Image registration using threefold orthogonal wavelet

Smadar Gefen; Oleh Tretiak; Jonathan Nissanov

doi:10.1117/12.506096

Translator Disclaimer

13 November 2003 Image registration using threefold orthogonal wavelet

Smadar Gefen, Oleh Tretiak, Jonathan Nissanov

Author Affiliations +

Proceedings Volume 5207, Wavelets: Applications in Signal and Image Processing X; (2003) https://doi.org/10.1117/12.506096
Event: Optical Science and Technology, SPIE's 48th Annual Meeting, 2003, San Diego, California, United States

Abstract

An algorithm for multidimensional nonlinear registration is proposed. The deformation field between two elastic bodies is represented by a multi-resolution separable wavelet. Using a progressive approach that reduces algorithm complexity the registration parameters are recovered in a coarse to fine order. A custom wavelet that approximates threefold orthogonality is developed. The performance of the algorithm is evaluated by the alignment of sections from mouse brains. The wavelet registration algorithm demonstrated on average fourfold improvement in section alignment over linear alignment.

Citation Download Citation

Smadar Gefen, Oleh Tretiak, and Jonathan Nissanov "Image registration using threefold orthogonal wavelet", Proc. SPIE 5207, Wavelets: Applications in Signal and Image Processing X, (13 November 2003); https://doi.org/10.1117/12.506096

ACCESS THE FULL ARTICLE