Abstract: A system of active fiducial markers for pose calculation of head mounted displays is described in which information is exchanged among said markers for the purpose of synchronization. Fiducial patterns are made more easily identifiable by selective duty cycles of sub groups of synchronized emitters and means is described to propagate pose information among markers.

Abstract: Techniques for an image-based analysis of a geological thin section include (i) acquiring a plurality of images from a geological thin section of a rock sample from a subterranean zone; (ii) manipulating the plurality of images to derive a composite image; (iii) optimizing the composite image to derive a seed image; (iv) identifying, in the seed image, a particular seed pixel of a plurality of contiguous pixels that comprise an image of a grain of a plurality of grains of the rock sample in the seed image; (v) determining, with a specified algorithm, a shape of the grain based on the seed pixel; (vi) determining, based on the shape of the grain, a size of the grain; and (vii) preparing the determination of the size of the grain for presentation to a user.

Abstract: Disclosed are methods and systems for calculating a contrast reagent (CR) extravasation rate constant and generating a contrast reagent leakage corrected relative cerebral blood volume (rCBV) image map of a brain region from dynamic susceptibility contrast (DSC) magnetic resonance imaging (MRI) time-course image data based on pharmacokinetic first principles. In one example approach, a computerized method may include performing a linearization transform of a DSC MRI time-course equation which accounts for an intravascular contribution and an extravasating component, and calculating CR leakage from a slope of a linear portion of the transformed data.

Abstract: Disclosed is a method and video surveillance system for detecting fraud. The system may receive images. The system may convert the images into binary images. Subsequently, the system may identify a reference frame amongst the binary images. The system may trigger face detection upon detecting motion within the binary images. The system may detect the motion based on a relative white pixel count of the binary image with respect to a reference image. The system may reduce a Region of Interest (RoI) window within the binary images based on a highest density of white pixel count. The system may determine whether a face is detected within the reduced RoI window. The system may determine whether mouth is detected within a lower half of the face when the face is detected. The system may detect the fraud when the face is not detected or the mouth is not detected.

Abstract: A method and device for adjusting a monitored region in a tracking scan, comprising: selecting a best match of a positioned image from tracked image(s) as a monitored layer image so as to reduce position deviation of the monitored layer image with respect to the positioned image in a direction perpendicular to a plane on which the positioned image is located; and adjusting a position of a second monitored region on the monitored layer image according to a position of a corresponding first monitored region selected from the positioned image so as to reduce position deviation of the second monitored region with respect to the first monitored region in a plane parallel to the plane on which the positioned image is located.

Abstract: Disclosed are systems, devices, and methods for detecting a trachea of a patient, an exemplary method comprising obtaining a three-dimensional (3D) model of a chest of the patient, generating slice images of the 3D model along an axial direction, identifying a connected component in each of the generated slice images, labeling a connected component in a top slice image of the generated slice images as an active object, associating each connected component in a current slice image with a corresponding connected component in a previous slice image based on a connectivity criterion, labeling each connected component in the current slice image associated with a connected component of the preceding slice image as the active object, and identifying the active object as the trachea, based on a length of the active object.

Abstract: Pet faces can be detected within an image using a cascaded adaboost classifier trained to identify pet faces with a high detection rate and a high false positive rate. The identified potential windows are further processed by a number of category aware cascade classifiers, which are each trained to identify pet faces of a particular category with a high detection rate and low false positive rate. The potential pet faces identified by the category aware classifiers may be processed to verify whether a pet's face is present or not.

Abstract: Application of inter-class and intra-class filtering, based on aggregate point-to-point distances, to vector data for purposes of filtering the vector data for purposes of pattern recognition. In some embodiments: (i) the inter-class filtering is based on Euclidean distance, in all dimensions, between vector data points in vector space; and/or (ii) the intra-class filtering is based on a distance, in all dimensions, between vector data points in vector space.

Abstract: Provided is a PRCA-based method for dynamically reestablishing a PET image. The method comprises: (1) performing collection and correction to obtain a coincidence counting matrix; (2) performing correction restriction on a PET measurement equation; (3) performing iterative estimation on PET dynamic concentration data; and (4) reestablishing each frame of PET image. In the present invention, different frames of collected data are regarded as a whole for reestablishment, and the relevancy of the PET data in time is fully used, so that the obtained result can embody the characteristic that the dynamic PET can show the time change of a target region; and secondly, in the present invention, a background and target region method is used, the interference to the target region caused by the background is reduced, in addition, the time and space correction are added in the reestablishment, the accuracy of the reestablishment result is higher, and the contrast between the target region and the background is improved.

Abstract: A method for denoising Magnetic Resonance Imaging (MRI) data includes receiving a noisy image acquired using an MRI imaging device and determining a noise model comprising a non-diagonal covariance matrix based on the noisy image and calibration characteristics of the MRI imaging device. The noisy image is designated as the current best image. Then, an iterative denoising process is performed to remove noise from the noisy image.

Abstract: A method determines motion between first and second coordinate systems by first extracting first and second sets of keypoints from first and second images acquired of a scene by a camera arranged on a moving object. First and second poses are determined from the first and second sets of keypoints. A score for each possible motion between the first and the second poses is determined using a scoring function and a pose-transition graph constructed from training data where each node in the post-transition graph represents a relative pose and each edge represents a motion between two consecutive relative poses. Then, based on the score, a best motion is selected as the motion between the first and second coordinate systems.

Abstract: A method of and apparatus for changing lesion classification data, the method including determining whether at least one mass is included in an image of an object, determining whether the at least one mass corresponds to a lesion by using first data including at least one first information, selecting a false negative (FN) mass which has been determined as not corresponding to the lesion among the at least one mass, based on a first input, and changing the first data to second data by using second information of the selected FN mass.

Abstract: An electronic device and method are provided. The fingerprint recognition method includes: obtaining a verification fingerprint image; transmitting the verification fingerprint image to the second processing unit; generating verification fingerprint data according to the verification fingerprint image by the second processing unit; transmitting the verification fingerprint data to the first processing unit by the second processing unit; comparing the verification fingerprint data with a plurality of registered fingerprint datasets to generate matching information by the first processing unit; transmitting the matching information from the first processing unit to the second processing unit; and verifying the verification fingerprint data according to the matching information by the second processing unit.

Abstract: In some examples, a method to reduce heel effect distortion in dual energy x-ray images includes receiving flood field images generated by x-rays at different energy levels and generating one or more normalize images based on the flood field images. The method may also include applying the one or more normalize images to one or more x-ray images and combining the x-ray images to generate a dual energy x-ray image with reduced heel effect distortion.

Abstract: Disclosed are systems, devices, and methods for detecting a trachea, an exemplary system comprising an imaging device configured to obtain image data and a computing device configured to generate a three-dimensional (3D) model, identify a potential connected component in a first slice image, identify a potential connected component in a second slice image, label the first slice image as a top slice image, label the connected component in the top slice image as an active object, associate each connected component in a current slice image with a corresponding connected component in a previous slice image based on a connectivity criterion, label each connected component in the current slice image associated with a connected component of the preceding slice image as the active object, and identify the active object as the trachea, based on a length of the active object.

Abstract: In an image classification method, a feature vector representing an input image is generated by unsupervised operations including extracting local descriptors from patches distributed over the input image, and a classification value for the input image is generated by applying a neural network (NN) to the feature vector. Extracting the feature vector may include encoding the local descriptors extracted from each patch using a generative model, such as Fisher vector encoding, aggregating the encoded local descriptors to form a vector, projecting the vector into a space of lower dimensionality, for example using Principal Component Analysis (PCA), and normalizing the feature vector of lower dimensionality to produce the feature vector representing the input image. A set of mid-level features representing the input image may be generated as the output of an intermediate layer of the NN.

Abstract: An apparatus includes a cropper operable to receive images and crop the images to exclude a border area, thus generating cropped images, a skin-pixel-identifier coupled to the cropper and that identifies pixel values that are representative of the skin in the cropped images, a first frequency filter coupled to the skin-pixel-identifier and that applies a frequency filter to output of the skin-pixel-identifier, a regional facial clusterial module coupled to the first filter and that applies spatial clustering to the output of the first filter, a second frequency filter operably coupled to the regional facial clusterial module and applied to the output of the regional facial clusterial module, a temporal-variation identifier coupled to the first filter and that identifies temporal variation of the output of the first filter, and a vital-sign generator coupled to the temporal-variation identifier that generates at least one vital sign from the temporal variation.

Abstract: According to one embodiment, an MRI apparatus includes a data acquiring part and a data processing part. The data acquiring part acquires first and second MR signals by applying at least one IR pulse under an application condition according to a relaxation time of a fluid. The first MR signals include MR signals, having negative values, from the fluid. The second MR signals include MR signals, having positive values, from the fluid. The data processing part generates first and second image data. The first image data depict the fluid as a lower signal region than that of a tissue. The second image data depict the fluid as a higher signal region than that of the tissue. The data processing part generates the first image data with a phase correction based on the second MR signals.

Abstract: An image processing apparatus includes a detection unit configured to detect areas that have changed between a plurality of images, a calculation unit configured to calculate movement vectors for respective areas on the plurality of images, an estimation unit configured to estimate areas where a moving object exists in the plurality of images by using the movement vectors for respective areas calculated by the calculation unit, and information about the motion of an imaging unit, which captured the plurality of images, in the plurality of images, and an identification unit configured to identify moving object areas based on the changed areas detected by the detection unit, and the areas where a moving object exists estimated by the estimation unit.

Abstract: In one example, a method includes receiving, by a computing device, data for a region of interest that includes growing crops. The received data for the region of interest can include image data for the region of interest. The method further includes identifying, by the computing device based on the received image data, rows of crops within the region of interest. The method further includes determining, by the computing device based on the received data for the region of interest associated with portions of the region of interest included in the identified rows of crops and excluding portions of the region of interest outside the identified rows of crops, a stand status of the growing crops within the region of interest. The stand status includes a quantity status corresponding to a population of crops within the region of interest.