Abstract: A multivalue image of the face input by a CCD camera 2 is stored in a multivalue-image memory 3. A multivalue-image characteristic extracting means 23 extracts a pixel of interest from the stored multivalue face image in accordance with distribution of relative brightness of the brightness of the pixel of interest and those of pixels adjacent to the pixel of interest. The extracted pixel of interest is stored in a binarized-image memory 5. The stored pixel of interest is used to extract an eye region. In accordance with the extracted eye region, an opening/closing determining means 7 determines opening/closing of the eyes.

Abstract: A method and apparatus is described that smoothes images within regions but not across boundaries. In one embodiment, a segmentation map is smoothed. Based on the color difference between pixels in an input frame and corresponding pixels in a background image, this segmentation map indicates the likelihood that each pixel in the input frame belongs to the foreground. The smoothed segmentation map may be processed further to reduce misclassification errors. Based on the segmentation map, the foreground portion of the image is superimposed over a new background image.

Abstract: The invention relates to a method of obtaining a developed two-dimensional image of the wall of a borehole. The method comprises the steps consisting in: measuring a primary physical magnitude in said borehole as a function both of depth and of azimuth; measuring a secondary physical magnitude in said borehole as a function of depth; establishing a relationship (ƒ) between said primary physical magnitude and said secondary physical magnitude; and deducing from said relationship values for said secondary physical magnitude as a function both of depth and of azimuth, which method makes it possible to reconstruct a two-dimensional image developed over the wall of a borehole concerning a secondary physical magnitude which is measured in said borehole as a function of depth only. The invention is particularly applicable to density imaging.

Abstract: Computer software for and a method of calculating ring-wedge data from a digital image by performing a discrete Fourier transform of the digital image. A discrete autocorrelation, discrete cosine transform, and/or Hadamard transform is also preferably performed, together with providing the results to a neural network (most preferably a fully connected, three-layer, feed-forward neural network with sigmoidal activation functions) to perform pattern recognition on the data.

Abstract: An image processing apparatus for calculating a new luminance value of a central pixel to adjust the spatial frequency characteristics of an input image includes a plurality of subfilters, totalizer, and adder. The subfilters are arranged in parallel with each other for a plurality of pixel groups each made up of one or more pixels in a submatrix. The subfilters multiply the sums of the luminance values of pixels included in corresponding pixel groups by predetermined coefficients corresponding to desired spatial frequency adjustment filter characteristics, and output the products for each submatrix made up of M×M (M is an odd number of 3 or more) pixels centered on pixels constituting an input image for a two-dimensional input image made up of many pixels that are arrayed in a matrix and represent luminance values at positions. The totalizer totals outputs from the subfilters, and outputs the sum as the adjustment amount of the spatial frequency characteristics.

Abstract: Methods for identifying a note with a partial OCR of one or more characters in the note's serial code. The methods record the characters read and associates each character read with its field position in the serial code. The method can use this information or combine the character and field information with positional information of the note within a stack in order to identify a note with a reasonable degree of statistical probability.

Abstract: For the reproduction of originals, images are generated on an image carrier, for example by printing. The imaging device that generates the image is usually not capable to cover at once the complete image area on the carrier. If the device is capable to cover the full width of the image area, the image may be generated line by line. Devices not having this capability will generate a first portion of an image line on the carrier. An adjacent second portion of the image line is then generated by another imaging device or after a period of time by the imaging device that generated the first portion. The region where the first and second portion meet on the carrier may cause visual artefacts on the final reproduction due to spatial misregistration of the adjacent line portions. This problem is solved by dividing the image in adjacent sub-images having an overlap zone on the carrier.

Abstract: A method of providing a representation of image data is disclosed. The method accesses a plurality of discrete sample values of the image data and calculates kernel values for each of the discrete sample values using a scaled kernel. The scaled kernel is constructed by transforming a kernel from a first range to a second range. In order to provide a representation of the image data, the kernel values are convolved with the discrete sample values.

Abstract: A scanning device for electronically capturing a fingerprint image, employing a finger guide unit and a platen. The finger guide unit positions a finger for scanning by means of a gap into which the finger is placed. The guide maintains the finger within the print scanning range when used in conjunction with a movable platen. The guide unit is rotatable allowing the guide to be moved to expose the whole movable platen. The finger guide unit has two guide plates disposed adjacent one another creating a gap. The gap width is adjustable by means of an adjustment device, allowing fingers of any size to be properly positioned and guided within the scanner reading range. The guide plates each have an edge lined with low-friction material which contacts the finger when in use. The guide plates each have an extension which serves as a handle for raising the guide unit and as a hanger for suspending the guide unit above the platen for use.

Abstract: A two-dimensional (2D) image model models the layout structure of a class of document images as an image grammar and includes production rules having explicit layout parameters as data items that indicate information about the spatial relationships among image constituents occurring in images included in the class. The parameters are explicitly represented in the grammar rules in a manner that permits them to be automatically trained by a training operation that makes use of sample document images from the class of modeled documents. After each sample image is aligned with the 2D grammar, document-specific measurements about the spatial relationships between image constituents are taken from the image. Optimal values for the layout parameters are then computed from the measurement data collected from all samples.

Abstract: An electronic database for image interpolation is generated by a computer. The computer generates a low-resolution image from a training image, a plurality of representative vectors from the low-resolution image, and a plurality of interpolation filters corresponding to each of the representative vectors. The interpolation filters and the representative vectors are generated off-line and can be used to perform image interpolation on an image other than the training image. The database can be stored in a device such as computer or a printer.

Abstract: An apparatus and method of template fitting for fitting a plurality of templates in correspondence with a gray-scale image, including receiving gray-scale image information of an observed image; defining a window of the gray-scale image information so as to enable a loose-gray-scale fit between the defined window and the plurality of templates; extracting a plurality of pixels of the image information and using the window to which to fit at least one of the plurality of templates. Further, fitting one of the plurality of templates to the defined window within a threshold looseness interval associated with the template wherein a looseness interval between the window of image data and the template is less than the threshold looseness interval.

Abstract: A three-dimension distance time-of-flight system is disclosed in which distance values are acquired by a plurality of sensors independently from each other. For use with this and similar systems, Z-distance accuracy and resolution are enhanced using various techniques including over-sampling acquired sensor data and forming running averages, or forming moving averages. Acquired data may be rejected if it fails to meet criteria associated with distance, luminosity, velocity, or estimated shape information reported by neighboring sensors. A sub-target having at least one pre-calibrated reflectance zone is used to improve system measurement accuracy. Elliptical error is corrected for using a disclosed method, and reversible mapping of Z-values into RGB is provided.

Abstract: Color image quantization using a hierarchical perceptual color model is disclosed. In one embodiment, a method constructs a clustering space of an image having a number of pixels, based on a color perception model. The clustering space includes a number of significant pixels, where each of the significant pixels does not have a parent pixel within the clustering space. The colors of the image are quantized based on these significant pixels. The remaining pixels have their colors mapped to one of the quantized colors.

Abstract: A method and apparatus for obtaining high-resolution images of rotating targets by using an image reconstruction algorithm without interpolation, are provided. The method comprises the steps of: a) acquiring initial information; b) calculating parameters; c) computing a start frequency ƒsk and a step frequency &dgr;ƒk; d) measuring data for the target to store them; e) determining whether or not the step d) is completed; f) if the determination result is negative, repeating the steps a) to e); and, if otherwise, obtaining the image; and g) displaying the image.

Abstract: A three-dimensional shape measuring apparatus capable of simultaneously obtaining range information and luminance information with high precision, independently of an object. A controller scans slit light, emitted from a laser beam source and shaped by a cylindrical lens, on an object plural times, by mirror surfaces of a polygon mirror, while causing the laser beam source to flash by using a laser beam source driver. The slit light is time-sequentially combined into projection pattern light having plural light stripes, respectively 3-level or more intensity-modulated, and the projection pattern light is projected onto the object. An image processor obtains the range information and the luminance information based on reflection light obtained by image pickup by first and second cameras.

Abstract: A method for improved readability of digitally captured document images that include printed or handwritten textual material overlaid on background graphics. Text in the document is generally composed at least in part of strokes characterized by pairs of edges in close proximity to one another. The digital image comprises an array of pixels representing at least a portion of the document. The edges in the pixel array are first identified and then grown by an effective amount so as to cause pairs of edges characterizing each stroke substantially to merge. The grown edges are then shrunk by an effective amount so as to cause non-stroke edges to be substantially eliminated without eliminating the merged stroke edges.

Abstract: Two different recognition processing units respectively perform a plurality of different recognition processing operations for the pattern to be recognized input from a character input unit, and acquire a plurality of recognition candidates and recognition scores. An accuracy calculation unit converts the recognition scores obtained by the two recognition processing units into accuracies based on a scale common to the plurality of different recognition processing operations using parameters stored in a parameter storage unit. A determination unit generates a recognition candidate sequence by determining the order of the recognition candidates obtained by the two recognition processing units on the basis of the accuracies converted by the accuracy calculation unit.

Abstract: An image processing device for calculating the motion direction of each pixel in a predetermined screen of interest from among a plurality of time series screens. The image processing device includes a score calculator for calculating a score corresponding to each of a plurality of motion directions of each pixel in the predetermined screen of interest, based on pixels present in the motion direction across the plurality of the time series screens, and a motion direction calculator for calculating the motion direction of each pixel in the predetermined screen of interest, by processing the plurality of the motion directions based on the scores corresponding to the plurality of the motion directions. The image processing device thus performs a highly accurate motion direction detection process within a short calculation time.

Abstract: Automated layer extraction from 2D images making up a 3D scene, and automated image pixel assignment to layers, to provide for scene modeling, is disclosed. In one embodiment, a computer-implemented method determines a number of planes, or layers, and assigns pixels to the planes. The method can determine the number of planes by first determining the high-entropy pixels of the images, and then determining a 1-plane through a predetermined n-plane estimation, such as via a robust estimation, and a most likely x-plane estimation, where x is between 1 and n, such as via a Bayesian approach. Furthermore, the method can assign pixels via an iterative EM approach based on classifying criteria.