Parametric image alignment using enhanced correlation coefficient maximization.

Signal Processing and Communications Lab, Department of Computer Engineering and Informatics, University of Patras, Rio-Patras, Greece.
IEEE Transactions on Pattern Analysis and Machine Intelligence (Impact Factor: 5.69). 11/2008; 30(10):1858-65. DOI: 10.1109/TPAMI.2008.113
Source: PubMed

ABSTRACT In this work we propose the use of a modified version of the correlation coefficient as a performance criterion for the image alignment problem. The proposed modification has the desirable characteristic of being invariant with respect to photometric distortions. Since the resulting similarity measure is a nonlinear function of the warp parameters, we develop two iterative schemes for its maximization, one based on the forward additive approach and the second on the inverse compositional method. As it is customary in iterative optimization, in each iteration, the nonlinear objective function is approximated by an alternative expression for which the corresponding optimization is simple. In our case we propose an efficient approximation that leads to a closed-form solution (per iteration) which is of low computational complexity, the latter property being particularly strong in our inverse version. The proposed schemes are tested against the Forward Additive Lucas-Kanade and the Simultaneous Inverse Compositional (SIC) algorithm through simulations. Under noisy conditions and photometric distortions, our forward version achieves more accurate alignments and exhibits faster convergence whereas our inverse version has similar performance as the SIC algorithm but at a lower computational complexity.

1 Bookmark
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The Imaging Computational Microscope (ICM) is a suite of computational tools for automated analysis of functional imaging data that runs under the cross-platform MATLAB environment (The Mathworks, Inc.). ICM uses a semi-supervised framework, in which at every stage of analysis computers handle the routine work, which is then refined by user intervention. The main functionality of ICM is built upon automated extraction of component signals from imaging data, segmentation and clustering of component signals, and feature computation and visualization. Analysis of imaging data through ICM can also be done in real-time, enabling guided imaging experiments. ICM is built using MATLAB's object-oriented class design, which allows the tool to be used both as a graphic user interface (GUI) as well as in custom scripts. ICM is freely available under the GNU public license for non-commerical use and open source development, together with sample data, user tutorials and extensive documentation.
  • [Show abstract] [Hide abstract]
    ABSTRACT: We investigate the characteristics of the elements of an orthogonal scattering Mueller matrix for spherical cells. Two parameter scatter plots with x- and y-coordinates determined by s11 + s12 and s11 − s12 values are drawn. The unexpected patterns of these two parameter scatter plots are more sensitive to the relative refractive index of cells. When a series of scatter plots in a database for cells' light scattering are prepared in advance, an image correlation technique can be used to judge the patterns of scatter plots, which shows a promising approach to reveal the tiny change of cells in a flow cytometry.
    Chinese Physics Letters 12/2014; 31(12). DOI:10.1088/0256-307X/31/12/127801 · 0.92 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In the field of image-guided surgery, Time-of-Flight (ToF) sensors are of interest due to their fast acquisition of 3-D surfaces. How-ever, the poor signal-to-noise ratio and low spatial resolution of today's ToF sensors require preprocessing of the acquired range data. Super-resolution is a technique for image restoration and resolution enhance-ment by utilizing information from successive raw frames of an image sequence. We propose a super-resolution framework using the graphics processing unit. Our framework enables interactive frame rates, com-puting an upsampled image from 10 noisy frames of 200×200 px with an upsampling factor of 2 in 109 ms. The root-mean-square error of the super-resolved surface with respect to ground truth data is improved by more than 20% relative to a single raw frame.
    Bildverarbeitung für die Medizin 2013; 03/2013

Full-text (2 Sources)

Available from
Jun 2, 2014