Abstract: Subject matter disclosed herein relates to electronic image object or logo recognition.

Abstract: A variety of systems and methods are described which enable quantitative information to be extracted regarding automated procedures, including those performed at a high speed that may require a user input, without having to interrupt the procedure. In addition, these systems and methods serve to provide information on one or more parameters of the automated procedure, whereby they may be modified, if required, to improve the automated procedure or the results from such a procedure. The systems and methods provided are especially useful in automated hair transplantation procedures.

Abstract: A method of image reconstruction for a magnetic resonance imaging (MRI) system includes obtaining k-space scan data captured by the MRI system, the k-space scan data being representative of an undersampled region over time, iteratively reconstructing preliminary dynamic images for the undersampled region from the k-space scan data via optimization of a first instance of a minimization problem, the minimization problem including a regularization term weighted by a weighting parameter array, generating a motion determination indicative of an extent to which each location of the undersampled region exhibits motion over time based on the preliminary dynamic images, and iteratively reconstructing motion-compensated dynamic images for the region from the k-space scan data via optimization of a second instance of the minimization problem, the second instance having the weighting parameter array altered as a function of the motion determination.

Abstract: An information processing device according to an embodiment of the present invention includes a detection unit, a calculation unit, a determination unit, and an estimation unit. The detection unit detects each three-dimensional position of a plurality of parts of an instruction object for indicating an image output surface. The calculation unit calculates an intersection point of a direction indicated by the instruction object and the image output surface based on each three-dimensional position of the parts of the instruction object. The determination unit determines whether the intersection point is within a predetermined range on the image output surface. The estimation unit estimates a position indicated by the instruction object on the image output surface based on the determination made by the determination unit.

Abstract: A system capable of determining which recognition algorithms should be applied to regions of interest within digital representations is presented. A preprocessing module utilizes one or more feature identification algorithms to determine regions of interest based on feature density. The preprocessing modules leverages the feature density signature for each region to determine which of a plurality of diverse recognition modules should operate on the region of interest. A specific embodiment that focuses on structured documents is also presented. Further, the disclosed approach can be enhanced by addition of an object classifier that classifies types of objects found in the regions of interest.

Abstract: There is provided an image processing method including analyzing contrast according to a spatial frequency of an input image for each RGB pixel, referencing a database in which a relationship between a crosstalk degradation amount and a disparity transition for each RGB pixel is stored in association with contrast according to spatial frequencies of various images, and acquiring a relationship between a crosstalk degradation amount and a disparity transition for each RGB pixel, the relationship corresponding to the contrast according to the spatial frequency of the input image, integrating the relationship between the crosstalk degradation amount and the disparity transition, the relationship having been acquired for each RGB pixel, and calculating disparity corresponding to a predetermined threshold set to the crosstalk degradation amount in the integrated relationship between the crosstalk degradation amount and the disparity transition.

Abstract: A display device and a method of controlling therefor are disclosed. A display device includes a main display unit configured to receive an input of at least one fingerprint and display information, a sub display unit configured to be exposed from a stored position and a controller configured to set a mode based on the inputted at least one fingerprint. If an inputted first fingerprint is matched with a fingerprint of a group of registered fingerprints, the controller is configured to set a first mode. If an inputted first fingerprint and a second fingerprint are matched with fingerprints of the group of the registered fingerprints, the controller is configured to set a second mode.

Abstract: A pattern processing device includes: an input unit to input an input image containing a plurality of pattern elements; an extraction unit that calculates edge intensities of pixels from the input image so as to extract edge pixels; an evaluation unit that obtains evaluation values for determining whether the pixels are foreground pixels or background pixels, based on comparison result between first thresholds set corresponding to the edge pixels and pixel values of pixels contained in vicinity regions of the edge pixels; a binarization determining unit that determines whether the pixels are the foreground pixels or the background pixels by comparing the evaluation values with a predetermined second threshold, and a coupling component extraction unit that extracts pixel coupling components obtained by coupling the pixels adjacent in any direction among the pixels determined to be the foreground pixels.

Abstract: A method for matching a pattern to a multi-view sequence includes receiving a multi-view sequence which includes a plurality of sequences. Each sequence includes symbols drawn from a respective alphabet. A pattern to be matched on the multi-view sequence is received. The pattern includes a sequence of symbols drawn from a plurality of the alphabets. Offsets are assigned to the symbols as a function of a latest position of the symbol in the pattern or a length of the pattern otherwise. The multi-view sequence is traversed with the pattern to identify index positions in the sequence at which the pattern matches the corresponding part of the multi-view sequence. The pattern is shifted between index positions by a shift which is based on a minimum of the offsets for those of the symbols of the plurality of sequences that are aligned with a last of the symbols in the pattern.

Abstract: A recording medium storing an image processing program according to one aspect of the present invention is a non-transitory computer-readable medium storing an image processing program to make a computer execute image processing on an image group on one timeline, the image processing program making the computer execute deriving a difference value that is based on a difference between pixel values of images that are adjacent in time series in the image group, and displaying a time-series difference image showing a time-series change in the difference value.

Abstract: An electronic device may include a finger biometric sensor to sense a user's finger adjacent thereto, and a memory for storing finger matching biometric data and a subset of finger matching biometric data. The electronic device may include a processor coupled to the finger biometric sensor to acquire finger matching biometric data from the finger biometric sensor, and perform a finger pre-matching between a subset of the acquired finger matching biometric data and the subset of stored finger matching biometric data and based upon context data to generate pre-match data. The processor may also perform a finger matching between the acquired finger biometric data and the stored finger matching biometric data based upon the pre-match data.

Abstract: A multi view-point image composed of a great number of images according to a shape of an object is generated or an information processing method used for generating a three-dimensional model or performing image processing of arbitrary view-point object recognition is provided, and based on a plurality of captured images obtained by imaging of the object from a plurality of view points by an imaging means, a relative position and orientation with respect to the object relative to the imaging means for each of the plurality of view points is calculated, and based on the calculated plurality of relative positions and orientations, a missing position and orientation of the imaging means in a direction in which imaging by the imaging means is missing is calculated, and an image used for displaying the calculated missing position and orientation on a display means is generated.

Abstract: A method and apparatus of image reconstruction attenuation correction in PET or SPECT cardiac imaging is provided. A volumetric attenuation imaging scan by an X-ray source may be used to generate a gamma ray attenuation map. The volumetric attenuation imaging scan may be randomized, and may be performed while the imaged subject is breathing.

Abstract: A method extracts planes from three-dimensional (3D) points by first partitioning the 3D points into disjoint regions. A graph of nodes and edges is then constructed, wherein the nodes represent the regions and the edges represent neighborhood relationships of the regions. Finally, agglomerative hierarchical clustering is applied to the graph to merge regions belonging to the same plane.

Abstract: Technology described herein provides techniques for screen detection. This could be a dynamic screen, such as a display screen of an electronic device, or a static screen such as a street sign. In one aspect, a screen is detected in frames of image data. An active image and/or an average color image may be formed based on frames of image data. A set of lines that are candidate for boundaries of a screen are identified in the frames. The active image and/or an average color is integrated on both sides of each line in the set of lines to form integration results. A set of screen candidates are formed based on the integration results. Screens in the screen candidates are scored according to a criterion. One or top few of the screens in the set of screen candidates is selected based on the scoring.

Abstract: A posture estimation device, which is able to estimate the posture of a humanoid articulated body with high precision, has: a head estimation unit (120) that estimates the position of a person's head from image information for an image that contains a person; a foot estimation unit (130) that, from the image information, estimates the position of the person's foot for which the sole of the foot is parallel to the floor surface; and a posture estimation unit (140) that estimates the posture of the person on the basis of the relative positional relationship between the estimated head position and the estimated foot position. For example, the posture estimation unit (140) estimates the side on which the foot is located, with respect to the head, as the front side of the person.

Abstract: Facial image bucketing is disclosed, whereby a query for facial image recognition compares the facial image against existing candidate images. Rather than comparing the facial image to each candidate image, the candidate images are organized or clustered into buckets according to their facial similarities, and the facial image is then compared to the image(s) in most-likely one(s) of the buckets. The organizing uses particular selected facial features, computes distance between the facial features, and selects ones of the computed distances to determine which facial images should be organized into the same bucket.

Abstract: A method and a segmentation system are disclosed. An embodiment of the method includes providing an image representation of the structure; providing a start surface model, including a mesh with a plurality of vertices connected by edges; defining for each vertex a ray normal to the surface model at the position of the vertex; assigning more than two labels to each vertex, each label representing a candidate position of the vertex on the ray; providing a representation of likelihoods for each candidate position the likelihood referring to whether the candidate position corresponds to a surface point of the structure in the image representation; and defining a first order Markow Random Field with discrete multivariate random variables, the random variables including the labels of the candidate positions and the representation of likelihoods, finding an optimal segmentation of the structure by using an maximum a posteriori estimation in this Markow Random Field.

Abstract: An image processing apparatus includes a modification processing unit configured to modify an input image by distributing a value of each of pixels in the input image over a two-dimensional distribution area having a randomly different size and direction in accordance with modification characteristic information for distributing each pixel over the distribution area. The modification characteristic information is information for modifying the input image using a modification characteristic which is randomly different for each pixel position.

Abstract: Techniques for atmospheric compensation in satellite imagery that include converting an image including an array of radiance values to an array of surface reflectance values. The conversion is performed in an automated fashion by identifying one or more portions of the image for which the surface reflectance can be estimated and determining the Aerosol Optical Depth (AOD) by iteratively comparing the radiance value captured by the image sensor to a calculated radiance value (based on the known surface reflectance, historical values for other atmospheric parameters, and the AOD) and adjusting the AOD until the calculated radiance value is substantially the same as the captured radiance value.