Abstract: A pattern recognition procedure forms a hierarchical statistical model using a hidden Markov model and a coupled hidden Markov model. The hierarchical statistical model supports a pa 20 layer having multiple supernodes and a child layer having multiple nodes associated with each supernode of the parent layer. After training, the hierarchical statistical model uses observation vectors extracted from a data set to find a substantially optimal state sequence segmentation.

Abstract: A string extraction method for an image based on multiple stroke width patterns matching is provided. The string extraction method includes matching each possible stroke width pattern with an input image for obtaining the similarities between the width patterns and each pixel, wherein the integrated similarity between each pixel and the stroke width patterns is namely an integrated computing result of all similarities between the pixel and all stroke width patterns.

Abstract: A sweep-type fingerprint sensor module includes a microprocessor and a sweep-type fingerprint sensor, which includes a substrate, and a sensing members array, a speed-detecting unit, and a processing circuit on the substrate. The array is composed of plural fingerprint sensing members. When the finger sweeps across the fingerprint sensor, the array sequentially acquires plural fingerprint fragment images from the finger with a sampling time interval. The speed-detecting unit is composed of first and second plate electrodes. The processing circuit processes and then outputs signals from the array and the speed-detecting unit.

Abstract: A system and method for non-rigid image registration using distance functions includes portions for receiving a source shape into an image space, integrating a global linear registration model with local deformations to assess the source shape, optimizing a functional defined on a parameter or feature space where the functional quantifies the similarity between the source shape and a target shape in terms of distance functions, creating an augmented registration space including a plurality of target shape clones coherently positioned in the image space, tracking moving interfaces between the source shape and the target shapes and clones through a level set method, and registering the source shape by seeking mutual correspondences between the source shape, the target shape and the target shape clones.

Abstract: The present invention relates to an iris extraction method. In the method, two searching regions are defined in a face image. A deformable template match algorithm and an energy function are used to measure the energy of each pixel with different hypothetical circular templates within the searching region. Pixels with the same hypothetical radius having energies greater than a predetermined threshold are recorded as iris candidates, wherein the pixel having the maximal energy is recorded as first iris candidate. Further, it detects associated iris pairs from iris candidates in each searching region, records the lower iris candidate having the maximal energy of iris pairs as second iris candidate, and selects the best iris candidate from first iris candidate and second iris candidate. Finally, it designates the best iris candidate having the maximal energy of all best iris candidates with different hypothetical radius as the iris in the face image.

Abstract: A watermark embedding method based on DCT subband image characters is disclosed. An original image is converted into a frequency image using a discrete cosine transformation. The watermark information is then embedded into a specific embedding block in each macro-block of the frequency image. The method has the following advantages: (1) the image embedded by watermark is resistant from distortion and damages from compressions; (2) the watermark image can be extracted without employing the original image; and (3) the quality of the image embedded with the watermark image can remain intact.

Abstract: Apparatus and method for registration comprises a computer and a server in communication via a network, an intranet and/or the Internet, means for entry of data into the computer, and a signature or biometric digitizer including coupling software for directly entering digitized signature or biometric data electronically into the computer. The data and digitized signature or biometric data are communicated to the server. The registration apparatus and method may be utilized for voter or other registration and/or another transaction.

Abstract: A method renders a model of a 3D object. A polygon model of the 3D object is generated, and a set of input images are acquired of the object. For each vertex of the polygon model, a set of visible views are located, and a set of closest views are selected from the visibility views. Blending weights are determined for each closest view. Then, the each polygon in the model is rendered into an output image. The rendering is performed by blending images of the set of input images corresponding to the set of closest views of each vertex of the polygon using the blending weights.

Abstract: Disclosed is a method for obtaining an accurate detected value of a similarity between images or the like. Original standard and input pattern matrices, each having a feature quantity of an image as an element, are created (Sb1 and Sb3). A weighting vector having a value of a change rate of a kurtosis of a reference pattern vector composed of a reference shape as an element is created, and an original and weighted standard pattern matrix is calculated by a product-sum operation of an element value of the weighting vector and an element value of the original standard pattern matrix (Sb2).

Abstract: A method and apparatus for measuring the location of objects arranged on a convex surface. A plurality of cameras is arranged in a stationary array about the surface, and is used to capture images of the objects. A parameterized model of the surface is developed using optimization techniques, and then the locations of the objects are established by triangulation. The method is applied to location of electrophysiological sensors on the head, for purposes of electroencephalographic source analysis, or for registration with other imaging modalities such as MRI (magnetic resonance imaging).

Abstract: A method and an apparatus for decoding a progressive joint photographic experts group (JPEG) bit stream as image data indicative of an image are disclosed. The method includes the following steps. First, the data indicative of a scan of the JPEG bit stream are received. Second, the data indicative of the scan are divided into a plurality of regions. One of the regions is then selected as a decoding region. Next, after the data indicative of the scan are decoded, the decoded coefficients produced according to the data indicative of the decoding region of the scan, and the nonzero history of decoded coefficients of the other regions produced according to data indicative of the other regions of the scan are stored in the memory. Finally, the decoded coefficients of the decoding region are outputted so as to construct a portion of the image data.

Abstract: A method of approximating the boundary of an object in an image, the image being represented by a data set, the data set comprising a plurality of data elements, each data element having a data value corresponding to a feature of the image, the method comprising determining which one of a plurality of contours most closely matches the object boundary at least partially according to a divergence value for each contour, the divergence value being selected from the group consisting of Jensen-Shannon divergence and Jensen-Renyi divergence. Each contour Ci defines a zone ZIi and a zone ZOi, ZIi representing the data elements inside the contour and ZOi representing the data elements outside the contour, each zone having a corresponding probability distribution of data values for the data elements therein, and wherein the divergence value for each contour Ci represents a measure of the difference between the probability distributions for the zones ZIi and ZOi.

Abstract: An image system for processing image data in the form of grey-scale value signals and for generating an image that can be displayed on a presentation device, in particular for a medical diagnostic device, has a circuit to harmonize the image data. This circuit is fashioned for automatic contrast increase by a new adjustment of the grey-scale value signals, and thus of the grey-scale value dynamic range as well, with the C-value defining the center of the grey-scale value range, being retained after the harmonization.

Abstract: A method for qualitatively evaluating material with at least one identification characteristic, whose position can vary within an expectation range designated by tolerance limits, involves the use of at least one illuminating device, at least one photoelectric sensor and an evaluating device. At least one background reference value and at least one mask reference are stored in the evaluating device. The background reference represents the characteristics of a printed image, particularly the gray scale value, in at least one portion which surrounds the identification characteristic. The mask reference represents the geometrical contour of the identification characteristic. During inspection of the printed material, differential image data is found, at least from the expectation range, from the actual image data, and from the background reference value in the evaluating device. The actual position of the identification characteristic is subsequently derived in the evaluating device.

Abstract: A tracking apparatus including a sensor tracker and a control tracker (60). The sensor tracker is connected to a sensor which senses a scene having at least one object therein, the sensor tracker provides sensor movement instructions to the sensor, enabling it track a selected object. The control tracker is located remotely from and communicates with the sensor tracker. Additionally, the control tracker takes measurements regarding the selected object and provides tracking instructions to the sensor tracker. The sensor tracker then utilizes the tracking instructions to adjust the sensor movement instructions, when necessary.

Abstract: A tray is provided for positioning objects for digital analysis wherein the objects have two ends defining a length, two edges defining a width and two side surfaces defining a thickness, wherein the tray includes a support surface defined in a plane and having at least one edge pocket adapted to position an object with one of the two edges facing upward for obtaining an image depicting thickness and length of the object, and having at least one side pocket adapted to position an object with one of the two side surfaces facing upward for obtaining an image depicting width and length of the object.

Abstract: A system and method for facilitating low bandwidth video image transmission in video conferencing systems. A target is acquired (video image of a person's head) and processed to identify one or more sub-regions (e.g., background, eyes, mouth and head). The invention incorporates a fast feature matching methodology to match a current sub-region with previously stored sub-regions. If a match is found, an instruction is sent to the receiving computer to generate the next frame of video data from the previously stored blocks utilizing a texture synthesis technique. The invention is applicable for video conferencing in low bandwidth environments.

Abstract: The present invention utilizes generic and user-specific features of handwriting samples to provide adaptive handwriting recognition with a minimum level of user-specific enrollment data. By allowing generic and user-specific classifiers to facilitate in a recognition process, the features of a specific user's handwriting can be exploited to quickly ascertain characteristics of handwriting characters not yet entered by the user. Thus, new characters can be recognized without requiring a user to first enter that character as enrollment or “training” data. In one instance of the present invention, processing of generic features is accomplished by a generic classifier trained on multiple users. In another instance of the present invention, a user-specific classifier is employed to modify a generic classifier's classification as required to provide user-specific handwriting recognition.

Abstract: A location mark detecting method of a robot cleaner capable of accurately detecting location marks from an image captured by an upwardly looking camera. The location mark detecting method comprises the steps of obtaining from the image object marks to be compared with the reference location marks, determining whether shapes of the object marks are identical to those of the reference location marks, determining whether a distance separating the object marks is identical to that between the reference location marks if it is determined that the shapes are identical, determining whether a surrounding image of the object marks is identical to that of the reference location marks if it is determined that the distances are identical, and identifying the object marks as the location marks if it is determined that the surrounding images are identical.

Abstract: A method of recognizing an injury pattern on a fingerprint is disclosed. The method comprises the steps of providing biometric information to a contact imager; imaging and characterizing the biometric information; comparing an image of the biometric information against previously stored templates; upon a comparison result of the comparison, determining an injury pattern; wherein upon an injury pattern determination, performing a comparison against a stored template based on features extracted from the biometric data and the damage data.