The Insight Journal logo

Image Registration with Automatic Computation of Gradients

Kahn, Eliezer, Staib, Lawrence
JHUAPL
Publication cover image

Please use this identifier to cite or link to this publication: http://hdl.handle.net/1926/1469
New: Prefer using the following doi: https://doi.org/10.54294/ov202k
Submitted by Eli Kahn on 2008-07-30T02:25:29Z.

Many image registration algorithms are formulated as optimization problems with a gradient descent based solver, One difficulty with designing and implementing such methods is in the implementation of the gradient computation. This process can be time-consuming and error-prone. In addition some functions do not have gradients that can be expressed in symbolic form. Automatic differentiation is useful for computing gradients of complicated objective functions. It moves the burden of computing gradients from the programmer to the computer. So far, AD has not been exploited for use in image registration. This paper describes a software library the authors have developed to automate the process of computing gradients of registration objective functions. This can alleviate the job of registration designers somewhat and potentially make it easier to design better registration algorithms.