Method and system for extracting metadata from an observed scene comprising the use of high-speed image sensor array observing the scene through a field-of-view, filtering, matching of interesting information defined as activity/incident in the observed scene with a predefined-library, adapting the filtering to enhance frequencies of interest and suppress all others, and extracting metadata of interest.

There is described herein a method and system for detecting, in a segmented image, the presence and position of objects with a dimension greater than or equal to a minimum dimension. The objects exhibit a property whereby a distance map of the object at a first scale and a distance map of the object at a second scale greater than the first scale differ by a constant value over a domain of the distance map of the object at the first scale. A distance map of a model object is compared to a distance map of a target object using a similarity score that is invariant to an offset.

Provided is an a priori constraint and outlier suppression based image deblurring method. A convolution model is used for fitting a blurring process of a clear image and then the blurred image I is restored, so that the purpose of image deblurring is achieved. The method comprises an evaluation process of the significant structure of a blurred image, a process of blurring kernel estimation and outlier suppression, and a process of restoring the blurred image by non-blind deconvolution. A structure in the blurred image is obtained by use of L0 norm constraint and heavy-tailed a priori information. The L0 norm constraint is used to evaluate the blurring kernel. The evaluated blurring kernel is subjected to outlier suppression. The final restored image is obtained by using a non-blind deconvolution algorithm. The present invention can prominently improve the restoration level of the blurred image.

The present disclosure relates to dividing image data obtained from a scan (e.g. MRI) of an object into two or more sets of data corresponding do unique motion patterns and/or motion sources. Each of the two or more sets of data can be corrected using an appropriate correction technique. One appropriate correction techniques includes generating kernels for each divided imaging dataset using center and adjacent slice information to correct for through-plane and in-plane artifacts.

In one embodiment, coloring artifacts of a color image output by a camera are minimized by taking into account a distortion introduced by the lens. Based on the distortion, the color reconstruction determines which pixels in the grayscale image to include in the reconstruction process. Additionally, the color reconstruction can take into account edges depicted in the grayscale image to determine which pixels to include in the reconstruction process. In another embodiment, coloring artifacts in a 360 degree color image are minimized by performing the color reconstruction process on a three-dimensional surface. Before the color reconstruction takes place, the two-dimensional grayscale image is projected onto a three-dimensional surface, and the color reconstruction is performed on the three-dimensional surface. The color reconstruction on the three-dimensional surface can take into account the distortion produced by the lens and/or can take into account the edges depicted in the two-dimensional and three-dimensional grayscale image.

A method for correction of an x-ray image recorded with an x-ray device with an anti-scatter grid for effects of the anti-scatter grid is provided. The anti-scatter grid has a spatially periodically repeating geometrical embodiment, and a calibration image recorded without an imaging object is used. The calibration image and the x-ray image are transformed by a transformation into the position frequency space. In the position frequency space, adaptation parameters describing changes of the calibration image optimizing a measure of matching between the x-ray image and the calibration image are established. For correction, the adapted calibration image is subtracted from the x-ray image, and the x-ray image is transformed back into the position space again using an inverse of the transformation.

An image synthesis apparatus for generating a composite image by synthesizing a second image with a first image, includes an image acquisition unit configured to acquire first group images including the first image and a plurality of different resolution images corresponding to the first image, and second group images including the second image and a plurality of different resolution images corresponding to the second image, a frequency component calculation unit configured to calculate low-frequency components and high-frequency components from the first group images and the second group images, and an image synthesis unit configured to generate the composite image on the basis of the low-frequency components of the first group images and the high-frequency components of the second group images.

The present invention provides an apparatus for displaying a two-dimensional cross-sectional image of an arbitrary base plane which matches to the subject's head without creating extra labor to the operator even when the subject's head is asymmetrical. The apparatus is connected to a display unit for displaying a cross-sectional image of a head. The apparatus comprising: a conversion parameter obtaining unit for obtaining a conversion parameter indicating a difference in shape between a standard head and a subject's head based on a volume data; a subject base plane generating unit for generating an anatomical base plane of the subject's head based on the conversion parameter and an anatomical base plane of the standard head; and a cross-sectional reconstruction unit for generating a cross-sectional image of the anatomical base plane of the subject's head based on the volume data of the subject's head and displaying said cross-sectional image on the display unit.

Disclosed embodiments facilitate keypoint selection in part by assigning a similarity score to each candidate keypoint being considered for selection. The similarity score may be based on the maximum measured similarity of an image patch associated with a keypoint in relation to an image patch in a local image section in a region around the image patch. A subset of the candidate keypoints with the lowest similarity scores may be selected and used to detect and/or track objects in subsequent images and/or to determine camera pose.

First visual information defining the visual content in a first projection may be accessed. Second visual information defining lower versions of the visual content in the first projection may be accessed. A transformation of the visual content from the first projection to a second projection may be determined. The transformation may include a visual compression of a portion of the visual content in the first projection. The portion may be identified. An amount of the visual compression of the portion may be determined. One or more lower resolution versions of the visual content may be selected. The visual content may be transformed using the one or more lower resolution versions of the visual content.