Object identification using sparse spectral components

摘要

One or more systems and/or techniques are provided to identify and/or classify objects of interest (e.g., potential granular objects) from a radiographic examination of the object. Image data of the object is transformed using a spectral transformation, such as a Fourier transformation, to generate image data in a spectral domain. Using the image data in the spectral domain, one or more one-dimensional spectral signatures can be generated and features of the signatures can be extracted and compared to features of one or more known objects. If one or more features of the signatures correspond (e.g., within a predetermined tolerance) to the features of a known object to which the feature(s) is compared, the object of interest may be identified and/or classified based upon the correspondence.

主权项

1. A method for identifying an object in image data generated by an examination using radiation, comprising:
identifying, within three-dimensional image data, a region of interest (ROI) of the three-dimensional image data comprising a possible granular object based upon one or more morphological characteristics of the possible granular object; generating a set of one or more two-dimensional image slices of the region of interest from the three-dimensional image data; transforming the set of one or more two-dimensional image slices from an image domain to a spectral domain; generating one-dimensional spectral signature from the set of one or more two-dimensional image slices transformed into the spectral domain; and verifying, using the one-dimensional spectral signature, that the possible granular object is a granular object of the method implemented at least in part via a processing unit; wherein the one or more morphological characteristics correspond to an Eigen-box fill ratio (EBFR).