Abstract: A method and system for detecting registration markers having the shape of an `X` on a scanned test target used to calibrate an image processing system. The procedure is impervious to scanning and printing distortion. A captured image is converted to a binary image and then segmented into a list of eight-connected components. A set of features is extracted from each component in the list. An accurate decision rule is executed on each component. If a component is found to be a marker, its centroid is returned as its position.

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: A method of making and using a target to verify an image from an imaging device is provided. A target is formed with a set of color patches that have numerically valued color characteristics. The color patches are repeated throughout the target as to permit verification of colors as a function of position of the color patches with respect to the target. A set of markers are provided to facilitate machine recognition of the target such that each position of the color patches may be referenced relative to the set of markers.

Abstract: The invention relates to a method for monitoring the quality of a moving web of multicolor print during a printing process, including monitoring the mutual location of the various colors on the basis of marks arranged on the web of print and further monitoring the location in longitudinal direction and transversal direction of the web of print in relation to at least one printing press.

Abstract: A process for pattern searching in which position coordinates of patterns on a workpiece with a rough surface can be determined automatically and with high precision, and a device for executing the process are achieved by CCD cameras and the like picking up patterns which are located on a workpiece with a rough surface, and which are formed only by intersecting lines, and by a storage means storing light-dark signals. Furthermore, according to the invention, the image signals are integrated in directions which are each parallel to the lines of the patterns, by which integral signals .SIGMA.Xn, .SIGMA.Yn are determined. By integrating the image signals, the images which are formed as a result of surface roughness are averaged. The integration signals clearly yield boundary positions of the patterns, and by differentiating these integral signals, the pattern positions are determined based on their peak positions.

Abstract: A method and apparatus uses naturally occurring object features as targets in a machine vision based robot (or other) guidance system. In one embodiment, a special high speed processor finds at least 3 pre-selected feature points on an object, which when considered with the data base for the object, allows a rapid 6 degree of freedom solution for the object location relative to the camera and thence connected automation. While primarily envisioned for industrial robots, the invention is useful for all sorts of machines including vehicles, construction machinery and the like--anywhere the target object has a known data base relative to the features in question.

Abstract: Method and apparatus for aligning more than two fragments of an image to assemble the image while providing high alignment quality between each pair of overlapping image fragments. Image registration operations are performed rapidly. The disclosed method and apparatus finds application in, for example, scanning, copying, and facsimile transmission of large format documents.

Abstract: Method and apparatus facilitate alignment of a print image to a desired position. The print image includes a set of original linear groupings of pixels. A distortion of the print image is determined as compared to the desired position. Based on the determined distortion, a set of original linear groupings of pixels to warp is identified. A set of warped linear groupings of pixels is then generated, which correspond to the set of original groupings of pixels. A placement location in the print image for the warped linear groupings of pixels so generated is identified, and the print image is printed with the set of warped linear groupings of pixels.

Abstract: A system is provided for rapidly recognizing hand gestures for the control of computer graphics, in which image moment calculations are utilized to determine an overall equivalent rectangle corresponding to hand position, orientation and size, with size in one embodiment correlating to the width of the hand. In a further embodiment, a hole generated through the utilization of the touching of the forefinger with the thumb provides a special trigger gesture recognized through the corresponding hole in the binary representation of the hand. In a further embodiment, image moments of images of other objects are detected for controlling or directing onscreen images.

Abstract: The invention provides improved machine vision methods for determining a calibration relationship among the imaging reference frames of multiple cameras (or other image acquisition devices) that acquire images of a common moveable object. The calibration relationship includes parameters for transforming positional coordinates among the camera's respective imaging reference frames. The method includes placing on the common object, stage, or belt a plurality of fiducials, e.g., calibration marks, that are at known positions relative to each other with respect to a frame of reference referred to as the "alignment reference frame"; aligning an axis of the alignment reference frame with an axis of the object's reference frame of motion, i.e.

Abstract: A method of locating a machine-readable two dimensional marker, such as a barcode, in an image. An image of a medium containing the two dimensional marker is processed to generate a mask containing one or more filled regions each of which is sufficiently large to contain the predetermined dimensions of the marker. To generate the mask, small image areas having a first pixel polarity which are internal to larger image areas having a different pixel polarity are first filled with pixels having the same polarity as the surrounding larger image areas. A morphological opening operation is then performed on the filled image to leave only such filled regions as are equal in size or larger than the predetermined dimensions of the marker. After the mask has been generated, the mask is logically combined with the original image to extract one or more candidate regions.

Abstract: A method and system for compositing graphical images, wherein an advanced adjustment layer may be applied during a compositing process to a set of image layers 1 . . . n, or to any subordinate subset of such image layers. One or more adjustment layers are applied to an intermediate merged image, generated by compositing previous image layers, and the adjusted result is stored as a temporary image. The temporary image is then in turn composited with the intermediate merged image. Any remaining image layers are then composited in with the intermediate merged image to generate a final merged image. The invention allows a user to apply a vast array of effects without requiring significant new knowledge on the part of the user. For example, if there are "A" adjustments and "T" transfer modes, the present invention allows A.times.T effects which leverage existing knowledge of the user of only A+T functions.

Abstract: A method and apparatus uses naturally occurring object features as targets in a machine vision based robot (or other) guidance system. In one embodiment, a special high speed processor finds at least 3 pre-selected feature points on an object, which when considered with the data base for the object, allows a rapid 6 degree of freedom solution for the object location relative to the camera and thence connected automation. While primarily envisioned for industrial robots, the invention is useful for all sorts of machines including vehicles, construction machinery and the like--anywhere the target object has a known data base relative to the features in question.

Abstract: Disclosed is an image signal processing apparatus that accurately detect the position of a specific portion of an object to be sensed. The image signal processing apparatus is adapted for an image sensing apparatus having an image sensing device for sensing an image of an object together with a target having a plurality of colors of different hues to produce an image signal. The image signal processing apparatus includes a color difference signal generation circuit, a detection circuit and a determining circuit. A color difference signal generation circuit, connected to the image sensing device, receives the image signal and produces a color difference signal. The detection circuit, connected to the color difference signal generation circuit, receives the color difference signal to detect if the color difference signal lies in a level range previously set in accordance with individual colors, and produces detection signals corresponding to the colors based on a detection result.

Abstract: An image forming apparatus includes a moving member for conveying a recording member on which an image is to be formed, image forming units for forming marks for detection of a position of the image on the moving member, an illuminating device for illuminating the marks for detection of the position, which includes a LED light source, a detecting device for detecting the marks, and a control device for controlling the image forming units with detection signals detected by the detecting device.

Abstract: A wafer sorting system utilizing optical character recognition and optical "gate sensors" to determine the orientation of the wafers for prealigning. It is envisioned that the machine will be installed in conjunction with a computer controller and multiple cassette stations. A first end of a transfer arm of a robot is equipped with an end effector to transfer individual wafers. The end effector of the transfer arm is extendable and retractable to select and remove the desired wafer from its cassette, and to transfer it to the prealigner or a target cassette in its proper orientation. The end effector includes a vacuum pickup and a sensor that enables detection of presence or absence of wafers in the cassette, and any misaligned wafers in the cassette. Further gate sensors are mounted on the prealigner to accomplish the orientation function prior to the wafer being placed on the prealigner chuck. Multiple perimeter points are used to determine the position of the center of the wafer.

Abstract: A method for automatic merging two images having overlapped parts for a handy scanner. The method starts from defining a meaningful sample in a first image using fuzzy logic. Then, a two level searches based on A* algorithm are executed thereafter to find a match point in the second image. After the match point is found, the two images are stitched together using linear interpolation.

Abstract: An image processing system with a quality assurance feature is disclosed for determining the quality of the images being processed. The system includes a plurality of sections operating independently and concurrently to insure reliability. One section includes calculation of a quality assurance parameter dependent on the fill factor and the compression ratio determined before and after compression respectively. A second section includes histogram hardware for generating qualified histograms representative of foreground data, and background data transitions and a comparator for detecting overlap therebetween. A third section develops a histogram parameter based on the areas of the histograms and compares this parameter to the quality assurance parameter for concurrence. The system also includes autosizing means for detecting the borders of an image using fuzzy logic.

Abstract: An image pickup unit optically reads, from an information recording medium having a portion that records multimedia information including at least one of audio information, video information, and digital code data in the form of an optically readable code pattern, the code pattern. A conversion unit converts the code pattern read by the image pickup unit into code data as an image. A block extraction unit extracts a block as a predetermined data unit from the code data by processing the code data converted by the conversion unit. A reference coordinate calculation unit calculates a reference coordinate position for determining the data reading coordinate position in the block by approximation using an Nth-degree curve passing the centers of a plurality of dots arranged at predetermined relative positions on the image upon extraction of the block as the predetermined unit of data from the code data by the block extraction unit.

Abstract: In a document filing apparatus, a file memory previously stores a plurality of documents including of line data, character data and image data. An image input section inputs a new document as image data. A character-line extraction section extracts line data and character data from the input image data. A document retrieval section retrieves a document to be compared with the new document from the file memory. A difference detection section detects differences of line data, character data and image data between the new document and the retrieved document. A register section registers the difference data and identification information of the retrieved document as the new document in the file memory.

Abstract: A holder and a method of making an index print using the holder. The method comprising the steps of:1) providing a holder having at least one sleeve for holding a film, said film having at least one developed image therein;2) scanning the holder so as to obtain a digital record representative of the images present on said negative film; and3) printing the digital record so as to form an index print wherein said at least one image is placed in a predetermined pattern.

Abstract: A deflection device allows deflection correction control of suspended cargo for deflections having both parallel deflection and skew deflection components. The suspended cargo is held by a suspension tool suspended from a trolley via ropes and is carried together with movement of the trolley. The device has mark detectors provided under the trolley with a range of vision facing downwardly and a corresponding plurality of marks provided opposite of the mark detectors on the suspension tool. A picture processing device generates picture signals of the first and second marks detected by the mark detectors. A deviation amount computing device calculates the deviation of the first and second marks, and a deflection amount calculating device calculates the amount of parallel deflection and the amount of skew deflection based on the computed deviation amount.

Abstract: A series of documents to be processed are optically inspected, and compared with a reference standard to identify the relative orientation of each document. To this end, an image acquired from the document (preferably from each side of the document) is focused on an array of picture elements (pixels) for electronically converting the acquired image to digital form. This produces a digitally encoded image, which can be enhanced if desired, defined by an array of pixels corresponding to the acquired image. For each acquired image, two reference areas, which are preferably symmetrically located on the document, are inspected for the presence of a pre-selected reference mark. Location of the reference mark in one of the two reference areas operates to determine the orientation of the document.

Abstract: A method and apparatus to search, locate and inspect an object or characteristic of interest on a non-rigid package. First, a model of patterns of interest are stored to train the system with a model of the characteristics of interest. A minimum spanning forest (MSF) is generated defining the characteristics of interest as vertices with each vertex referencing a vertex closest to itself in order to minimize the sum of the distances between vertices in each minimum spanning tree (MST) of the MSF. At run time two coarse alignment features that the system has been trained to identify are located to determine rotation and coarse position of a non-rigid package being inspected. Local alignment then determines the exact position of local alignment points each of which is a starting vertex associated with one or more characteristics of interest as vertices in that starting vertexes MST.

Abstract: A scanner using a small, inexpensive CCD array for accurately and easily re-creating an error free reproduction of any scanned image wherein a plurality of laser alignment marks are temporarily projected, from an inexpensive solid state laser via a low cost plastic fiber optic cable, onto the surface of the document, and capturing the image as a number of small segments, along both the horizontal and vertical dimensions of the document onto the surface of the image being scanned. These temporary, projected, alignment marks permit the accurate positioning of adjacent, scanned segments during reconstruction of the scanned document. This scanner can scan documents of any width with an accuracy such that the scanned document can be readily, easily and accurately reassembled regardless of the insensitivity of, or misalignment of the scanning array in the apparatus or the skew of the document relative to the camera doing the scanning.

Abstract: A method for accurately determining a center of target marks provided on a workpiece. The method involves imaging, at an imaging station, a circular target mark associated with the workpiece. A signal produced by the imaging operation is binary-encoding, in an image processor, and displayed on a monitor screen connected to said image processor. Starting points X1 and X2 of a different level of intensity are detected by scanning in one of either an X-axis direction or a Y-axis direction on a center of a cursor (shown on the monitor screen) when the center of the cursor is within the target mark. Other starting points Y1 and Y2 of a different level of intensity are detected by scanning in another of the X-axis direction or the Y-axis direction on a mid-point of coordinates of the starting points X1 and X2.

Abstract: Fiduciary mark detection system usable with an over-the-belt optical character recognition (OCR) reader for ascertaining the position and orientation of text within the destination address on parcels moving along a conveyor, comprising charged coupled device (CCD) array, analog-to-digital (A/D) converter, general purpose computer, and software program. Image processing software program comprising projection histograms, convolution filtering, correlation, radial variance, first moments of inertia, edge image analysis, Hough method, detection confidence testing. Orientation defining mark comprising fluorescent ink placed approximately in the center of the destination address block on a parcel is non obstructive of the underlying text and may be affixed to parcel any time prior to scanning. Fiduciary mark comprising two circles of different diameter oriented such that a vector from the center of large circle to center of small circle is oriented in the same direction as underlying text.

Abstract: This invention is a mail address reading apparatus including a circuit for detecting image data of a mail, a circuit for detecting marks indicating the position of an address area from the image data, and a circuit for specifying the address area of the image data based on the position indicated by the marks and reading the address of the image data in the address area. In this apparatus, the address area can be specified by the detected mark position without causing any problem even if image information other than the address is present and the address can be correctly read.

Abstract: In an image forming device recognizing a specified area as a rectangular shape in an original image in which the area is specified by a frame indicated by use of a marker pen or the like, erroneous detection of a rectangular shape due to noise is prevented. Pixels having the halftone value in the image data are recognized as a frame and an area surrounded by the frame is defined by a rectangle and rectangle information thereof is provided. The size of the rectangle indicated by the rectangle information is determined, and if the size of the rectangle is smaller than a preset value, the rectangle information is eliminated as invalid information.

Abstract: A system and method for interactively creating forms including displaying the forms during creation, and interpreting completed forms received via a facsimile device. The system includes the following features: automated reminder, automated data export, suspense processing, and automated confirmation. Analog objects can be created and interpreted. Screen definitions for forms can be converted to the type of form defined by the present invention.

Abstract: Lithographic plates have an identifying folio and an image thereon. The image corresponds to a print image to be printed on sheet material such as newspaper stock. An image camera optically examines the identifying folios of each of the lithographic plates to ascertain folio information, and optically examines the images of each of the lithographic plates to ascertain image information including registration information and exposure information. A CPU records in an the electronic memory the ascertained folio information of the identifying folio of each lithographic plate and records in the electronic memory the corresponding ascertained image information of the image of each lithographic plate. An operator using a keyboard can access the image information of a particular plate recorded in the electronic memory by reference to the corresponding recorded folio information for the particular plate whereby the folio information and the image information are cross-referenced.

Abstract: An anti-counterfeit detector and method for identifying whether a platen image portion to be photocopied contains one or several pre-selected monetary note patterns. The detection is performed in a rotation and shift invariant manner. Specifically, the pattern can be of any orientation and at any location of the image. Moreover, it can be embedded in any complicated image background.

Abstract: A system and method are disclosed for locating an acquisition target consisting of a plurality of concentric rings of alternating levels of reflectivity (bull's-eye pattern) in two-dimensional images such as optically encoded symbologies. Such targets may be found even if they vary in size and tilt angle with respect to an imaging camera. Symmetry characteristics of the targets are used to locate the targets independent of the threshold level selected for determining transitions between rings of different reflectivity.

Abstract: An image processing apparatus includes an input unit for inputting images, and storage units for storing the images input from the input unit. The storage units store a plurality of images having common partial images. The apparatus further includes a determination unit for determining positions of the respective overlapped common partial images of the plurality of images stored in the storage units, a synthesis unit for forming an image by synthesizing the plurality of images according to a result of the determination by the determination unit, and an output unit for outputting the image synthesized by the synthesis unit.

Abstract: A checkered characteristic pattern is picked up by an image input device to form pick-up data. Characterizing points (intersecting points) are detected from the pick-up data. From the arrangement of the characterizing points about the center of the pattern and the positions of the characterizing points on the picture plane, a mapping function obtained when a TV camera is assumed to be a pin-hole camera is prepared. Reference positions of the characterizing points through the entire picture plane are calculated from the mapping function. The reference positions are compared with the actual positions on the picture plane to calculate a correcting function which in turn is stored in a correcting function preparing device. Normally, the inputted image is corrected by the correcting function and then outputted to an image output device.