Abstract: An overlapped handwriting input method, which includes: moving a touch unit on a touch screen, recording and displaying the track of a stroke on a handwriting area of the screen; determining whether the stroke currently being written and all previously input strokes having a color A belong to the same character; if yes, keeping the current stroke color unchanged; otherwise, determining whether an inactive visual layer character is present on the screen; if yes, clearing an image of the inactive character and related stroke information; otherwise, defining as the inactive character all strokes having the color A, excluding the current stroke; submitting data of the current inactive character to a recognition engine, and outputting a recognition result. Thus, the interface friendliness for users to continuously input handwriting according to their natural writing practice is ensured, and multiple handwritten characters can be written continuously without pause, thereby improving handwriting input efficiency.

Abstract: A method for authenticating biometric data determines a first set of descriptors of a fingerprint. Each descriptor in the first set represents a region of the fingerprint that includes multiple minutiae. The method compares each descriptor in the first set of descriptors with each descriptor in a second set of descriptors to determine a number of matching descriptors and compares the number of matching descriptors with a threshold for authenticating the biometric data.

Abstract: The invention relates to the use of diffusion kurtosis imaging (DKI) in the diagnosis of Parkinson Disease related neurodegenerative disorders, including (but not limited to) Parkinson's disease (PD) and Parkinson plus syndromes.

Abstract: A method includes extracting a fully sampled fixed kVp sinogram for a pre-determined kVp of interest from an under-sampled mixed kVp sinogram generated from a switched kVp computed tomography scan. A system includes a fixed sinogram extractor that extracts a fully sampled fixed kVp sinogram from an under-sampled mixed kVp sinogram from a switched kVp computed tomography scan. A method includes de-noising at least one of a fully sampled fixed kVp sinogram extracted from an under-sampled mixed kVp sinogram or the under-sampled mixed kVp sinogram by smoothing lower kVp measurements of the sinograms and sharpening higher kVp measurements of the sinograms.

Abstract: An image processing apparatus includes: an enlarging unit that enlarges target data by using an enlargement factor based on an optimal sample number indicating a quantity of samples per unit length suitable for an image processing process; a decomposing unit that generates a group of data satisfying the optimal sample number by performing a decomposing process realized by a multi-resolution analysis on the enlarged data; a data processing unit that generates an already-processed group of data by performing the image processing process on the group of data satisfying the optimal sample number; a reconstructing unit that generates reconstructed data by performing a reconstructing process realized by a multi-resolution analysis on the already-processed group of data; and a reducing unit that reduces the reconstructed data in such a manner that the quantity of samples per unit length becomes equal to the quantity of samples per unit length in the target data.

Abstract: Evaluating an image is disclosed. A plurality of attributes of the image is analyzed. A determination is made that a portion of the attributes of the image imperfectly matches a reference attribute signature corresponding to a device. It is distinguished whether the imperfect match likely corresponds to a modification of the image.

Abstract: The PMP Growth algorithm described herein provides for image tracking, segmentation and processing in environments where the camera system moves around a great deal, i.e., causing image jumps from one image frame to the next. It also is operative in systems where the objects themselves are making quick movements that alter their path. Attributes of the PMP Growth algorithm allow tracking systems using the PMP Growth algorithm to follow objects a long distance in a scene. This detection and tracking method is designed to track objects within a sequence of video image frames, and includes detecting keypoints in a current image frame of the video image frames, assigning local appearance features to the detected keypoints, establishing Point-Motion-Pairs between two successive image frames of the video image frames, and accumulating additional matches between image locations to form complete coherent motion object models of the objects being tracked.

Abstract: The present invention relates to a method and device for obtaining an image of a crumpled document from an image of this document when it is crumpled. The method comprises a step of determining a three-dimensional geometric model of the surface of the crumpled document by triangulation of three-dimensional points defined from the pattern of a target extracted from the image of this document when it is crumpled; the method is characterized in that it comprises a step of determining a projection of the three-dimensional geometric model onto a so-called acquisition plane, by means of error minimization of this projection under constraints of preserving defined geometric characteristics in the vicinity of the three-dimensional points, and in that it comprises a step of superimposing the textures associated with the three-dimensional model onto the projection of this model thus determined.

Abstract: The invention relates to an imaging apparatus for imaging an object of interest. An analytical reconstruction unit (12) analytically reconstructs an analytical image of the object from detection data, in particular, from projection data, and an iterative reconstruction unit (13) iteratively reconstructs an iterative image of the object from the detection data, wherein a combination unit (14) combines the analytical image and the iterative image for generating a combination image. An iterative image can comprises shading artifacts, which may be caused by preprocessing the detection data before performing the iterative reconstruction. An analytical image shows reduced shading artifacts, in particular, shows no shading artifacts at all. Thus, by combining the analytical image and the iterative image a combination image can be generated, in which the shading artifacts are reduced in comparison to an iterative image, thereby improving the quality of the reconstructed final image of the object of interest.

Abstract: A method and system for stereo correspondence. The method for stereo correspondence includes a matching cost computation step, a cost aggregation step, a disparity computation step, and a disparity optimization step. The matching cost computation step acquires a left disparity space image and a right disparity space image by using horizontal gradients and vertical gradients of intensities of all component channels of every pixel in a left image and a right image. Utilizing the invention, accurate disparity maps may be acquired quickly.

Abstract: A method and apparatus for determining position and orientation enabling navigation of an object using image data from at least a first and a second 2D image from at least one camera mounted on said object. The method comprises the steps of: correcting images from one or several cameras and from at least a first and a second 2D image for their respective radial distortion and other measurable effects which result in poor image precision; matching 2D image items in and between at least a first and second 2D image; calculating a fundamental matrix by using correlated image points from at least a first and a second 2D image; calculating and extracting estimated first rotation and translation values from the fundamental matrix using single value decomposition (SVD) based on information from at least a first and a second 2D image; iterating more accurate final rotation and translation values by using the LevenBerg-Marquard algorithm and determining the position and orientation of said object.

Abstract: A method for inspecting tire tread, having circumferentially juxtaposed elements separated by identically shaped boundaries and having patterns arranged in a predetermined sequence, includes: acquiring an image of a surface of the tire tread, the image including pixels associated with a light-intensity level; transforming the image by circumferentially offsetting pixels located axially at a same distance (x1, x2) from a given circumferential reference (OY), by an inverse (?y1, ?y2) of a circumferential offset (y1, y2) with respect to an axial line (OX) of a point (P1, P2) located on a boundary line of known shape at the same axial distance (x1, x2) from the circumferential reference (OY), such that boundaries between elements appear as straight traces orientated in an axial direction; and analyzing the image to identify points located on an axially orientated straight line, the points being treated as points located on a boundary line between two elements.

Abstract: A tire tread, having circumferentially juxtaposed elements separated from one another by identically shaped boundaries and having a least one basic pattern, is inspected by: producing an image of the tire tread; identifying tread wear indicators on the image; grouping together sub-sets of the indicators according to the basic pattern(s) included in the indicators; determining a characteristic point of each of the sub-sets of the indicators; determining a sequence of distances by computing distances between the characteristics points of each of the sub-sets of the indicators; comparing and the sequence of distances with a known sequence of distances between characteristic points of the basic pattern(s) to confirm coincidence thereof; and projecting a shape of a boundary between elements of the tire tread onto a surface to be inspected according to the known sequence of distances between characteristic points of the basic pattern(s).

Abstract: One exemplary embodiment involves identifying feature matches between each of a plurality of object images and a test image, each feature matches between a feature of a respective object image and a matching feature of the test image, wherein there is a spatial relationship between each respective object image feature and a test image feature, and wherein the object depicted in the test image comprises a plurality of attributes. Additionally, the embodiment involves estimating, for each attribute in the test image, an attribute value based at least in part on information stored in a metadata associated with each of the object images.

Abstract: Provide is a process monitoring device in a semiconductor manufacturing apparatus that can readily and reliably monitor the process in the semiconductor manufacturing apparatus. The process monitoring device includes a storage unit that stores a normal state moving image data indicating a normal state of the process; an image capturing unit that captures an image of a state of the process to be monitored to acquire a moving image data; an abnormality level calculation unit configured to extract a feature amount for each frame of the moving image data and the normal state moving image data, and calculate an abnormality level based on the extracted feature amount; and a display unit that displays the abnormality level calculated by the abnormality level calculation unit in association with a frame position of the moving image data.

Abstract: Methods, systems, and devices for up-scaling a source input video from a lower, first resolution to a desired output video having a higher, second resolution, using fractal zooming techniques to replace each individual source pixel of each respective frame of the source input video with a multiple of proposed replacement pixels in the vertical and horizontal dimensions having similar characteristics as the individual source pixel, reducing noise associated with each respective frame of the desired output video, re-sizing, as necessary, each respective replacement frame to the second resolution, and outputting each zoomed replacement frame to generate the desired output video having a higher, second resolution, which is the up-scaled version of the source video. The fractal zooming techniques include identifying a plurality of candidate pixels from the source video and selecting a group of pixels from the candidate pixels that best matches the individual source pixel.

Abstract: Methods and apparatuses for compressive sensing that enable efficient recovery of features in an input signal based on acquiring a few measurements corresponding to the input signal. One method of compressive sensing includes folding an image to generate first and second folds, and recovering a feature of the image based on the first and second folds without reconstructing the image. One example of a compressive sensing apparatus includes a lens, a focal plane array coupled to the lens and configured to generate first and second folds based on the image, and a decoder configured to receive the first and second folds and to recover a feature of the image without reconstructing the image. The feature may be a local geometric feature or a corner. Compressive sensing methods and apparatuses for determining translation and rotation between two images are also disclosed.

Abstract: A method for providing hand detection may include receiving feature transformed image data for a series of image frames, determining asymmetric difference data indicative of differences between feature transformed image data of a plurality of frames of the series of image frames and a reference frame, and determining a target area based on an intersection of the asymmetric difference data. An apparatus and computer program product corresponding to the method are also provided.

Abstract: Various embodiments are directed to generating video data using temporally offset image data samples having disparate exposure times. Synthetic samples are generated for each of the pixels at a particular time period by computing, for each synthetic sample, a combined intensity of the captured samples that fall within the time period. Synthetic samples from adjacent pixels are grouped and image data in different groups is compared to identify matching groups. Video frames are constructed by combining image data from the captured samples based upon the matched images.

Abstract: Methods for inspecting a wafer and/or predicting one or more characteristics of a device being formed on a wafer are provided. One method includes acquiring images for multiple die printed on a wafer, each of which is printed by performing a double patterning lithography process on the wafer and which include two or more die printed at nominal values of overlay for the double patterning lithography process and one or more die printed at modulated values of the overlay; comparing the images acquired for the multiple die printed at the nominal values to the images acquired for the multiple die printed at the modulated values; and detecting defects in the multiple die printed at the modulated values based on results of the comparing step.