Abstract: A method to arbitrate between results obtained from observationally derived data by several procedures, where the results are items characteristic of the observationally derived data is disclosed. Each procedure is given a ranking according to the confidence on the procedure. The results and characteristics derived from the results are used in a plurality of rules, where the rules are used to arbitrate between the results.

Abstract: A user interface can display electronic ink in one section of a display device and corresponding recognized or converted text in another section of the display device that was generated from a electronic ink recognition system. Each page of electronic ink and each corresponding page of converted or recognized text are linked to one another. In other words, each page of electronic ink can be displayed only with its corresponding page of converted or recognized text until a command or message is received that editing of the converted or recognized text has been completed. Once the command or message is received that editing of the converted or recognized text has been completed, then the link between an electronic ink page and its corresponding converted text page is broken. This means that the converted text page can now be saved independently of its corresponding electronic ink page.

Abstract: A device and method for reading optical marks are disclosed. The device, an optical mark reader (OMR) has an array of photo sensors with light-emitting diodes (LEDs), which are driven by digital-to-analog converters (DACs), which are in turn controlled by a microcontroller. When calibrating the OMR, the sensors read a white card, and the microcontroller adjust the DACs so that the outputs of all sensors are at a voltage close to the saturation points of the photo-transistors in the sensors so that the maximum useable ranges of the sensors are utilized. The sensors then read one or more patterns of known grayscales and their response voltages are recorded. The microcontroller generates an array of voltage values as a function of grayscale for each sensor and store the values in a memory device. When reading an optical marks, the sensor output voltage in response to a mark is looked up in the table of voltages values stored in the memory device to determine the grayscale of the mark.

Abstract: A method and system for on-line resolving is described that dynamically provides resolvers with rules for evaluating answers to particular types of data items. Rules are stored which relate to procedures for evaluating the data items. When data items are displayed to a resolver for evaluating, the corresponding rules are displayed for evaluating the displayed data item.

Abstract: At least one beam emitted from a light source is deflected by a deflector, and the beam deflected by the deflector is imaged on a surface to be scanned by imaging optical system having a diffracting surface on at least one surface thereof. Of diffracted lights diffracted by the diffracting surface when the surface to be scanned is scanned by the beam, relative to diffracted light of an order used to form a spot on the surface to be scanned, the expanse of the stray light of one of unnecessary diffracted lights of the other orders undergoing surface-reflection by a refracting surface of the imaging optical system upon incidence on the surface to be scanned is designed to be wider in the sub-scanning direction than in the main scanning direction.

Abstract: An ultra-high speed image sensor is a frame transfer type. A charge corresponding to an intensity of a incident ray is generated at an element of a charge transfer path corresponding to each window. The generated charge is transferred on the charge transfer path by voltages applied from the charge transfer electrodes to. Each of the charge transfer electrodes to has a larger size in a charge transfer direction at portions corresponding to the window than that at portions covered with the intercepting film.

Abstract: An compact imaging apparatus having an OCT function is provided. An image formed of the illuminating-light reflected from a examination area is displayed on a monitor. A signal-light for obtaining an optical tomographic image is guided in a fiber through an insertion portion and projected onto a living tissue measurement area by an illuminating lens. The measurement area is scanned with the signal-light by a Piezo actuator moving the output face of the fiber. An OCT obtaining-portion obtains and displays on a monitor an optical tomographic image by using the interference caused by the signal-light reflected from the measurement area and a reference-light. By performing the scanning with the signal-light using an image-obtaining lens, the need to insert a probe for obtaining an optical tomographic image through a forceps port is eliminated. Therefore, the number of required forceps ports is reduced, and the insertion portion can be made thin.

Abstract: A parameter setting section sets a parameter stored beforehand in a parameter storage section as a parameter in an operation in an image pick-up section or an image processing section until an image pick-up start detection section detects an image pick-up start of a code. Moreover, when the image pick-up start detection section detects the image pick-up start of the code, the parameter setting section changes the parameter extracted from image information output from the image pick-up section or image information subjected to predetermined image processing in the image processing section from the parameter stored in the parameter storage section.

Abstract: According to the present invention, the recorded images with image-accompanying data of the postal articles or documents to be read of different customers are furnished. For each customer, master data are stored in a searchable manner. The master data includes at least the origin of the images, the range of the agreed services and, in a cost model, includes their costs according to established image attributes. Before each reading process, the respective customer and the respective reading job including the necessary image attributes are determined from the image-accompanying data are determined from the image-accompanying data and from the master data. After conducting the reading process, the customer, the procesing information concerning the reading steps with the reading and processing results, the established image attributes and the image-accompanying data are stored for each image in a searchable, sortable and time-related manner.

Abstract: A method for increasing the speed at which data items are processed. The method receives electronic representation of data items and organizes the data items into separate groupings. The method next displays a particular grouping of data items to a resolver so that the resolver can evaluate the data items. In displaying the data items, the method uses a matrix of cells and displays one data item in each of the cells. The resolver can thus simultaneously view multiple data items, which facilitates efficient evaluations of the data items.

Abstract: A method and system for automated sorting machines is provided in which a feedback between OCR and ABL takes place. According to a first aspect of the present invention, a loose coupling between ABL and OCR is proposed in which the ABL system is asked for a further address block potentially present on the letter's surface when the first one being passed from ABL to OCR yielded that no destination ZIP code could be extracted from it. The confidence of the actual OCR and the ABL result, the address block contents supplemented with some additional criteria based on general knowledge, further, the sort plan actually loaded on the concerned sorting machine and the postmark information found in the stamps of the postmark can advantageously be used to make the ABL restart decision. Further, the ABL system can continue to search further address blocks while the OCR system processes one or a plurality of address blocks being passed to it from ABL in a preceding procedure related to the same letter.

Abstract: A method and apparatus creates a reduced-resolution version of an image and uses the reduced resolution version to identify recognition parameters. The recognition parameters are then used on the original version of the image to recognize objects such as characters in the image.

Abstract: A method and system for processing groupings of data items. Data items are received in electronic form, after which the data items are divided according to predefined categories and organized into separate groupings. The data items in the groupings are reported.

Abstract: The present invention employs an instruction button for inputting an instruction to simultaneously executing registration, in a full-text-search database, of a document scanned by one scanning operation and subjected to OCR processing, and registration of the document in a designated folder contained in a database of a folder tree structure. This single instruction button enables the user to simultaneously register read images in a folder, and text data resulting from OCR processing executed on the read images.

Abstract: In an optical data reader, light is aimed out through a window at objects located in front of the window, and reflections from the objects and/or the window itself are detected. The amount of detected light is compared to one or more expected levels to determine when an object is present in front of the window and/or whether the window is properly installed. The optical reader is controlled based on this determination. Control functions that may be implemented in this manner include, for example, waking up the data reader when an object is detected in front of the glass, and disabling the data reader if the window is removed.

Abstract: By printing documents and other objects with machine readable indicia, such as steganographic digital watermarks or barcodes, a great variety of document management functions can be enabled. The indicia can be added as part of the printing process (after document data has been output by an originating application program), such as by printer driver software, by a Postscript engine in a printer, etc. The indicia can encode data about the document, or can encode an identifier that references a database record containing such data. By showing the printed document to a computer device with a suitable optical input device (e.g., a webcam), an electronic version of the document can be recalled for editing, or other responsive action can be taken.

Abstract: A general document recognition system is described which is intended to be used in connection with an electronic document transmission function used on a computer network. The general document recognition system is set up to recognize any number of document types created by application programs in the network and is also set up with rules as to how to extract destination data from each document type. The extracted data from each document can be the actual intended destination, such as a facsimile telephone number, or can be the identity of the intended recipient individual. If a recipient, rather than a destination, is extracted from the document, the general document recognition system can query a previously designated external database to recover the destination information for that recipient. An LDAP database is the preferred external database for this function.

Abstract: A digital camera takes photographs of printed material upon recognition of a specified text pattern. In one exemplary embodiment of the present invention, the process of photographing printed material based on text pattern recognition is partially manual. In a second embodiment of the present invention, the process is highly automated.

Abstract: A system and method for using specially printed paper and a handheld device to supplement, or replace, large displays and user interfaces commonly required for efficient use of computing devices. The paper is encoded with location information and a message. The message is distributed redundantly across the page, may be arbitrarily large, and may contain security information. In one embodiment, the device uses a single sensor to read the encoded message and location information, and to measure the relative motion of the device. After scanning the specially printed paper, a user may then raise the device, place it on any convenient flat surface, and continue to slide, exploring areas outside of the printed copy.

Abstract: A method and system is disclosed for facilitating the input of information into a computing device by a scanning means. A pocket scanner that has only the minimum components/parts therein and will not operate without being connected to the computing device that subsequently receives scanning signals therefrom. In particular, the disclosed scanner does not have a separate power supply to energize the components/parts to work.

Abstract: The method for evaluating schlieren in glassy or crystalline optical materials includes irradiating a test sample of the optical material with light and producing a shadow image of the test sample on a projection screen. The shadow image of the test sample is received in an electronic image receiving device, such as a digital camera, and is compared with another shadow image of schlieren obtained with a comparison sample by means of interferometry. Then the optical material of the test sample is evaluated with the help of the comparison results.

Abstract: The reading results of an agreed number of images of items, achieved by the OCR reader, are temporarily stored subdivided into reading results which are read unambiguously and reading results which are rejected. Then classes of words or word groups belonging together of the reading results temporarily stored and rejected, consisting in each case of n address words, n=1, 2, . . . , a, with interword gaps m, m=0, 1, . . . b are formed which do not drop below a particular similarity factor referred to in each case a particular n and m value between them. In the dictionary or dictionaries of the associated address areas, representatives, at least, of the classes whose frequency exceeds a predetermined value are included.

Abstract: The developmental potential of a mammalian oocyte for successful implantation is evaluated by producing a plurality of intensity images of the oocyte using polarized light optics, and calculating a retardance image with a sensitivity of 3 nm or less. The presence, location and morphological characteristics of a meiotic spindle in the oocyte can then be determined based on the spindle structure in the retardance image, and the developmental potential of the oocyte can be evaluated.

Abstract: An oscillating microscopic or tomographic optical input image is directed at a tunable Bragg cell and a tuning control device applies a fluctuating AC hetrodyne signal to the cell, such signal having a phase locked template with respect to oscillation of the optical image, causing the cell to hetrodyne and correlate a phase locked matching template with the oscillating optical input image. A time integrating detector integrates output signals from the Bragg cell while illuminated point sources of the optical image are interconnected with corresponding imaging points upon the integrating detector via a high resolution holographic lens array within the Bragg cell. The array consists of recorded interference patterns between tiny one micron point sources of light produced by an optical fiber with broad wave fronts of light. A DC signal applied to the Bragg cell along with the AC signal enables beneficial wavelength discrimination and averaging.

Abstract: A video microscopic visualization system and image processing and data extraction and processing method for in situ detailed quantification of the deposition of sub-micrometer particles onto an arbitrary surface and determination of their concentration across the bulk suspension. The extracted data includes (a) surface concentration and flux of deposited, attached and detached colloids, (b) surface concentration and flux of arriving and departing colloids, (c) distribution of colloids in the bulk suspension in the direction perpendicular to the deposition surface, and (d) spatial and temporal distributions of deposited colloids.

Abstract: An image reading device reads an image of an electronic part as an image pickup object with camera 8 having a line sensor. The line sensor comprises a plurality of pixels having a photoelectric transfer element arranged in series. The image reading device selects pixels periodically one by one and outputs image signals. The pixels for outputting image signals are set based on width data of an image pickup area stored on image pickup area storage 10. The image reading device monitors a relative positional relation between the image pickup object and the line sensor using a pulse of encoder 4A, and controls writing of the image signal into an image storage 15 with a storage controller 12 based on length data of the image pickup area. This process can remove uselessness of outputting the image signal from an unnecessary range and storing it, and improve efficient image reading.

Abstract: A method and system provides computerized high-rate image processing. Each detecting element receives electromagnetic radiation and produces an electrical detection signal according to an amount of electromagnetic radiation received on the respective detecting element. The electrical detection signals of each detection element corresponding to an assigned region of interest in the field of view. The electrical detection signals of all detecting elements assigned to the same region of interest are summed to produce an output signal.

Abstract: An image reader includes a transparent plate (1) having end portions (1a and 1b) that are chamfered in a direction in which a document is carried thereon. The transparent plate (1) has recess portions (11aand 11b) formed in a lower surface thereof, and a housing (4) is engaged into the recess portions of the transparent plate. The image reader can prevent such a document as a check or banknote from being jammed, can be easily assembled and improve the reliability of the carrying of the document, and enables higher-speed reading.

Abstract: A storage system is provided for paper and electronic documents. Electronic documents include electronic image documents and electronic work documents, which may be completely unrelated in form or content, are acquired or produced to provide one or more real time sequences of electronic documents in one or more real time sequences of date/time instances. Acquired or produced physical documents, for ultimate convenience, simply are added to the front (or the back) of one or more cumulative physical stack. The resulting electronic records of a database, with assured precision, uniquely identify the physical locations of the physical documents and the electronic locations of the electronic documents, both in terms of their associated date/time instances. In effect, these date/time instances guarantee that virtual sets of related physical documents may be conveniently accessed and physically retrieved, and that corresponding sets of related electronic documents may be immediately displayed and suitably presented.

Abstract: By scanning both sides of a photographic print, data from the back of the print may be associated with the image. If the backside data includes text, optical character recognition (OCR) techniques optionally may be used to convert the image of the back of the photo into text that may be included in a database or other data structure allowing the text to be associated with the photographic image. This allows the user to quickly and easily search a large database of images for either a specific image or a group of images according to some set of search criteria.

Abstract: An image sensing apparatus has an optical lens system and a color image sensing device. The optical lens system forms an image on the color image sensing device by means of light from an illuminated subject. The color image sensing device is a charge coupled device which has a plurality of pixels. The apparatus fulfills the conditions: 1.5×p×FNo.<|LBg−LBe|<5.0×p×FNo. 1.5×p×FNo.<|LBc−LBe|<5.0×p×FNo. where p is a predetermined pitch of a photoelectrically converted pixel of said color image sensing device, LBe is a paraxial back Ad focal length of an e-line (546.07 nm in wavelength), LBg is a paraxial back focal length of a g-line (435.84 nm in wavelength), LBc is a paraxial back focal length of a C-line (656.28 nm in wavelength), and FNo. is an F-number of said optical lens.

Abstract: A document handling system is configured for processing a variety of different documents. The system includes an input receptacle for receiving a stack of documents, a standard sensor for scanning at least one non-color characteristic of the bills in the stack, a color sensor for scanning the color characteristics of the bills, and an output receptacle for receiving the bills after they have been processed. A transport mechanism is included for transporting bills, one at a time, from the input receptacle past the sensors to the output receptacle. An operator interface is provided for displaying information to an operator and inputting information to the system. A processor is also included for processing the data gathered from the sensors to evaluate the bills.

Abstract: Method and Device for drawing and formatting an image. Whenever a user prepares to use an application, or a file, to treat the scanned image of an object, the user only needs to place the object on a scanner and to select the icon of the application, or the file, and compile it with the icon of the scanner. The utilization of the present invention will automatically drive the driver of the scanner and integrate the relative information into the driver. Thus, after the scanned image is acquired, the application, or relative application of the file, is automatically active to treat the scanned image. Further, the format of the scanned image could be transformed by some applications such as the OCR.

Abstract: A handheld device scans a line of information in the form of Internet URL's, Internet protocol addresses, Internet e-mail addresses, FTP sites, USENET news group addresses, DNS addresses and bar codes as they occur in print advertising and printed media. The scanned information is decoded and displayed for user verification. The device utilizes onboard information retrieval software that establishes a connection to the Internet to retrieve HTML, XML, WML, and VRML documents, e-mail messages, USENET news, Java applets, ActiveX documents, Active Server Pages, or file transfers from the Internet locations interpreted by the handheld scanner.

Abstract: A method for optical part shape measurement of a bare metal part to determine acceptability of the manufactured part. A variable level light source illuminates the part which is mounted on positioning equipment that allows the part to be moved from one position to another. Localized variations in light level are first determined and are compared with a reflectivity model of the part to determine optimization of the setup. Light level and viewing orientation of the part are adjusted to optimize the quality of test data obtained. Data quality is reviewed to ascertain a confidence factor for each location on the part's surface. Using both the reflectivity model and quality test results, data acquired for specified areas of the part is either accepted or rejected. Light level and part orientation are changed based upon how a reflectivity map of the part changes with each adjustment. New and acceptable data are now acquired for those areas of the part where data was previously discarded.

Abstract: An imaging system includes two sets of cameras: a first set for capturing optical mark or optical character recognition data and a second set for capturing visual images. Full visual images of pages containing answers to open-ended questions are retained and are retrievable by a reader such that an area of interest wherein the answer is expected is displayed, but the remaining area is also available for viewing. The system permits the alignment of a page based upon edge detection if the page contains only an open-ended answer, obviating the need for timing tracks. Hardware and software elements cooperate to store the image temporarily in a server having a response time commensurate with the scanner. The image is then processed with the use of high-performance index imaging for optical storage and retrieval, and then routed to a long-term storage device.

Abstract: A user interface can display electronic ink in one section of a display device and corresponding recognized or converted text in another section of the display device that was generated from a electronic ink recognition system. Each page of electronic ink and each corresponding page of converted or recognized text are linked to one another. In other words, each page of electronic ink can be displayed only with its corresponding page of converted or recognized text until a command or message is received that editing of the converted or recognized text has been completed. Once the command or message is received that editing of the converted or recognized text has been completed, then the link between an electronic ink page and its corresponding converted text page is broken. This means that the converted text page can now be saved independently of its corresponding electronic ink page.

Abstract: The present invention pertains to a method and device for recognizing distribution data on postal packets, small packages or journals during the automatic mail processing, especially to systems by which the automatic handwritten adress recognition process is supplemented and improved by video coding. The distribution data are written on various backgrounds, including pattern backgrounds. After a first unsuccessful optical character recognition attempt, the complete surface of the postal packet is displayed with a grid on a videocoding-screen. Once a picture segment has been selected which contains a larger part of the distribution data, the operator submits an image portion containing said picture segment and the adjacent areas to a new optical character assessment, while making sure that all the data area is included in the image portion.

Abstract: Cross correlation between a reference image frame and a comparison image frame determine the direction of motion relative to x and y orthogonal axes for a pointing device that uses optical imaging to monitor movement relative to a surface. Pixel data for a portion of the surface are loaded into a buffer memory that shifts the data between successive positions in the buffer memory as each pixel of a comparison frame is processed to compute cross correlation. Auto correlation is determined for positions in the reference frame and used with the cross correlation results to determine a sub-pixel interpolation for the movement of the pointing device. A new reference frame is loaded using data for the comparison frame currently being processed if the pointing device is moved sufficiently so that the next comparison frame will not overlap the existing reference frame.

Abstract: A method for searching for a query word in a database of automatically recognized text generated, for example by an optical character recognition (OCR) system or a speech recognition (SR) system finds entries that most closely match the query word. The database is indexed into a trie data structure, which represents all possible words in the database. The trie data structure has a plurality of branch nodes, each representing a letter of at least one word, and a plurality of leaf nodes, each representing a respective word. The trie data structure is searched for each query word by selecting the first letter of the query word and also selecting a root node in the trie data structure as the current node. All possible child nodes of the current node are identified. Respective estimated probability values for matching respective letters of the query word with the letters associated with the nodes in the path taken through the trie data structure are calculated for each identified child node.

Abstract: An image processing technique for selecting a text region from an image is described. Character and formatting information for each word in the image is used to determine an active region for each word in the image. For a preferred embodiment of the present invention, the character and formatting information is derived during optical character recognition (OCR). A first and last word within a selected text region is identified based on at least one active region associated with at least one word within the selected text region. Using the first and last words within the selected text region, all words within the selected text region are identified. An image of the selected text region may be displayed. Text contained within the selected text region may be copied to an application program.

Abstract: An apparatus and method capable of verifying a scanned image utilizing a verification algorithm based on a topological analysis of the scanned image and an apparatus and method capable of verifying a scanned image utilizing a verification algorithm based on an improved bi-level separation analysis incorporating an anti-stroke scoring method with a character outlining method.

Abstract: A messaging device has a message reception component configured to receive a printable message from a message originator, and a printer that prints the received message and that also prints an origin identifier of the message originator on the print medium. After the message is printed, a user marks it up for reply to the message originator. The messaging device has an optical scanner and optical recognition logic that detects the origin identifier and that instructs the messaging device to send the annotated message back to the message originator. In addition, the optical recognition logic recognizes instructions written on handwritten cover sheets. By preparing such a cover sheet with handwritten instructions, a user can instruct the message device regarding various transmission parameters such as recipients and recipients' telephone or facsimile numbers.

Abstract: In one embodiment, a scanner is provided having inter alia an optical zoom system, which includes a movable lens assembly and a rotatable mirror. The image to be scanned, the optical zoom system and the scanning head are located along an optical axis. The optical resolution of the image is variable by selectively displacing the lens assembly along the optical axis while simultaneously rotating the rotatable mirror about its center. In a further embodiment, a scanner is provided having inter alia a variable aperture for controlling the infiltration of stray light in a scanner having a plurality of optical resolutions.

Abstract: An adjustment system for a plate-like member includes a cam member formed with an appropriate cam curve in contact with front or rear surface of, for example, a reflector installed in an optical scanner to reflect a scanning beam of an optical scanner so that a reflecting direction of this reflector may be adjustably varied by rotating the cam member and optical and scanning characteristics of the optical scanner may be ensured.

Abstract: A system for automatically routing data captured by multifunctioning devices, such as scanners through speech and voice recognition. After capturing an image or document with the device, speech disposition commands are made by a user speaking into a voice pickup component in the device to control the disposition of the captured image or document. The user uses the commands to program various tasks and operations and build more powerful commands. The system executes and learns commands with multitasking. As one of the tasks, the system has a training function which can be used to prompt for additional information for incomplete commands. The system keeps previously performed commands and can use these commands for parameters to complete an incomplete command.

Abstract: An optical character recognition (OCR) system is provided, in which syntactical and semantic rules, provided along with an input image to be scanned and applicable to the contents of the scanned image, are used in connection with the results of the OCR scan to identify the scanned characters. As a result, the recognition rate and confidence are enhanced. By providing the checking based on syntactical and semantic rules within the OCR system, application programs which would receive and use the OCR results are freed from the added burden of having to perform their own syntactical and/or semantic checking on the OCR results the application programs receive from the OCR system.

Abstract: The present invention relates to an image input device including a substrate, a light sensor, a light emitter, and a light guide. The light sensor, the light emitter, and the light guide are provided on the substrate. The light emitted from the light emitter is guided to a position above the light sensor by the light guide.

Abstract: An imaging engine includes a plurality of linear imaging arrays, image formation optics, at least one illumination module and supporting circuitry that are embodied within a modular engine housing. The plurality of linear imaging arrays and image formation optics are mounted on an optical bench (which is integral to the engine housing) and provide field of views corresponding to the plurality of linear image arrays. The at least one illumination module produces planar light illumination that substantially overlaps the field of views corresponding to the plurality of linear imaging arrays.

Abstract: A system and a method for converting markings made on media with a marking agent into a digital form representing the markings. The system of the present invention includes a marking device and an illumination digital scanning device. The marking device can be a manual or machine marking device, each containing the marking agent. The marking agent is dispensed by the marking device onto the media. The marking agent is a chemical that emits a certain radiation frequency set when illuminated by an illumination frequency set. The illumination digital scanning device converts the markings of the marking agent into a digital form. The method of the present invention includes marking the media with the marking agent, illuminating the markings to cause the marking agent to radiate at the radiation frequency set and converting the radiation into a digital form representing the markings.