You are in : Home » Results & submissions » Select UOA » 13 - Electrical and Electronic Engineering, Metallurgy and Materials » View submission: University of Surrey » Outputs » Detail

Output details

13 - Electrical and Electronic Engineering, Metallurgy and Materials

University of Surrey

Return to search Previous output Next output

Output 0 of 0 in the submission

Article title

Mutual Information for Lucas-Kanade Tracking (MILK): An Inverse Compositional Formulation

Type

D - Journal article

DOI

10.1109/TPAMI.2007.70757

Title of journal

IEEE Transactions on Pattern Analysis and Machine Intelligence

Article number

Volume number

Issue number

First page of article

180

ISSN of journal

0162-8828

Year of publication

2008

URL

Number of additional authors

Additional information

Mutual information (MI) applied to image registration allows multimodal/nonlinear matching of 2D/3D images. However, histograms make this process slow. Simple matching can be sped up with mathematical tricks but these are difficult to apply due to their use of probability. This work introduces a generic framework that allows heavily optimised matching to be performed using a variety of interpolation schemes. This approach has been used in tracking/image registration, medical imaging and multimodal registration. The first author now works for Siemens Molecular Imaging.

Interdisciplinary

Cross-referral requested

Research group

None

Proposed double-weighted

Double-weighted statement

Reserve for a double-weighted output

Non-English

English abstract