Abstract: A method is provided including acquiring imaging data of an object to be imaged from a computed tomography (CT) detector. The method also includes reconstructing the acquired imaging data into an initial reconstruction image, and performing material characterization of an image volume of the initial reconstruction image to provide a re-mapped image volume. Further, the method includes performing forward projection on the re-mapped image volume to provide forward projection data, and providing an error projection based on the forward projection data. Also, the method includes filtering at least one of the initial reconstruction image, the re-mapped image volume, the forward projection data, or the error projection. The method also includes using the error projection to update the initial reconstruction image to provide an updated reconstruction image.

Abstract: In a case where generating a training image of an object to be used to generate a dictionary to be referred to in image recognition processing of detecting the object from an input image, model information of an object to be detected is set, and a luminance image of the object and a range image are input. The luminance distribution of the surface of the object is estimated based on the luminance image and the range image, and the training image of the object is generated based on the model information and the luminance distribution.

Abstract: The invention discloses an image restoration method and an imager processing apparatus using the same. The method includes the following steps: receiving a haze image comprising a plurality of pixels; detecting whether a color cast phenomenon occurs on the haze image; if yes, calculating a plurality of Laplacian distribution values respectively corresponding to the color channels; determining a maximum distribution value and a minimum distribution value among the Laplacian distribution values, and generating a self-adaptive parameter by comparing the maximum distribution value and the minimum distribution value; adjusting the transmission map by the self-adaptive parameter so as to generate a adjusted transmission map; calculating a plurality of color parameters respectively corresponding to the color channels according to the Laplacian distribution values; and restoring the haze image by using the color parameters and the adjusted transmission map so as to obtain a restored image.

Abstract: A method and system for blood flow velocity reconstruction from medical image data is disclosed. Flow system geometry of a flow conduit is generated from medical image data. The flow system velocity includes an inlet, walls, and one or more outlets of the flow conduit. A measured velocity field is extracted from the medical image data. Inlet and wall fluxes are estimated based on the measured velocity field or other external measurements. Outlet fluxes are estimated such that mass conservation is constrained based on the inlet and wall fluxes. A reconstructed velocity field is calculated by solving flux-constrained Poisson (FCP) equations that are constrained by the estimated output fluxes.

Abstract: There is provided a measurement apparatus including an objective lens, a stage, a setting unit, and a controller. The stage is configured to support a sample vessel in which a plurality of wells each containing a sample are arranged and to define relative positions of the sample vessel and the objective lens. The setting unit is configured to determine whether to set each of the plurality of wells to be a measurement target and set the measurement target. The controller is configured to control the stage such that a well determined to be the measurement target by the setting unit and the objective lens face each other.

Abstract: According to a processing period for OCR processing of image data for character recognition for a given page, the image processing section determines whether or not to generate image data for character recognition for a next page subsequent to the given page in accordance with an image quality setting different from that set for the given page. Upon determining generation in accordance with an image quality setting different from that set for the given page, the image processing section determines the image quality setting for the next page based on document type and size of the given page of the original document. The image processing section generates image data for character recognition for the next page in accordance with the determined image quality setting.

Abstract: A filtering device includes an evaluation value deriving module that derives, for a pair of generated images having mutual relevance, multiple evaluation values indicative of correlations between any one of blocks extracted from one of the images and multiple blocks extracted from the other image, respectively, a reference waveform part setting module that sets a reference waveform part of a transition waveform comprised of the multiple evaluation values, the reference waveform part containing the evaluation value having the highest correlation, and a difference value determining module that determines whether one or more similar waveform parts similar to the reference waveform part exist in the transition waveform, and determines, based on the result of the determination, whether the evaluation value with the highest correlation is valid as a difference value.

Abstract: The present technology relates to an information processing apparatus, an information processing method, and a program capable of searching for and tracking a person desired to be searched for and tracked from images captured by a plurality of cameras with high precision. By inputting decision information used for a user to decide a searching target in a moving-object image PA captured by a monitoring camera imaging an imaging area CamA on a screen P211 indicating a searching and tracking result, as indicated by a hand H1, and by erasing a plot E from the searching and tracking result because of a distant position to which a person may not travel at an average human movement speed for about 5 seconds despite moving for a time of 5 seconds (1:00:05 to 1:00:00) from a plot A to the plot E by time-space comparison between detection results of the plots A and E, it is possible to improve precision of the searching and tracking result.

Abstract: An image is segmented by subjecting the image to an iterative thresholding operation, and a hierarchical representation of clusters is obtained by analyzing the results of each of the iterative thresholding steps to find clusters of adjacent image elements. A type class is assigned to a leaf cluster of the hierarchical representation and the assigned class is propagated towards the top of the hierarchical representation. Then a mask is generated marking the locations of image elements contained in the top ancestral clusters of a specific type.

Abstract: A method, apparatus and computer program product are provided to facilitate scene segmentation from focal stack images. The method may include receiving a set of focal stack images, calculating a focal measure for each of a plurality of pixels of the set of focal stack images, and grouping each of a plurality of pixels for which the focal measure was calculated into a plurality of super pixels. The method may also include calculating a focal measure for each of the plurality of super pixels, segmenting a respective focal stack image based on the focal measure of each of the plurality of super pixels, calculating a color probability for each of the plurality of super pixels, and segmenting each focal stack image based on color probability of each of the plurality of super pixels.

Abstract: A framework is provided for accelerating multi-scan and multi-channel data acquisition in a clinical MRI protocol by estimating correlation functions from images previously acquired or reconstructed, with the same or with different contrast and resolution. Using an MRI apparatus, the method collects a plurality of prior MRI image scan data sets, obtains a current MRI scan data, and reconstructs the current MRI scan data set using an aggregate of the plurality of prior MRI image data sets. The method provided may optimize previously acquired MRI image data sets to reconstruct an MRI image scan data set and image.

Abstract: A method for an optical fingerprint recognition, the method includes scanning a fingerprint image using a multiple scan which allows alternating a first scan condition and a second scan condition different from each other; determining whether an input fingerprint is a dry fingerprint depending on a darkness level of a fingerprint image derived from the first scan condition; and performing a fingerprint recognition using a fingerprint image derived from the first scan condition or a fingerprint image derived from the second scan condition in accordance with the determination result as to the dry fingerprint.

Abstract: The invention relates to a method for assessing the presence of a watermark in a video wherein the video comprises at least a sequence of frames. The method comprises for at least one frame among one of the sequences of frames the steps of computing a set of axial cross-correlation values, wherein each axial cross-correlation value corresponds to a correlation between the frame and a reference watermark shifted along a spatial horizontal axis; obtaining a detection score by computing a weighted sum of values output by a function applied to said axial cross-correlation values; assessing the presence of a watermark according to the detection score. Such method is particularly well adapted to the detection of disparity coherent watermark but is compliant with any watermarking technique. A device implementing the method is further disclosed.

Abstract: A method for sending a screen image by a computing device is described. A modification image representing a modified region of the screen image is determined. The modification image has a lossless format. Location information is encoded in one or more alpha channels of the modification image. The modification image is sent.

Abstract: Surveillance systems may be found in both private and public spaces. In private spaces, they can be designed to help provide and monitor secure premises. Similarly, public spaces may also use surveillance systems to determine an allocation of public resources. A camera surveillance system according to an embodiment of the invention uses advanced image processing techniques to determine whether an object moving across a scene is a person. The camera surveillance system achieves an accurate and efficient classification by selectively processing a set of features associated with the object, such as features that define an omega shape. By selectively processing the set of features associated with the object, the methods and systems described herein reduce the computational complexity of standard image processing/object detection techniques.

Abstract: Head-mounted display apparatus and login method thereof are provided. The head-mounted display apparatus includes an image capturing device, a pico-projector, an application specific integrated circuit (ASIC), and an application processor. The image capturing device captures a first eye image and a plurality of second eye images corresponding to a locus image. The ASIC determines whether the first eye image passes an iris recognition test. The application processor controls a pico-projector to project the locus image when the first eye image passes an iris recognition test, and generates a pupil locus based on the plurality of second eye images. The application processor determines whether the pupil locus is compliant with the locus image, and allows a login request if the pupil locus is compliant with the locus image.

Abstract: Systems and methods are provided for determining the safety of an image, which may be used to determine whether an image is appropriate for a given purpose or for use in a given context. Determining the safety of the image may include analyzing the image to determine the amount of skin exposed in various key body areas of each human represented in the image, such as a photograph.

Abstract: A vehicle external environment recognition device includes a three-dimensional position deriving module that derives three-dimensional positions in real space of subject parts in images that are obtained by imaging a detection area, an object identifying module that groups the subject parts of which differences in the three-dimensional position are within a predetermined range to identify an object, an edge intensity deriving module that horizontally divides an area containing the object to set divided areas, and derives an edge average that is an average value of edge intensities based on a luminance value of each pixel within each of the divided areas; and a floating matter identifying module that compares the edge average with a predetermined threshold, and identifies the object to be likely floating matters when the edge average is less than the threshold.

Abstract: An processor (118) includes a bullous emphysema identifier (206) that processes voxels of the volumetric image data and identifies voxels corresponding to bullous emphysema, a two dimensional projection image generator (206) that generates a 2D bullous emphysema projection image based on the voxels corresponding to bullous emphysema, wherein an intensity of a contour of a bulla in the 2D bullous emphysema projection image is based on a size of the bulla, and a feature highlighter (210) that highlights the bullous emphysema in the 2D bullous emphysema projection image using second first indicia.

Abstract: Described is a system for improving object recognition. Object detection results and classification results for a sequence of image frames are received as input. Each object detection result is represented by a detection box and each classification result is represented by an object label corresponding to the object detection result. A pseudo-tracklet is formed by linking object detection results representing the same object in consecutive image frames. The system determines whether there are any inconsistent object labels or missing object detection results in the pseudo-tracklet. Finally, the object detection results and the classification results are improved by correcting any inconsistent object labels and missing object detection results.