Abstract: In an apparatus for online signature verification, a signature data input unit digitalizes a locus of a user signature and reads the locus as a sequence of points. A first and a second pattern transform unit performs a speed equalization and a velocity transform on the signature sequence and generates a first and a second transformed pattern sequence, respectively. A characteristics extraction unit extracts three characteristics vectors from the signature sequence, the first and the second transformed pattern sequence, respectively, to thereby generate the three characteristics vectors. A difference vector estimation unit generates a difference vector. A determination unit determines whether an input signature and the reference signature are signed by a single person.

Abstract: A method and apparatus for reconstruction of a region of interest (ROI) for an object using an imaging system is provided. The imaging system may substantially exactly reconstruct the ROI with a straight line trajectory. In the straight line trajectory, the ROI is not bounded or encircled by the actual trajectory of the source (e.g., no chords that are composed from two points on the source trajectory intersect or fill the ROI to be imaged). However, the ROI may be substantially reconstructed by using “virtual” chords to reconstruct the ROI. The virtual chords are such that no point on the trajectory is included in the virtual chord (such as one that is parallel to the straight line trajectory). These virtual chords may intersect and fill the ROI, thus enabling substantially exact reconstruction. Further, in reconstructing the image, the straight line trajectory may be assumed to be infinite in length.

Abstract: A method and system for detecting the corners of a region in an image.

Abstract: A method and apparatus for reconstruction of a region of interest for an object is provided. The reconstruction of the object may be based on chords which may fill a part, all, or more than all of the region of interest. Using chords for reconstruction may allow for reducing data acquired and/or processing for reconstructing a substantially exact image of the ROI. Moreover, various methodologies may be used in reconstructing the image, such as backprojection-filtration, and modified filtration backprojection.

Abstract: According to this invention, a fingerprint sensor is mounted for fingerprint collation, and a movable protection unit which coverts the fingerprint sensor is arranged. In fingerprint authentication, the protection unit moves to expose the fingerprint sensor. Along with movement, the apparatus is powered on and activated, and the fingerprint sensor also operates to perform collation processing. The protection unit which covers the fingerprint sensor in normal use is formed by a member capable of handwriting input. This arrangement provides an information terminal apparatus which has a collation function and enables handwriting input.

Abstract: Features of a mouth in a current image of a sequence of digital images of a human face may be estimated by deriving a deformable mouth model template in an iterative process. The process may include minimizing an energy function receiving iteration-dependent arguments to determine optimal transformation parameters of an iteration-dependent transformation, and transforming components of the deformable mouth model template by the iteration-dependent transformation having the optimal transformation parameters. The deformable mouth model template is initialized more than once during the process. The deformable mouth model template may include modeling of teeth.

Abstract: A method of improving a digital color image having pixels, the method includes identifying pixels from the digital color image representing one or more sky regions; detecting sky occlusion regions by examining the sky regions; developing a model based on the identified sky pixels, wherein such model is a mathematical function that has inputs of pixel position and outputs of color; and using the model to operate on the digital color image to replace the values of pixels from the sky occlusion regions with values predicted by the model.

Abstract: A method for identifying of tokens in a video sequence is described. First, the video sequence is scanned for boundaries between consecutive parts of the sequence where the appearance of the tokens is expected. After that step, candidate regions are pre-selected and classified in parts of the video sequence adjacent to detected boundaries, and tokens are located in the candidate regions. Information carried on the tokens is located, interpreted, and merged into consistent sets of information after passing a confidence analysis. In parallel a change in the visual appearance of a token, signaling a special event, is detected.

Abstract: A method for finding the optimal threshold for image segmentation in image recognition is disclosed. The method includes the steps of: a) gaining histogram distribution of an image; b) computing entropy values corresponding to gray levels in the histogram; and c) gaining a minimum entropy value corresponding to the gray level as the threshold value by using a fixed point iteration FPI based on the computed entropy values.

Abstract: When an image inputted is displayed on the display, determined is an enhancing degree as a parameter for enhancing the sharpness of the input image by using at least one of information about a subject included in the input image and information about the display for displaying the input image. By using the enhancing degree determined, color distribution is controlled on a first principal component analysis axis obtained by analysis based on a principal component analysis in a color space. Furthermore, the texture of the subject is magnified in size and again mapped onto the subject. Due to this, the input image can be enhancement-processed to a well texture feeling easy to view.

Abstract: Systems and methods are provided for excluding extraneous image features from inspection operations in a machine vision inspection system. The method identifies extraneous features that are close to image features to be inspected. No image modifications are performed on the “non-excluded” image features to be inspected. A video tool region of interest provided by a user interface of the vision system can encompass both the feature to be inspected and the extraneous features, making the video tool easy to use. The extraneous feature excluding operations are concentrated in the region of interest. The user interface for the video tool may operate similarly whether there are extraneous features in the region of interest, or not. The invention is of particular use when inspecting flat panel display screen masks having occluded features that are to be inspected.

Abstract: A method, apparatus, and article of manufacture provides the ability to process image data. Image data is output as picture screen elements to a display. In response to selecting a sample of the picture screen elements, a reference co-ordinate system is generated. The reference co-ordinate system is used to process each of the picture screen elements. An axis of the reference co-ordinate system defines a distance. The picture screen elements are discriminated and processed according to the distance by proportionally averaging the co-ordinates.

Abstract: A system and method for detecting a passing vehicle is disclosed. A video sequence comprising a plurality of image frames is received. Image intensity is measured and image motion is estimated in each image frame. A hypothesis model describing background dynamics is formulated. The measured image intensity and motion estimation is used to determine if the background dynamics has been violated in a given image frame. If the background dynamics has been violated, motion coherency is used to determine whether the violation of the background dynamics is caused by a passing vehicle.