Abstract: Systems and techniques for performing resolution enhancement on target patterns based on holographic imaging technique (HIT) are described. During operation, an electronic design automation (EDA) tool can compute an in-line hologram of the target patterns based on parameters associated with a photolithography process that is used in a semiconductor manufacturing process, wherein the semiconductor manufacturing process is to be used for printing the target patterns on a semiconductor wafer. Next, the EDA tool can determine the mask patterns based on the in-line hologram.

Abstract: The invention provides a method for processing input image data by an image processing device, to reach a desired visual effect within an output image, wherein input image data are stored within an input memory device and the input image data are transferred based on data of a lookup table into respective output image data stored within an output memory device, the lookup table being generated based on at least one data remapping function to reach the desired visual effect, wherein further the entries within the lookup table are arranged in such a way that when processing the lookup table the input memory device is addressed in a sequential reading order; a computer readable medium having stored thereon program code to carry out the inventive method as well as an image processing device to carry out the method.

Abstract: Generation of a plurality of orthomosaic image layers for a geographical area, wherein the layers comprise different spatial resolutions and are radiometrically normalized to facilitate improved radiometric consistency when zooming relative to the geographic area. In applications that facilitate zooming with respect to a geographic area imaged by the orthomosaic layers, radiometric normalization of the orthomosaic image layers may reduce radiometric discontinuities when zooming in, zooming out, and/or panning a displayed portion that is output to the user. The orthomosaic layers may be generated based on one or more orthomosaic image layer or may be developed independently using a source images. In any regard, the radiometric normalization may include generating a normalization function based on image metadata that is calculated and may be independent of the spatial resolution of the image.

Abstract: Some embodiments are directed to a system and a method for estimating gaze from a set of eye measurement points that are indicative of a gaze pattern of a user viewing a scene. Some other embodiments are directed to obtaining sets of eye measurement points from different users viewing the same scene. In another embodiment, the different sets of eye measurement points are mapped to a common coordinate system for reciprocal calibration In yet another embodiment, a scene transformation for mapping the common coordinate system to a coordinate system associated with the scene can be calculated by matching eye measurement points from the common coordinate system to interest points of the scene. The scene transformation is thereby calculated more accurately than individually calculated scene transformations, thereby providing a more accurate estimate of the gaze points.

Abstract: Methods and apparatuses are provided for capturing an image in a portable terminal. An image is received at the portable terminal. An eye region is detected in the image. An eye center of the eye region is determined. It is determined whether a reflection region is detected in the eye region. When the reflection region is detected, a shape of the reflection region is determined, and guide information for preventing the reflection region is output based on the shape of the reflection region.

Abstract: A method of estimating a time to collision (TTC) of a vehicle with an object comprising: acquiring a plurality of images of the object; and determining a TTC from the images that is responsive to a relative velocity and relative acceleration between the vehicle and the object.

Abstract: A face comparison device according to the present invention includes: an occluded-feature point estimation unit that estimates an occluded-feature point that is a feature point of an invisible face, and outputs position information of the occluded-feature point; a pseudo-feature point estimation unit that estimates a pseudo-feature point that is an erroneously detected feature point not captured within the input image due to occlusion, and outputs position information of the pseudo-feature point; and a comparison unit that generates a normalized image of the input image by using the position information of the occluded-feature point and the pseudo-feature point, generates a normalized image of an acquired comparison image, and compares the first facial feature vector extracted from the normalized image of the input image and the second facial feature vector extracted from the generated normalized image of the comparison image.

Abstract: In part, the invention relates to processing, tracking and registering angiography images and elements in such images relative to images from an intravascular imaging modality such as, for example, optical coherence tomography (OCT). Registration between such imaging modalities is facilitated by tracking of a marker of the intravascular imaging probe performed on the angiography images obtained during a pullback. Further, detecting and tracking vessel centerlines is used to perform a continuous registration between OCT and angiography images in one embodiment.

Abstract: A method and system for automated decision support for treatment planning of arterial stenoses is disclosed. A set of stenotic lesions is identified in a patient's coronary arteries from medical image data of the patient. A plurality of treatment options are generated for the set of stenotic lesions, wherein each of the plurality of treatment options corresponds to a stenting configuration in which one or more of the stenotic lesions are stented. For each of the plurality of treatment options, predicted hemodynamic metrics for the set of stenotic lesions resulting from the stenting configuration corresponding to that treatment option are calculated.

Abstract: The present disclosures relates to finding or localizing machine readable indicia (e.g., a barcode or digital watermark) in imagery. One claim recites an apparatus comprising: memory for buffering blocks of image data, the image data having been captured with a camera and depicting a printed object; one or more processors programmed for: generating an edge orientation sensitive feature set from the image data; using a first trained classifier to determine whether the feature set includes data representing a barcode; and using N additional trained classifiers to determine an orientation angle associated with the barcode, wherein N comprises an integer greater than 3, and wherein the orientation angle is selected based on a probability metric. Of course, other claims and combinations are provided too.

Abstract: Apparatus and methods for dynamical tracking of movement of cells and cell groups within cell populations using magnetic resonance imaging are provided.

Abstract: A method for proactively creating a photobook includes identifying a group of images by a computer system and automatically creating a design for a photobook by the computer system without receiving a user's request for designing a photobook if the number of images in the group is determined to be within a predetermined range. Pages of the photobook incorporate a plurality of images in the group. The method further includes presenting the design of the photobook to a user for preview and receiving an order from the user for a physical manifestation of the photobook based on the design.

Abstract: Systems and methods for assisting a physician in a medical intervention comprises performing a 2D-3D deformable registration, and more particularly, performing a 2D-3D registration based on multiple live 2D fluoroscopic views, and implemented on a multi-core processing framework such as a Graphics Processing Unit.

Abstract: Systems and methods are described that provide a fast and simple way of processing meat or food products. Information is compiled and analyzed regarding the condition of a carcass, meat product, styling of the meat product and associated tray or package. Information is used in various processes, including determining which further processing steps are required. The information is also stored for future reference and analysis.

Abstract: The present application discloses a user information extraction method and a user information extraction apparatus. The method comprises: acquiring an image comprising at least one digital watermark; acquiring user related information corresponding to a user and comprised in the at least one digital watermark in the image; and projecting the user related information to a fundus of the user. In the present application, user related information used in a certain scenario is extracted in the corresponding scenario and projected onto a fundus of a user, and therefore, the user does not need to memorize the user related information, thereby avoiding inconvenience caused when the user forgets the user related information.

Abstract: A method and apparatus for motion determination comprising generating a hash value for each changed pixel in a frame of an image display sequence, the changed pixels indicated in a set of sparse display coordinates, for each changed pixel, overwriting (X, Y) information at a position in a symbol table indexed by the hash value, the (X, Y) information comprising one display coordinate associated with the each changed pixel, generating motion vectors for a frame, each motion vector specifying a pixel area determined from at least one (X, Y) delta between one of the changed pixels represented in the symbol table and a previously changed pixel represented at the position in a previous frame symbol table for a previous frame in the image display sequence, and transmitting the motion vectors from the host computer over a network to a client computer.

Abstract: A system and method for imaging a tooth. The method illuminates the tooth and acquires reflectance image data and illuminates the tooth and acquires fluorescence image data from the tooth. The acquired reflectance and fluorescence image data for the tooth are aligned to form aligned reflectance and fluorescence image data. For one or more pixels of the aligned reflectance and fluorescence image data, at least one feature vector is generated, having data derived from one or both of the aligned reflectance and fluorescence image data. The aligned reflectance and fluorescence image data and the at least one feature vector are processed using one or more trained classifiers obtained from a memory that is in signal communication with the computer. Processing results indicative of tooth condition are displayed.

Abstract: A content aware pattern stamping tool that preserves the visual texture of an area within an image when filling the area with a pattern is provided. In one embodiment, the pattern stamping tool analyzes an area to be filled with a pattern to determine textural characteristics of the area. These textural characteristics may include reflectance and shading. Once the pattern stamping tool has determined the textural characteristics of the area, the pattern stamping tool fills the area with the pattern and applies the textural characteristics to the filled area. Through application of the textural characteristics, the pattern stamping tool generates an image that combines the pattern with the original textural characteristics of the area.

Abstract: Systems, methods, and devices for predicting driver intent and future movements of a human driven vehicles are disclosed herein. A system for predicting future movements of a vehicle includes a camera system, a boundary component, a body language component, and a prediction component. The camera system is configured to capture an image of a vehicle. The boundary component is configured to identify a sub-portion of the image corresponding to an area where a driver of a vehicle is located. The body language component configured to detect a driver's body language. The prediction component configured to predict future motion of the vehicle based on the driver's body language detected by the body language component.

Abstract: A rotary stage is controlled to two measurement positions along a rotational direction in which an object surface is moved when detecting a wavefront of reflected light from partial regions by a detector, to move the object surface. Respective placement errors in a trajectory of the object surface at the two measurement positions are measured based on wavefronts detected by the detector in states in which the rotary stage is controlled to each of the two measurement positions. For the remaining measurement positions among the measurement positions, respective placement errors with respect to the trajectory of the object surface are estimated based on the placement errors measured. Before measurement of each item of partial shape data, the rotary stage is controlled to a measurement position and stages are controlled to a position that cancels a placement error at the measurement position to align the object surface.