhance the visibility of medical devices shown in internal images. A medical device may be inserted into a patient. Internal images of the patient may then be acquired via various medical imaging techniques. However, the medical device may only be partially visible in the images, if at all. For instance, the images may be acquired with minimal radiation exposure to the patient and/or the medical device may be thin or made of translucent material. Model data may be associated with the geometry or other characteristics of the medical device. The model data may be adapted, such as rotated, resized, bent, or otherwise modified, to form a “best fit” with the medical device as actually shown in the internal images. The adapted model data may be superimposed onto a display of the medical device as shown in the internal images to enhance visibility of the medical device.

Abstract: The invention relates to a device for merging a 2D radioscopy image with an image obtained from a 3D image data record, having a memory unit that stores the 2D radioscopy image and the 3D image data record, a segmentation unit that segments an inner surface of a hollow organ from the 3D image data record, a registration unit that registers the 2D radioscopy image with the 3D image data record, a back-projection unit that back-projects the pixels of the 2D radioscopy image onto the segmented surface, taking account of the projection geometry of the 2D radioscopy image and the registration, and an image merger unit that generates a virtual endoscopy view of the surface from the segmented surface using the back-projected pixels. The device primarily allows 2D radioscopy images to be superimposed during interventional procedures with a fly display of the interior of an interesting organ.

Abstract: A method of generating a multiscale contrast enhanced image is described wherein the shape of edge transitions is preserved. Detail images are subjected to a conversion, the conversion function of at least one scale being adjusted for each detail pixel value according to the ratio between the combination of the enhanced center differences and the combination of the unenhanced center differences.

Abstract: Method and system for processing an object within a diagnostic image comprises segmenting a three dimensional (3D) object within a diagnostic image. A contour of the object is fitted with a 3D mesh comprising splines in at least first and second directions. The splines provide a plurality of editable control points, and the splines in the first direction intersect with the splines in the second direction at intersection points. A position of at least one control point on the 3D mesh is adjusted based on a user input.

Abstract: During acquisition of ultrasound data in a medical imaging procedure, three-dimensional model of a structure being imaged, e.g., an electroanatomical map, is co-displayed and visually marked, to indicate progress of data acquisition. The plane of intersection successive two-dimensional images are marked on the as a line or colored region on the three-dimensional model. This display enables the operator to determine regions where sufficient data have been captured, and guides the operator to areas where additional data collection is still needed. Various color schemes are used to indicate the relative sufficiency of data collection.

Abstract: Disclosed is a method and apparatus for registering data points in data sets representing scan data. Data points corresponding to a physical feature represented in the scan data are automatically detected. The detected data points in one data set are correlated with detected data points in another data set. A group of similarity transformations between the correlated detected data points is then calculated. The group of similarity transformations is then combined. In one advantageous embodiment, the physical feature is vertebras.

Abstract: A method for determining the risk of rupture of a blood vessel using an appropriate set of 2-D slice images obtained by scanning the blood vessel, the method comprising: generating a mesh model of the blood vessel using the set of 2-D slice images; conducting finite element stress analysis on the mesh model to calculate the level of stress on different locations on the mesh model; and determining the risk of rupture of the blood vessel based on the calculated levels of stress on different locations on the mesh model.

Abstract: A method for correcting subject motion in positron emission tomography (PET) imaging includes acquiring navigator signals from the subject with a magnetic resonance (MR) imaging system. The navigator signals are used to determine subject motion during a PET scan relative to a reference position and corrective values therefrom. Sinogram data acquired during the PET scan can then be corrected using the corrective values. PET images are then reconstructed from the corrected sinogram data.

Abstract: A method for registering an anatomical structure using at least one marker attached to the structure includes: obtaining a three-dimensional model of the structure via an imaging method; obtaining at least two two-dimensional recordings of the structure from different angles; and ascertaining a spatial position and location of the three-dimensional model or a position and location of the three-dimensional model in a patient coordinate system based on a matching method that uses the position of the at least one marker in the at least two two-dimensional mappings such that the three-dimensional model of the structure matches the structure.

Abstract: A method and system for automatically detecting rib metastasis in a thoracic CT volume is disclosed. The ribs are segmented in said CT volume by recursive tracing. A series of cross-sectional images are then generated along a centerline of each rib. Cortical and trabecular bone structures are segmented in each of the cross-sectional images for each rib. Features are calculated for each cross-sectional image based on characteristics of the cortical and trabecular bone structures, and alterations are detected in the cross-sectional images based on the features. Rib metastasis is detected in a rib when an alteration is detected in a number of consecutive cross-sectional images along the centerline of the rib.

Abstract: A series of holograms is recorded by synchronizing a camera with laser pulses under the control of a digital delay generator. Amplitude and phase images are calculated while image distances are adjusted for the best focus on the object under observation. The amplitude and phase images are reconstructed while adjusting the image distances over a predetermined range to maintain the object in focus. Numerical superposition of a plurality of holographic fields taken with varying wavelengths provides high resolution microscopic three-dimensional imaging. Numerical reconstruction is based on an angular spectrum method that enables calculation of the image at any distance from the hologram plane. Wavelength scanning digital interference holography also enables image reconstruction along an arbitrarily tilted plane.

Abstract: A three dimensional image processing apparatus includes a feature point designation unit which designates feature points on at least two selected images selected from a plurality of images in different radiographing directions, a three dimensional position calculation unit which calculates a three dimensional position associated with a feature point, a two dimensional position calculation unit which calculates the two dimensional position of a feature point on an unselected image on the basis of the calculated three dimensional position of the feature point, a feature point extraction unit which extracts a feature point from an unselected image, a positional shift calculation unit which calculates a positional shift of the two dimensional position of the extracted feature point with respect to the calculated two dimensional position of the feature point, a correction unit which corrects the position of the unselected image on the basis of the calculated positional shift, and an image reconstruction unit which

Abstract: A system and method provide local image enhancement. Internal native images of a patient may be acquired during an interventional procedure. A portion of the native images may show an interventional device or material. Subtracted images may be created by subtracting mask images from the native images, such as via either digital subtraction angiography to display vessel structures, or “roadmapping” during interventional procedures to deploy various medical devices and materials. The local level of absorption associated with the portion of the images showing a vessel structure or in which the interventional object resides may be determined from either the native images or the mask images. Subsequently, the subtracted images may be locally altered to compensate for the local level of absorption such that the visibility of a vessel structure or interventional object is enhanced. The subtracted images may be enhanced by altering the local contrast, brightness, or sharpness, or noise.

Abstract: X-ray images are recorded of a patient's heart and the heartbeat phase is registered as that is done. The heartbeat phases are coarsely divided into intervals and all X-ray images that have been assigned heartbeat phase from the interval are used for reconstructing a 3D image dataset. The movement fields of the other 3D image datasets are then calculated for one of said 3D image datasets. Movement fields are vector fields indicating the movements of similar structures from one local area to the other. A departure is then made from the coarse interval division, and for each heartbeat phase a movement field is interpolated individually or at least for fairly short intervals from the movement fields determined in advance, which field is used for generating a deformed 3D image dataset that has been imaged onto a reference heartbeat phase. The deformed 3D image datasets are then added together.

Abstract: An analysis system automatically analyzes and counts fluorescence signals present in biopsy tissue marked using Fluorescence in situ Hybridization (FISH). The user of the system specifies classes of a class network and process steps of a process hierarchy. Then pixel values in image slices of biopsy tissue are acquired in three dimensions. A computer-implemented network structure is generated by linking pixel values to objects of a data network according to the class network and process hierarchy. Objects associated with pixel values at different depths of the biopsy tissue are used to determine the number, volume and distance between cell components. In one application, fluorescence signals that mark Her2/neural genes and centromeres of chromosome seventeen are counted to diagnose breast cancer. Her2/neural genes that overlap one another or that are covered by centromeres can be accurately counted. Signal artifacts that do not mark genes can be identified by their excessive volume.

Abstract: A method for determining the quality of focus of a digital image of a biological specimen includes obtaining a digital image of a specimen using a specimen imaging apparatus. A measure of image texture is calculated at two different scales, and the measurements are compared to determine how much high-resolution data the image contains compared to low-resolution data. The texture measurement may, for example, be a Brenner auto-focus score calculated from the means of adjacent pairs of pixels for the high-resolution measurement and from the means of adjacent triples of pixels for the low-resolution measurement. A score indicative of the quality of focus is then established based on a function of the low-resolution and high-resolution measurements. This score may be used by an automated imaging device to verify that image quality is acceptable. The device may adjust the focus and acquire new images to replace any that are deemed unacceptable.

Abstract: An Any Which Way Check Acceptance method and apparatus is provided, which allow a set of checks to be deposited in a stack, where each check can be oriented in any of sixteen different ways. In one embodiment of the invention, the ATM check reader has an MICR and OCR scanner/reader. When a set of checks is deposited, each check is subjected to a MICR scan and an OCR scan. If the check is aligned correctly and right side up, then the check is processed based on the MICR scan information. If the check is not aligned correctly or is upside down, then the MICR read fails because the magnetic stripe on the check is not where it is expected to be. Rather than rejecting the check at this point, the invention uses the OCR scan information from both the front and back of the check to process the check.

Abstract: An object recognition apparatus that processes images, as acquired by an imaging means (10) mounted on a moving object, in a first image plane and a second image plane of different points of view, and recognizes an object in the vicinity of the moving object. The object recognition apparatus comprises: a feature point detection means (42) that detects feature points in first and second image planes of an object image; a fundamental matrix determination means (43a) that determines, based on calculation of an epipole through the auto-epipolar property, a fundamental matrix that expresses a geometrically corresponding relationship based on translational camera movement, with not less than two pairs of feature points corresponding between the first and second image planes; and a three-dimensional position calculation means (43b) that calculates a three-dimensional position of an object based on the coordinates of the object in the first and second image planes and the determined fundamental matrix.

Abstract: Generation of basis functions for spectral reflectances of color samples is provided. Reflectance information of the color samples is input, the reflectance information is weighted with a weighting function based on a wavelength dependence of an optical sensor, and the weighted information is analyzed to obtain the basis functions. Basis functions for illuminants are generated by inputting reflectance and associated information of the color samples, inputting illuminant information, constructing a matrix of weighted tristimulus values, and analyzing the matrix to obtain the basis functions. A weighting function for an optical sensor is generated by inputting a first weighting function, based on transformation of a reflectance perturbation from a reflectance space into a color space of the sensor, calculating the first weighting function with predetermined stimuli to obtain a plurality of resulting functions, and averaging the resulting functions to obtain the weighting function for the sensor.

Abstract: An apparatus and method of reproducing a preferred color to eliminate or reduce errors caused when converting of colors of an input image in corresponding color regions of a color space, respectively, wherein the colors of an input image are included in a plurality of different color regions. The apparatus includes a region judging unit to judge whether pixels of an input image are included in one or more preset color regions, a color converting unit to execute a color conversion of the pixels in at least one conversion-desired color regions among one or more color regions that include the pixels, and an output unit to output an image formed by the color-converted pixels.

Abstract: Disclosed are an apparatus and method to improve clarity of images, which can prevent the degradation of the clarity of a display unit caused by deterioration of a contrast characteristic. The apparatus includes: an artifact reducing unit determining a representative color of one of the images and moving a color of an edge as the determined representative color; a filter extracting a high frequency component of the image; and a sharpness enhancement unit improving the clarity of the image having the color of the edge moved and the filtered high frequency component.

Abstract: An image processing method takes as its input, a patch of an image where a candidate red-eye has been detected. The method includes classifying the patch with a classifier trained to assign the patch either to a default first class of patches associated with a standard correction of the candidate red-eye or to at least one second class of patches associated with a modified correction of the candidate red-eye. The modified correction may be designed to reduce a risk of degradation of the image for the second class of patches. The classification optionally includes determining a confidence level associated with the classification. If the image is classified into the at least one second class and the confidence level, where determined, exceeds a threshold, the modified correction is applied to the patch, otherwise, the standard correction is applied.

Abstract: An illumination equalizing device includes a polygonal rotary column disposed in a sealed space, equipped with light sources, and rotatable at specific angular intervals, light sources radiating light onto an image test member attached to a wall of the sealed space for testing a digital image, the light sources mounted on side surfaces of the polygonal rotary column, illuminometers measuring illumination values of light radiated onto the image test member, and a rotary column control unit rotating the polygonal rotary column at set angular intervals so that the illumination values measured by the illuminometers are equalized. A method for equalizing the illumination of light sources for a digital image test member, and an apparatus and method for testing the color of a digital image uses the illumination equalizing device.

Abstract: A system, medium, and method with noise reducing adaptive saturation adjustment. The system with adaptive saturation adjustment includes a luminance value extracting unit extracting luminance values of an input image, and a saturation adjusting unit adjusting saturation components of the input image on the basis of the extracted luminance values.

Abstract: This invention more effectively suppresses color fringing in a color image by image processing. An image processing method includes estimating the degree of color fringing in a color image based on the color image that is generated by photo-electrically converting an object image and formed from a plurality of color planes. The method also includes removing from the color image the estimated degree of color fringing.

Abstract: Upon creating a color conversion table from a first color space to a second color space, a reversal region where hues are reversed is detected from at least one color gamut in step S2, and the reversal region is corrected in step S3. Mapping is done based on the corrected color gamut in step S4, thereby creating an appropriate color conversion table that suppresses any hue reversal.

Abstract: A method for rigid registration of ear impression models, including: extracting a canal region from an undetailed ear impression model, the undetailed ear impression model representing an undetailed surface of an ear canal and outer ear geometry; extracting a canal region from a detailed ear impression model, the detailed ear impression model representing a detailed surface of the ear canal; generating an orientation histogram for the canal region of the undetailed ear impression model and an orientation histogram for the canal region of the detailed ear impression model; performing a rotational alignment between the orientation histograms; computing a translational shift between the canal regions after performing the rotational alignment; and performing a registration between the undetailed and detailed ear impression models after computing the translational shift.

Abstract: A system and method for analyzing the motions of an object based on the silhouettes of the object are provided. The system includes a foreground detector, a contour extractor, a model generator, a corner histogram generator, and a value of similarity measuring unit. The foreground detector detects a moving foreground object from an input image. The contour extractor extracts silhouette contour of the detected foreground object, and the model generator generates mean value histogram models as references to determine motions of the object.

Abstract: Software of a simple configuration checks whether an original image to be corrected is an image picture, and an image correction process based upon a formed histogram of the original image is not performed for an image different from the image picture. An image processing condition is set in accordance with the formed histogram to perform the image correction process for the original image. An image processing method judges from a shape of the formed histogram whether the original image is an image picture, and does not perform not perform the image correction process for the original image if it is judged that the original image is not an image picture.