Abstract: Methods, systems and user interfaces for providing feedback to a user based on recognition of character-based ink input are provided. A first feedback is provided to the user to indicate a character as which ink input by the user is recognized. The first feedback is displayed in proximity to the displayed input ink so that the user knows to which ink character the first feedback corresponds. A second feedback may optionally also be provided indicating a correctness of the recognized ink input, as compared to a predefined correct value such as a correct word game solution or answer, by displaying the input ink in one format to indicate that the recognized value is correct, and by displaying the input ink in a second format to indicate that the recognized value is incorrect.

Abstract: A digital image processing method for determining an orientation of a face in a digital color image generates a mean grid pattern element image from a plurality of sample face images and an integral image from the digital color image. A face is located in the color digital image by using the integral image to perform a correlation test between the mean grid pattern element image and the digital color image at a plurality of effective resolutions by reducing the digital color image to a plurality of grid pattern element images at different effective resolutions and correlating the mean grid pattern element image with the plurality of grid pattern element images, whereby either the mean grid pattern element image or the grid pattern element images are provided at a plurality of different orientations. Accordingly, an orientation of the face in the color digital image is determined by using the images with different orientations in the correlation test.

Abstract: Techniques and tools for spatial extrapolation of pixel values in intraframe video encoding and/or decoding are described. For example, to predict the pixel values for a block of pixels, a video encoder or decoder uses spatial extrapolation from the pixel values of pixels in a causal neighborhood for the block of pixels.

Abstract: A user's handwritten signature data is transmitted to a host device, when the user registers his or her signature. A signature information controlling unit reads the codes of a character string of a font closest to handwriting shape data by referencing a signature dictionary information unit, extracts a predetermined number of digits of numeric values from the codes, generates a user ID by making the numeric values successive to the number of codes, and registers this user ID and the input handwritten signature to the signature dictionary information unit by making a correspondence between them. When a signature is authenticated, a user ID is automatically generated from a handwritten signature input by a user, and checked between generated user ID and registered user ID.

Abstract: The present invention includes a method for analyzing an image wherein elements defining a path within a two-dimensional image are received from a prescreener. A Sobel operator may be applied to the region around each of the elements of the chain to obtain a corresponding array of gradient directions. An angle correction may be applied to any of the gradient directions that goes beyond the highest value (in radian measure; the Pi ?Pi transition), to obtain an array of gradient directions free of any artificial jumps in value. The gradient direction array (Sobel chaincode) can have its bandwidth taken to determine a single number of straightness so as to identify extremely straight edges, (manmade objects) from less straight edges (natural objects). A similar process can be used to analyze contours for straight sections, which are also parallel. These two and other filters applied to the gradient array can be part of a feature suite, for feature space analysis.

Abstract: There is provided a stereoscopic image forming apparatus which can reduce the image memory capacity and the time required for synthesizing a three-dimensional striped image. A three-dimensional image is synthesized such that pixels of the same coordinates in respective images of a multiple viewpoint image sequence of the subject viewed from a plurality of viewpoints are arranged as adjacent pixels in accordance with the arrangement of the viewpoints of the images based on the acquired subject image and an acquired parallax map corresponding thereto. Pixels values of the subject image corresponding to the respective pixels of the three-dimensional image are found according to a parallax deviation derived from the corresponding parallax map and are written into the respective pixels of the three-dimensional image. The synthesized three-dimensional image is outputted, whereby a stereoscopic image can be observed through an optical member having a cyclic structure superposed on the outputted image.

Abstract: A method and computer program product are disclosed for generating training data over a plurality of feature variables for a new output class in a pattern recognition classifier representing a plurality of existing classes with previously calculated statistical parameters. Deviation measures are generated for each feature variable for each of the plurality of existing classes from the calculated statistical parameters. The deviation measures for each feature variable are averaged across the plurality of existing classes. Feature data is extracted from an ideal pattern, representing the new class, for each of the feature variables. Statistical parameters are approximated for each feature variable for the new class from the extracted feature data and the averaged deviation measures.

Abstract: An electronic device stores a plurality of user's fingerprints in such a manner that each of a plurality of functions is stored in correspondence to any one of the fingerprints. Every time before using a function, the electronic device recognizes a user using a fingerprint corresponding to the function. For example, when the right thumb, right index finger and right middle finger are respectively stored in correspondence to an individual recognition function, imaging execution function and copy quantity setting function, at least three fingerprints are checked while the user is recognized by the electronic device, the copy quantity is set and imaging is accomplished. In such a manner that a user is multiply identified by a plurality of fingerprints during using the electronic device, the accuracy in recognizing a user and security can be enhanced with the structure as simple as the conventional one.

Abstract: An image super resolution system computes a high resolution image of a target from multiple low resolution images of the same target. Each low resolution image differs slightly in perspective from each of the other low resolution images. A coarse registration operation determines initial estimates of registration parameters (e.g., representing shifts and rotation in perspective) associated with each low resolution image. A fine registration operation improves the initial estimates using Bayesian analysis to infer the registration parameters and an acuity parameter. As such, a marginal likelihood of the low resolution images is optimized to determine the improved estimates of the registration parameters and the acuity parameter, which are used to solve for the high resolution image.

Abstract: A personal authentication system of this invention has a card reader, in which a bar code reading device for reading a two-dimensional barcode containing personal data, a CMOS image sensor for producing face data by photographing the face of a person, and a fingerprint reading device for producing fingerprint data by reading the fingerprint of the person are assembled as one unit. A personal computer performs a projection transform and a brightness correction to the barcode read by the card reader for acquiring accurate data. Then, the personal data, the face data, and the fingerprint data are compared with database for authenticating the person. Therefore, this invention achieves more accurate personal authentication and leads to improved security.

Abstract: An encoder (103) encodes image data using a first parameter Q1, and a re-encoder (107) re-encodes the encoded result of the encoder (103) using a second parameter Q2. When the encoded data size obtained by the encoder (103) exceeds a predetermined size, Q1 is replaced by Q2, and encoded data streams previously encoded by the re-encoder (107) are saved in a buffer (108) as those encoded by the encoder (103) after the parameter is changed. Upon executing a re-encoding process, the re-encoder (107) re-encodes encoded data streams previously encoded by the re-encoder (107) using a parameter that can assure a higher compression ratio than Q2.

Abstract: Computer-based methods and systems for automatically determining convergence when registering image sets are provided. Example embodiments provide an Enhanced Image Registration System (EIRS), which includes an Image Comparison Module, a Transformation Optimizer, and a Convergence Calculator. When the EIRS receives two image sets to align, the Image Comparison Module compares two image sets to determine or measure how closely the image sets are aligned. The Transformation Optimizer determines an appropriate transformation to apply to one of the image sets to align it with the reference image set. The Transformation Optimizer then applies the determined transformation. The Convergence Calculator examines one or more points within the transformed image set to determine when convergence is attained.

Abstract: A method and workstation for producing a combined image, including information from first and second diagnostic images, identify areas of increased uptake in the second diagnostic image as a region of interest which contains pixels representing the areas of increased uptake. The areas of increased uptake in second diagnostic image are mapped onto equivalent areas in the first diagnostic image using a deviation value calculated from a difference of a first peak position and a second peak position of pixel values of said pixels. The first peak position is a first significant peak of intensity values of the pixels and has a first intensity value, and the second peak position corresponds to a second intensity value which is half the first intensity value.

Abstract: Techniques for generating a fully-textured 3D model of a human face are disclosed. According to one aspect of the present invention, a fully automatic system is configured to generate a 3-D model from a sequence of images that are produced from a single camera when a user is moving his/her head steadily from one direction to another, for example, from the left side of the camera to the right side of the camera. The images are processed in a two-stage process. First, the camera pose information is estimated for each of the valid image frames. Second, a mesh model is generated with respect to the camera pose information, and subsequently is textured with reference to one or more of the image frames.

Abstract: A method discovers patterns in unknown multi-dimensional data. A time-series of the multi-dimensional data is generated and a point cross-distance matrix is constructed by self-correlating the time-series. All minimum cost paths in the point cross-distance matrix are located at multiple time resolutions. The minimum cost paths are then related to temporal sub-sequences in the multi-dimensional data to discover high-level patterns in the unknown multi-dimensional data.

Abstract: A character recognition method is provided, in which the method includes the steps of: picking up images in a motion picture by changing brightness for each image; extracting a character area from each image; recognizing at least one character in the character area by performing a matching process between the character area and dictionary images for each image, and determining a character recognition result for each image; and selecting a final character recognition result of which the matching degree is the highest from the character recognition results of the images. Accordingly, even when a character is too dark to recognize due to shadows in the daytime or a character is too bright to recognize due to irradiation in the nighttime, the character can be recognized by using images having differing brightness.

Abstract: A system and a method for minutiae record matching is claimed that includes the processing a first plurality of ordered minutiae match values with weighting values corresponding to a function of at least the number of minutiae in the corresponding latent print and the corresponding print in the tenprint for a given unweighted match value to define a second plurality of weighted match values. The second plurality of weighted match values may be further normalized based at least on the highest unweighted match value to generated a third plurality of weighted match values.

Abstract: During registration, an iris image taken is frequency-analyzed using a plurality of frequencies f1 to fn to generate features for the respective frequencies f1 to fn. During authentication, frequencies f2 to fn are selected from the frequencies f1 to fn for use in frequency analysis for authentication. An iris image of a person to be authenticated taken is frequency-analyzed using the selected frequencies f2 to fn to generate features for the respective frequencies f2 to fn. The generated features are compared with the features generated for the same frequencies during the registration to perform personal authentication.

Abstract: A plurality of document definition information for identifying documents, and format control information for recognizing a character recorded on a document corresponding to each of the plurality of document definition information are held beforehand, documents targeted for character recognition are identified as specific documents based on document images of the entered documents targeted for character recognition and the document definition information and, based on a result of the identification, character recognition is executed by using corresponding format control information. A document definition device adds a plane area of each of documents to be identified to the document definition. An OCR device checks the plane area on the document by using the document definition before check of a preprint accompanied by character recognition.

Abstract: A method and computer program product are disclosed for recognizing italic text in an optical character recognition system. A plurality of digital images of alphanumeric characters are created from a block of text, each comprising a plurality of rows of digital pixels. The digital images are preprocessed such that each image is normalized to equal size and the pixels within each image have a first value, such as “black,” or a second value, such as “white.” The position of the left-most pixel with a first value in each row is determined for each image. The position of each left-most pixel with a first value is recorded as an ordered pair including the row number and ordinal position within the row. A best-fit line and a corresponding slope are calculated for the ordered pairs via linear regression. The calculated slope is then compared to a predetermined threshold.