Abstract: A document authentication control device has a card positioning device with a document insertion region, an optical scanner, a data processor that receives data from the optical scanner, a database for storing processed optical image data, and a display screen for displaying document, authentication, and other data. The data processor correlates an image region of a document and a reference region of the document to corresponding image and reference regions of the document retrieved from the database, thereby determining the authenticity of the document. The reference region is a region of the document that is spaced away from the image region of the document.

Abstract: Documents are classified into one or more clusters corresponding to predefined classification categories by building a knowledge base comprising matrices of vectors which indicate the significance of terms within a corpus of text formed by the documents and classified in the knowledge base to each cluster. The significance of terms is determined assuming a standard normal probability distribution, and terms are determined to be significant to a cluster if their probability of occurrence being due to chance is low. For each cluster, statistical signatures comprising sums of weighted products and intersections of cluster terms to corpus terms are generated and used as discriminators for classifying documents. The knowledge base is built using prefix and suffix lexical rules which are context-sensitive and applied selectively to improve the accuracy and precision of classification.

Abstract: A plurality of cameras acquire images of a plurality of reference points located on known positions in a three-dimensional space, an image processor obtains the coordinates of projected points thereof on the respective images, and a plurality of affine cameras having linear relation between the three-dimensional space and images are assumed for calculating how the affine cameras project the respective reference points and correcting the coordinates of the projected points to be consistent with the projected points.

Abstract: In a reverse vending apparatus for detecting containers, e.g., bottles of glass or plastic, or packaging made of metal, wood, glass or plastic which for the recycling of materials or reuse of the container are inserted in the machine and conveyed past a detector station containing a video camera, a video image analyser (125, 130) is connected to the video camera in order to analyse the video image whilst the container (B) is conveyed in lying position and with its axis parallel to the direction of transport past the video camera (109). The video analyser (125) contains a calculator component (130) for determining, when the container moves into the video image, whether the container enters the detection zone (video image) mouth (B1) (e.g., top portion or neck of bottle) (FIG. 3b) first or bottom (B2) (FIG.

Abstract: Faces are one of the most commonly recognized features among people. According to the invention a system for recognizing intensity images of faces is provided. Intensity images of a face are captured and normalized. The intensity images are transformed, filtered and then transformed again. The filter is based on a three-dimensional image of a face against which the intensity image is being compared. The result is a form of correlation that is substantially illumination independent.

Abstract: Methods and systems for data compression and decompression are disclosed. Specifically, the method for data compression of the present invention receives eight inputs representing pixel information of an image and performs a combination of an 8-point discrete cosine transform (DCT) and weighting function to obtain eight outputs representing digital representations of an image. The method for data decompression receives eight inputs representing digital representations of an image and performs a combination of an inverse weighting function and an 8-point inverse discrete cosine transform (IDCT) to obtain pixel components of an image. The methods and systems of the present invention may be used in optimizing digital video encoders and decoders.

Abstract: Disclosed is a method, system, and program for converting an externally defined four dimensional colorant, e.g., CMYK, to an equivalent four dimensional colorant, e.g., C'M'Y'K, having components of a printer. A measurement is made of first color values, e.g., L.sup.* a.sup.* b, of a first set of patches having predetermined combinations of varying percentages of three primary colors, e.g., CMY, printed by the printer. Each combination of known CMY values are correlated with corresponding color values, e.g., L.sup.* a.sup.* b, as input to a first inversion program for determining CMY values for any given color value (L.sup.* a.sup.* b). A measurement is also made of second color values, e.g., L.sup.* a.sup.* b, of a second set of patches having predetermined varying percentages of a fourth colorant (K) printed by the printer. The first inversion program is used to determine CMY values corresponding to the color values, L.sup.* a.sup.* b, for the varying percentages of the fourth colorant (D).

Abstract: An image filming and compression system includes a color complementary filter having a predetermined color arrangement; a CCD for generating image data for output according to the light of an object received via the color complementary filter; block forming circuit for dividing the image data into blocks; and image data converter circuit for calculating spatial frequency components of a luminance signal and color difference signals for each block according to the image data. The image data converter circuit directly calculates the spatial frequency components of the luminance signal and the color difference signals by conducting the only linear transformation on the image data. This obviates the need for a means to generate the luminance signal and the color difference signals according to which the spatial frequency components of the luminance signal and the color difference signals are calculated.

Abstract: A device, and a method for its operation, for verifying a person's identity by comparing in a correlator (18) selected features of a reference fingerprint image, generated in a sensor (10) from the fingerprint of a person of known identity, with a subject fingerprint image taken from a person whose identity is to be verified. In an enrollment procedure, a fingerprint from a person of known identity is analyzed in an enrollment processor (14) to locate multiple reference patches that together are distinctive to that person's fingerprint. The reference patch images are stored, together with their locations in the image, in a reference image storage unit (16). When a subject fingerprint image is later provided, every reference patch is compared with every possible patch of similar size in the subject image, to find a set of candidate match locations in the subject image.

Abstract: A method of enhancing the readability of rapidly displayed text and with rapid apprehension, at a rate which is greater than the maximum unaided reading capability of that subject using the method. The method comprises a rapid and sequential moving of the words of text through a window on a screen of a computer monitor. In accordance with the method, the words are allowed to pass through or be displayed in the display window, one word at a time, and at a rate in which the time for display which is based on the number of characters in a word is related to and a function of the total amount of time required for all of the words in a segment of the text to be displayed. A time for display of each word of average character length is the same, and that certain words in a segment will be displayed for a longer period of time than other of the words. Usually, the words which contain more characters will have a longer display period.

Abstract: An arrangement of discrete objects is analyzed. First and second characteristics are extracted from an actual arrangement of discrete objects and an ideal arrangement of points, respectively, and the first and second characteristics are compared. Each characteristic is invariant, to within an angular constant, under an affine transformation of the respective arrangement.

Abstract: A method and apparatus for compression of data using a technique for quantization and encoding referred to as Mapping through Interval Refinement (MIR). The method uses the size of the original data set together with a target compression ratio to determine the size of a compressed representative of the original data. The data elements after de-correlation are effectively sorted in decreasing order of significance and then written to an output data set using an efficient encoding method which incrementally refines the precision of elements already output. The output process continues until the target compressed file size is reached. Decompression of the compressed data is accomplished by reading in the sorted elements and restoring them to their locations in the data set, and to the precisions saved in the compression process.

Abstract: When an image file is to be registered, image data is read from a document; features of the document are extracted from the read-out image data; the image file is generated with the extracted document features correlated to the read-out image data for storage, and further in a case wherein an image file is to be retrieved, image data is read from a document, features of the document are extracted from the read-out data, and an image file having document features identical to the information for retrieval from image files with the extracted document features stored therein as information for retrieval.

Abstract: Method and apparatus for filtering non-text information from a page containing text, the text being associated with a color. The page is represented as an image in a first color space. The image is converted to a second color space that has a color channel closely associated with the text color. The color channel is selected and gray values are derived that correspond to text color channel values associated with cells in the image. Cells in the image having gray values of a predefined relationship with respect to predetermined threshold values are marked as text cells, and the remaining cells are identified as non-text cells. The gray values of the text and non-text cells are adjusted to increase the contrast between text and non-text information. The single-color space image may then be printed by a monochrome printer.

Abstract: An operation of an iris filter is carried out on an original image signal representing an image, and the degree of centralization of gradients of the original image signal with respect to a picture element is thereby calculated, each of picture elements constituting the image being taken as the picture element. An image portion, which is associated with a high degree of centralization, in the image is detected in accordance with the calculated degree of centralization. Image emphasis processing is then selectively carried out on the detected image portion. Alternatively, a morphology operation is carried out on an original image signal Dorg by using a multiply structure element Bi and a scale factor .lambda., and a morphology signal Dmor is thereby obtained.

Abstract: A system for digitally capturing a product image includes a digital camera, a computer interfaced with the digital camera and programmed to provide a graphical interface including indicators relating to the exposure setting of the camera, the resolution image size of the image to be captured and the product identification number. The camera is controlled through the operation of a pointing device, such as a mouse and "buttons" displayed on the interface including setting the camera in a remote control mode, capturing a product image, selecting an image resolution, saving an image and resetting the system for digital capture of the next product image. A sensing device such as a bar code scanner is provide for recording the product number and inputting the number into the computer. Captured product image data is saved to a database along with product dimensions. One or more processors are used to process the data to crop, resize and silhouette the product image.

Abstract: A system and method which enables the location and orientation of an image to be determined without introducing scanning artifacts into the rendered image. The system utilizes a separate set of sensors on a scanning bar that are sensitive to a wavelength of light outside the range of wavelengths of the typical sensors found on the scanning bar, such as red, green, or blue. Moreover, the system includes a light source which is capable of emitting the wavelength of light that is outside this range of wavelength of light. Thus, whenever the additional set of sensors detect light, the system would determine that the light was due to a scanning artifact, such as a hole, rip, or dog ear in the original document being scanned.

Abstract: Deviation between an upper portion and a lower portion of a screw hole is recognized. This is accomplished by imaging holes in respective objects to obtain a contrast image. The position of the hole in the upper object and the lower object is detected. The deviation between the positions is calculated. Screws are tightened sequentially beginning with the hole having the smallest deviation. The rotation angle of the object to be tightened is determined. From this rotation angle, the deviation of other holes is calculated.

Abstract: A microorganism detecting apparatus comprising a fluorescence microscope section which is furnished with a motor-driven xyz stage assembly for placing thereon a slide sample subject to fluorescent staining. An illumination subsystem for projecting excitation light of predetermined wavelength on the sample and a filter assembly for emission, which limits the band of frequencies emitted to a video camera which captures the images of fluorescent stained microorganisms from the sample slide mounted on the xyz stage assembly. A computer reads the output value of the band-limited signal from the video camera and processes the read output. A subsystem device has controllers which drive the xyz stage assembly so as to permit the microorganism sample to be scanned over its whole area. Each image is displayed on a video display monitor and detected microbes in the sample are stored on a hard drive and in an imaging archive system to permit verification or reexamination.

Abstract: A DCT based lossy compression method for compressing a digitized image composed of a matrix of image samples to provide a compressed image which satisfies a predefined bit budget. The digitized image is first sub-divided into blocks (e.g. of size 8.times.8 pixels). A discrete cosine transform (DCT) comprising a set of DCT coefficients is then derived for each block. A quantization table is selected from a set of quantization tables and, using the selected table, the coefficients of each DCT are quantized. A zero-value index, corresponding to the average number of zero value quantized DCT coefficients per DCT, is determined. A predicted zero-value index is calculated using said predefined bit budget and a quantization table selected from said set of tables using the determined index and the predicted index. Using that selected table, the unquantized coefficients of the DCTs are re-quantized and the requantized coefficients compressed using run-length encoding and Huffman encoding.