Abstract: One embodiment of the present invention provides a system that uses directional weighting functions while computing optical flow for an image through belief propagation. The system operates by computing local velocity estimates for points in the image. The system also computes directional weighting functions for points in the image, wherein the directional weighting functions facilitate propagating information in a manner which can vary with direction. The system subsequently uses these directional weighting functions during a belief propagation process, which propagates the local velocity estimates between points in the image, and which computes an optical flow field for points in the image.

Abstract: The present invention is a method of optical character recognition. First, text is received. Next all words in the text are identified and associated with the appropriate line in the document. The directional derivative of the pixellation density function defining the text is then taken, and the highest value points for each word are identified from this equation. These highest value points are used to calculate a baseline for each word. A median anticipated baseline is also calculated and used to verify each baseline, which is corrected as necessary. Each word is then parsed into feature regions, and the features are identified through a series of complex analyses. After identifying the main features, outlying ornaments are identified and associated with appropriate features. The results are then compared to a database to identify the features and then displayed.

Abstract: An optical recognition device is provided. The optical recognition device includes a transparent substrate, a patterned infrared reflective film formed thereon, and an infrared anti-reflective film sheltering a gap in a recognition pattern of the patterned infrared reflective film, wherein the patterned infrared reflective film reflects the recognition pattern by reflection of infrared light and transmission of visible light. The invention also provides a display incorporating the optical recognition device.

Abstract: An automatic data collection device (10) and method reads images from display screen (22) of an electronic display device (24), such as a cellular telephone. The method reads a flashing image of a target machine-readable symbol (12) displayed on the display screen, by obtaining at least two images of the display screen. In the first image, the image of the target machine-readable symbol is present. In the second image, the image of the target machine-readable symbol (12) is absent. The second image of the display screen, when the image of the target machine-readable symbol is absent, comprises noise and other images that are irrelevant to the decoding process. This noise in the second image is subtracted from the first image of the display screen having the image of the target machine-readable symbol displayed thereon the symbol. A resulting image from the image subtraction is an improved image of the target machine-readable symbol.

Abstract: A test strip reader is provided with an optical mouse integrated circuit sensor that reads the test line, reference line and control line of a lateral flow assay strip by light absorption and determines the position of the test strip beneath the image on the integrated circuit board using digital signal processing algorithms. The digital signal processing algorithms process the imaged surface at a very high rate (e.g., 1500 frames per second) to determine the direction and speed of movement of the lateral strip with respect to the reader optics and image capture components. The sensor outputs this position information in a quadrature pattern format. A microcontroller uses the known position of the strip with respect to the reader to calculate the optical absorption of each colored reagent line, and the diagnostic significance (i.e., either qualitative or quantitative) of the test strip.

Abstract: An image processing program includes the first step (S101, S102) of acquiring the first parameter serving as a parameter associated with 3D display on the first 3D display device, and acquiring the first 3D image data corresponding to the first parameter, the second step (S103) of acquiring the second parameter serving as a parameter associated with 3D display on the second 3D display device, and the third step (S104) of generating the second 3D image data corresponding to the second parameter on the basis of the first 3D image, the first parameter, and the second parameter.

Abstract: An image sensing apparatus is configured such that the level of each of first and second output signals obtained by exposing a color image sensor by using mutually differing first and second photoelectric conversion properties is compared with one of threshold values to thereby select output signals to be used as signals for constituting an image from among the first and second output signals for individual color components thereof. The threshold values are set for the individual color components based on the first and second output signals.

Abstract: This invention comprises the means for the capture of full spectrum images in an electronic camera without the use of color primary filters to limit the spectral color gamut of the captured image. The fundamental principle of the invention is that each pixel of the image sensor acts as an independent spectrophotometer and spectral separator. Electromagnetic energy enters though a slit or collimating optic. Electromagnetic energy gets diffracted into component spectra by diffraction grating spectrophotometer for each pixel of image Electromagnetic energy leaves diffraction grating at different angles based on wavelength of the energy Spectrophotometer separates light for each pixel into its spectral components onto photodetector line array elements. Individual line array elements which are activated determine the original radiance level of the light source containing that specific wavelength region. The sum of these regions determines the spectral signature of the light at that pixel element.

Abstract: An information processing apparatus, an information processing method and a computer readable medium that analyze a character string and execute desired processing using a simple operation. A character string reading device reads the character string in an image photographed by a photographing device, a character string capture and analysis device identifies a type of information represented by the character string by capturing and analyzing the character string read by such character string reading device, and extracting information represented by the character string, and a display controlling device generates an analysis result screen including the type of the character string and the information obtained by such character string capture and analysis device and displaying the analysis result screen on a display.

Abstract: An optical scanner includes a housing and an intermediate member that includes a first joining surface and a second joining surface. The first joining surface is attached to the housing and the second joining surface is attached to at least one optical element of any one of a first optical system and a second optical system. In a three-dimensional coordinate in which a first one of coordinate axes is a direction that is parallel to both the first joining surface and the second joining surface, a second range on the first coordinate axis corresponding to the second joining surface includes a center point of a first range on the first coordinate axis corresponding to the first joining surface.

Abstract: When the user of a system directs an indicator toward a light-emitting section, an imaging section provided in the indicator acquires an image PA in a given area including the light-emitting section. A determination section determines whether or not each pixel individually satisfies a first condition based on light-reception information relating to each pixel of the image PA, and a calculation section calculates an indication position of the indicator based on the positions of effective pixels in the image using the effective pixels which satisfy the first condition as pixels corresponding to the light-emitting section. The calculation section calculates a representative value of the effective pixels based on identification information relating to the effective pixels while changing weighting on the identification information relating to the effective pixels depending on whether or not the effective pixels satisfy a second condition.

Abstract: A method of imaging a coding pattern disposed on a surface of a substrate. The method comprises the steps of: (a) positioning a nib of an optical reader on the surface and capturing an image of a portion of the coding pattern; (b) locating at least nine target elements in the imaged portion; (c) observing a perspective distortion of the target elements due to a 3D orientation of the reader relative to said surface; (d) calculating a 2D perspective transform using the target elements; and (e) determining a position of the nib on the surface using the 2D perspective transform and local tag data contained in the imaged portion. The imaged portion of the coding pattern has a diameter of at least one tag diameter and less than two tag diameters. The coding pattern is specially adapted for the method.

Abstract: A method of imaging a coding pattern disposed on a surface of a substrate. The method comprises the steps of: (a) operatively positioning an optical reader relative to the surface and capturing an image of a portion of the coding pattern; (b) sampling and decoding x-coordinate data and y-coordinate data within the imaged portion; and (c) determining a position of the pen. The coding is specially adapted to minimize space occupied by coordinate data. The imaged portion has a diameter of at least (l+q)?2 and less than (2 l)?2, where l is the length of a square tag in the coding pattern and q is the width of a central column or row of data within each tag.

Abstract: A method and system for nano-encoding and decoding information related to printed texts and images on paper and other surfaces is provided. The system and method includes a nano-encoder for encoding information related to printed texts and images; and then collocating the encoded information with the related printed texts and/or images. The system also includes a nano-decoder for decoding information encoded by the nano-encoder. The nano-decoder includes a text processing database having a translator database. The translator database includes a definition database; and a summary database. In addition, the system and method includes detecting luminescent nano particles and/or magnetic nano particles; and determining invariant properties of the detected nano particles. The invariant properties are then matched with coded information.

Abstract: An image sensor and a manufacturing method thereof are provided. The image sensor can include a lower layer on a substrate having a photodiode, a middle layer on the lower layer, and an upper layer on the middle layer. The middle layer can have a lower refractive index than the lower layer and the upper layer. The middle layer can also have stepped regions for filtering red, green, and blue light.

Abstract: Stored digital data is searched for on the basis of an input image, difference information is extracted by comparing the retrieved digital data and the input image, and the difference information is composited to the digital data. Digital data generated by composition is stored. When no digital data is retrieved, the input image is converted into vector data, and the image that has been converted into the vector data is stored as digital data. Obtained region segmentation information and an input image are composited, the composite image is displayed on an operation screen of an MFP, and a rectangular block to be vectorized is designated as a specific region from the displayed region segmentation information. A user designates the specific region by designating rectangular blocks in an image using a pointing device.

Abstract: A mobile robot for sensing and decoding a surface coding pattern on a surface includes a housing, A platform is in the housing. An on-board controller is mounted on the platform and configured for wireless communication with a host computer system. A differential drive system is mounted on the platform and connected to the controller so that the controller can steer the platform relative to the surface. An image sensor is mounted on the platform, arranged to sense the surface coding pattern and connected to the controller to communicate data representing the surface coding pattern to the host computer via the controller.

Abstract: A document image scanner; a camera having a field of view, for sensing differentiated information areas on each physical document as the physical document is transported; an image processing system associated with the camera, for producing a virtual image data file from the differentiated information areas sensed by the camera; sensors for determining the position of the physical document relative to the camera field of view; of electro-mechanical devices for actuating the transporter; and a data interface controller for receiving data from the sensors and controlling the electro-mechanical devices. A communications link is provided between the data interface controller and the image processing system for synchronization by the data interface controller, of the physical document as conveyed and the virtual document image captured by the image processing system.

Abstract: A system and method for determining the image resolution of a check image using MICR characters. The disclosed system includes an extracting system for extracting a magnetic ink code recognition (MICR) code line from the document image, wherein the extracting system provides coordinate values for each of a plurality of MICR characters in the MICR code line; a calculating system for calculating a set of resolution values based on the coordinate values of the MICR characters; and a statistical analysis system that calculates a representative resolution value from the set of resolution values.

Abstract: Provided are an optical vision chip (OVC) and an image recognition method using the OVC. The OVC includes: a first display displaying an object image; a second display displaying a standard model image; and an optical sensor optically or electrically coupling the object image and the standard model image respectively displayed on the first and second displays and outputting a difference between the object image and the standard model image as an electrical signal.

Abstract: The present invention relates generally to steganography and data hiding. One claim recites: a method including: at an Internet access point, obtaining data representing audio or video content, the data including a steganographic signal hidden therein, the steganographic signal being hidden in the data representing the audio or video content through alterations to the data; analyzing the date to obtain the steganographic signal; upon obtaining the steganographic signal, determining whether to allow the audio or video content to be communicated through the Internet access point based at least on the steganographic signal and data that is separate from the steganographic signal; and providing a report including details of said act of determining. Of course, other combinations are provided and claimed as well.

Abstract: Methods of organizing a series of sibling data entities in a digital computer are provided for preserving sibling ranking information associated with the sibling data entities and for attaching the sibling ranking information to a joint parent of the sibling data entities to facilitate on-demand generation of ranked parent candidates. A rollup function of the present invention builds a rollup matrix (126) that embodies information about the sibling entities and the sibling ranking information and provides a method for reading out the ranked parent candidates from the rollup matrix in order of their parent confidences (141). Parent confidences are based on the sibling ranking information, either alone or in combination with n-gram dictionary ranking or other ranking information.

Abstract: Generating an image includes receiving a light at sensors, where the light is associated with images. A previous matrix is determined, where the previous matrix includes image information associated with an image. For each sensor, a current image data corresponding to a current image is generated and a current matrix is determined using the previous matrix and the current image data. The current matrix includes image information associated with the current image. A fusion matrix is computed according to the current matrix of each sensor, where the fusion matrix initiates generation of a fused image.

Abstract: An image reading apparatus includes a casing, an upper plate and a transparent plate. The casing has a first opening, and a reading means is disposed in the casing. The upper casing plate is disposed over the casing and has a second opening that is positioned opposite the first opening. The transparent plate is mounted on the first opening. The transparent plate is wedged in the second opening through assembly of the casing and the upper plate.

Abstract: A system and method for detecting check fraud includes a check scanning module and a detection module. The check scanning module scans checks and matches the encoded Magnetic Ink Character Recognition (MICR) data (i.e. serial number, Customer Account Number and amount) from the scanned digital electronic images with items in an issuance database which contains client provided check particulars. The detection module passes the check images through an optical character recognition (OCR) process to read what is written on the check and to match results against the issuance database. If the written information on the face of a check is unreadable or there is no match with the information in the issuance database, the detection module passes the check through a series of slower more precise OCR processes. Any checks that are not successfully read and matched are highlighted as an “exception” and immediately forwarded to the client for further action.

Abstract: A meter is read. An image on a face of the meter is captured. Optical character recognition of digits of a digital display on the face of the meter is performed. At least one stored template is used to perform the optical character recognition of digits.

Abstract: An image processing method comprises forming a histogram of an entire image, determining a ratio between a reference luminance value and a reference threshold value at a maximum frequency, dividing the image into local areas, forming a histogram of each local area, determining a luminance value at a maximum frequency, multiplying this luminance value by the ratio between the reference luminance value and the reference threshold value to obtain a threshold value of the local area, and performing binarization for the local area using the threshold value. Therefore, it is possible to determine an appropriate threshold value in each local area of a multiple gray-level image, and obtain, using this threshold value, a binarized image which enables accurate separation of an object from a background.

Abstract: Methods and apparatuses for drawing and formatting an image are described. In at least one embodiment, when 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 several embodiments 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 is activated to treat the scanned image. Further, the format of the scanned image could be transformed by some applications such as the OCR.

Abstract: A method and system providing a transfer container crane with container code recognition of a container identified by a container code to a container inventory management system is disclosed. The system and method are capable of performing these tasks without the use of non-standard container tagging.

Abstract: A method for displaying a locus of positions on a map is disclosed. In the method, positions where images have been picked up by a digital camera device are determined based on characters included in the picked up images, and a locus of the determined positions of the images are displayed on a map to show a route in which the camera device has been transferred. Also, attributes of characters included in a picked up image are judged to decide whether the characters indicate a name of place or a station name, for example, and a map that matches the judgment is displayed. For example, a road map may be displayed when the characters are determined to indicate a name of place, and a railroad route map may be displayed when the characters are determined to indicate a station name. Furthermore, a position determined based on the characters may be displayed on the map that matches the attribute of the characters to show where in the map the image was picked up.

Abstract: A mobile device, system, method, and software for communicating with the internet utilizing a written universal resource locator (URL). A camera unit is used to receive a raw visual light image containing a written URL, the raw visual light image is converted to an electronic image, and the device locates glyphs of at least one particular standardized set of URL characters in the electronic image, for example glyphs corresponding to www. Then the URL characters are extracted from the electronic image, the URL is sent in a request signal to a web server, and in response an internet site is presented. The mobile device includes initiation means for sending an instruction to obtain a raw visual light image that includes glyphs of at least one particular set of characters, such as www, and further includes a camera, a display, and an internet interface. The mobile device processes an electronic image signal provided by the camera, in order to obtain the web site signal from the internet interface.

Abstract: A scanning device, a laser projector and an optical device that are capable of accomplishing a wide scanning area in a simple manner include a galvanomirror that is a scanning part scans a laser light in a two-dimensional direction. The laser light from the galvanomirror is incident on a scanning optical system. The scanning optical system includes a first lens group having a positive refracting power and a second lens group having the positive refracting power in this order from the scanning part. The galvanomirror is disposed in the vicinity of a focal position that is located at an incident side of the laser light of the first lens group. The first lens group and second lens group are disposed such that the focal position that is located at an exiting side of the laser light of the first lens group is approximately coincident with the focal position that is located at an incident side of the laser of the second lens group.

Abstract: For each paper type, a plurality of two-dimensional excitation characteristics tables Ti are provided in one to one correspondence with a plurality of colors i. The excitation characteristics table Ti for each color i contains a plurality of sets of excitation-reflectance data Bi (?0, ?) in a two-dimensional matrix form, for a plurality of combinations of incident light wavelengths ? and reflected light wavelengths ?0. The excitation-reflectance data Bi (?0, ?) indicates the ratio of the amount of the reflected light wavelength ?0 generated in response to incidence of the incident light wavelength ?, with respect to the amount of the incident light wavelength ?. Using the two-dimensional excitation characteristics table Ti corresponding to the user's selected paper type and using the spectral radiation characteristics S(?) of the user's selected light source type, Equations (9)-(11) are calculated to create an output profile, and color conversion is performed by using the output profile.

Abstract: An improved image data processing architecture utilizes a negotiation protocol with an information push technique to provide a more efficient and effective image data rendering pipeline. The improved image data processing architecture allows the optimization of data transfer through the use of image transfer parameters and flags. In another aspect of the invention, a selection mechanism is provided to allow a client application to easily select an image frame as the current frame in a multi-dimensional image. Image sinks within the invention may further support non-blocking behavior.

Abstract: An imaging system for reducing aberrations from an intervening medium, and an associated method of use are provided. The system may be an optical or task-based optical imaging system including optics, such as a phase mask, for imaging a wavefront of the system to an intermediate image and modifying phase of the wavefront such that an optical transfer function of the system is substantially invariant to focus-related aberrations from the medium. A detector detects the intermediate image, which is further processed by a decoder, removing phase effects from the optics and forming a final image substantially clear of the aberrations. Other systems may employ an encoder that codes wavefronts of acoustical waves propagating through a medium to make the wavefronts substantially invariant to acoustical aberrations from the medium. Imaging and decoding of the wavefronts reverse effects of the wavefront coding and produce sounds substantially free of the aberrations.

Abstract: An image processing apparatus captures a target image containing marker images and a recognition target range identified by a marker-image set including at least parts of the marker images. The image processing apparatus includes an image capturing section, a first detection section, a position estimation section and a second detection section. The first detection section detects one marker image as a reference marker image from a captured image. The position estimation section adopts a marker image, which is other than the reference marker image and is contained in at least one of marker-image sets containing the reference marker image, as a corresponding marker image. The position estimation section estimates a position of the corresponding marker image in the captured image based on a size of the detected reference marker image. The second detection section detects the corresponding marker image based on the estimated position of the corresponding marker image.

Abstract: An improved method and apparatus for discriminating between currency bills of different denominations uses an optical sensing and correlation technique based on the sensing of bill reflectance characteristics obtained by illuminating and scanning a bill along one of its dimensions. A series of detected reflectance signals are obtained by sampling and digitally processing, under microprocessor control, the reflected light at a plurality of predefined sample points as a currency bill is moved across an illuminated strip with a preselected dimension parallel to the direction of transport of the bill. The sample data is subjected to digital processing, including a normalizing process, whereby the reflectance data represents a characteristic pattern that is unique for a given bill denomination and incorporates sufficient distinguishing features between characteristic patterns for discriminating between different currency denominations.

Abstract: Apparatus and methods are disclosed for processing printed material to provide an index of locations within the printed material that can be associated with external actions such as displaying a graphical image, providing an audio or video output, or providing a multimedia output. The associations are stored in a database. Apparatus and methods are also disclosed that allow a user to image the printed material and by indicating a desired location within the printed material can cause one of the associated actions to be executed.

Abstract: The present invention relates to an image pre-processing method for a pattern detection system, such as a bar code detection system. The method comprises the steps of: detecting a start point and an end point of a pattern on the basis of image data of at least a portion of a captured image, estimating a point spread function from the image data or a modified image data on the basis of the detected start point and the end point, and restoring the image data or the modified image data using the estimated point spread function.

Abstract: A method for operating an optical sensor which has a light receptor that receives line-by-line reflected or returned light for a complete picture. At least some of the received pictures are compressed with a picture compression algorithm. To process the picture and more quickly store it in a memory-saving manner, the optoelectronic sensors compress the picture simultaneously with its receipt by the receptor. Optoelectronic sensors for use in this manner can be a code laser or a laser scanner for determining distance or generating separation pictures.

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: The invention relates to a method and a device for reading the addresses of mailings with an OCR device and a video coding device. On an ambiguous reading result from the OCR device an extract is automatically generated with specified extraction rules from address alternatives as a partial result of the OCR process and the number of concurrent or non-concurrent extracts determined. When the number of the address alternatives does not exceed a maximum value, an extraction coding with the specified extraction rules is carried out with predominantly or only different extracts and a selection coding, for the address alternatives transmitted to the video coding device with the image, is carried out with predominantly or only the same extracts.

Abstract: A user can enter handwritten electronic ink into a writing guide on an electronic page of an electronic tablet. An ink processing module can display the handwritten electronic ink as it is rendered on the electronic page by the user. Upon the occurrence of a predefined event, the writing guide module can automatically recognize and convert the electronic ink to text without the user's manual intervention. The writing guide module can replace the electronic ink in the writing guide with the converted text.

Abstract: Disclosed is an ink composition suitable for ink jet printing comprising a luminescent compound, a solvent, and an energy active compound, and optionally a non-luminescent colorant. The energy active compound, when exposed to energy, generates one or more active species that can react with the luminescent compound to alter one or more of the characteristics of the luminescent compound. The luminescent compound can be colored or colorless. Also disclosed is a method for marking substrates comprising providing a mark comprising a luminescent compound and an energy active compound. Further disclosed is a jet ink composition suitable for printing on substrates authentication or security marks which can be rendered unreadable. The luminescence of the mark is quenched and the visible color is changed when irradiated with a light.

Abstract: An image capture device electronically captures and selects a desired text portion. A visible light image is projected onto text on a document to enable a user to position the light image relative to the desired text portion. At least some of the text is captured in accordance with a position of the light image. A text selector selects the desired text portion from the captured text.

Abstract: The present invention relates to a method of processing postal matters in an automatic address-reading system, an image of the surface of each article of mail having address information being obtained and delivered to a first automatic evaluation system, and incorporately evaluated address information being delivered for evaluation to a first video coding system. It is provided that the address information of those images which have not been completely evaluated in the video coding system are delivered, using the results of the video coding system to another automatic evaluation system.

Abstract: A number of novel watermarking applications, and improvements to watermarking methods, are disclosed. Included are techniques for encoding printed circuit boards and street signs with watermarks, deterring credit card fraud and controlling software licensing using watermarks, registering collectibles via watermarks, encoding the margins of printed pages with watermarks, and using watermarks to convey extra information in video by which fidelity of the rendered video may be improved.One particular arrangement is a method in which a PDA, wristwatch, or other portable device with a display screen presents an image that depicts a proprietor of the device, and also includes a machine-readable identifier (e.g., a watermark or barcode). This image is sensed by a separate device, such as a webcam or a camera-equipped cell phone. The sensing device can then take an action based on the identifier (e.g., linking to an email account or to a web site that corresponds to the person depicted on the display screen).

Abstract: The present invention concerns an image processing apparatus and an image processing method, in which an edge coordinates extraction circuit is used to extract edge coordinates information for an input bitmap. By converting the bitmap image into vector data the edge coordinates information so extracted reduces the time required for raster-vector conversion.

Abstract: In order to segment a digital image of a postal packet in order to read a postal address (AP) automatically on said packet, the method consists: in subdividing (20) the image into image blocks of identical size; in applying (30) processing based on a Hough transform to each image block in order to identify in the image block in question a privileged direction for the distribution of image points in the block under consideration; in grouping together (40) contiguous image blocks within the image having a common privileged direction in order to define (50) a rectangular zone of interest (ZI) containing the group of said contiguous blocks having a common privileged direction in such a manner that said rectangular zone of interest has a longitudinal edge parallel to said common privileged direction; and in applying the automatic address-recognition algorithm to said zone of interest in the image in order to read a postal address automatically.

Abstract: An image analysis system for automated reading of printed multi-character codes, for example on antibiotic susceptibility testing disks, makes use of an orientation means, for example an underline printed beneath the code, to bring the code or its image into canonical alignment with an optimum reading direction for the code. Automated reading of the codes on randomly-orientated AST disks is therefore possible.