Image registration algorithms can also be classified according to the transformation models they use to relate the target image space to the reference image space. The first broad category of transformation models includes linear transformations, which include rotation, scaling, and other affine transforms, but not translation (translation is non-linear transformation). Linear transformations are global in nature, thus, they cannot model local geometric differences between images.
The second category of transformations allow 'elastic' or 'nonrigid' transformations. These transformations are capable of locally warping the target image to align with the reference image. Nonrigid transformations include radial basis functions (thin-plate or surface splines, multiquadrics, and compactly-supported transformations), physical continuum models (viscous fluids), and large deformation models (diffeomorphisms).
Other articles related to "transformation models, models, model":
... SOMF offers eight models of implementation, also known as "Bell's Transformation Models", as depicted in the displayed image named SOMF transformation models ... Each of these units of work, namely models, identify the methodology, process, platform, best practices, and disciplines by which a practitioner ought to accomplish a modeling task ... The illustrated ninth model is the Governance Model, which should be employed to manage the other eight models ...
Famous quotes containing the word models:
“The greatest and truest models for all orators ... is Demosthenes. One who has not studied deeply and constantly all the great speeches of the great Athenian, is not prepared to speak in public. Only as the constant companion of Demosthenes, Burke, Fox, Canning and Webster, can we hope to become orators.”
—Woodrow Wilson (18561924)