Related Experiment Video
Updated: Jul 10, 2026
09:23
Quantification of Information Encoded by Gene Expression Levels During Lifespan Modulation Under Broad-range Dietary Restriction in C. elegans
Published on: August 16, 2017
Mutual information for Lucas-Kanade Tracking (MILK): an inverse compositional formulation
Nicholas Dowson1, Richard Bowden
1Siemens Molecular Imaging, Oxford, OX1 2EP, UK. nicholas.dowson@siemens.com
IEEE Transactions on Pattern Analysis and Machine Intelligence
|November 15, 2007
Summary
This study introduces an inverse compositional formulation of Mutual Information (MI) for optimization. The new method offers a 15% speed improvement for image registration while maintaining accuracy.
Area of Science:
- Medical image analysis
- Computer vision
- Computational mathematics
Background:
- Mutual Information (MI) is a widely used metric for image registration.
- Traditional MI optimization methods can be computationally intensive.
Purpose of the Study:
- To develop a more efficient formulation of Mutual Information for image registration.
- To improve the speed of registration algorithms using the Levenberg-Marquardt optimization technique.
Main Methods:
- Proposed an inverse compositional formulation of Mutual Information.
- Applied this formulation to the Levenberg-Marquardt optimization algorithm.
- Investigated the properties of the Hessian matrix in the proposed formulation.
Main Results:
- The inverse compositional formulation results in a constant Hessian matrix.
- This constant Hessian can be pre-computed, leading to significant speedups.
- Achieved a 15% improvement in speed compared to the standard formulation.
- Maintained similar convergence accuracies as the standard MI formulation.
Conclusions:
- The proposed inverse compositional MI formulation offers a computationally efficient approach for image registration.
- This method accelerates the Levenberg-Marquardt optimization process without compromising accuracy.
- Presents a valuable advancement for medical image analysis and other registration applications.
More Related Videos
Related Concept Videos
01:29Composition of Body Fluids
Water functions as a solvent accommodating various solutes, which can be categorized under electrolytes and non-electrolytes. Non-electrolytes are usually held together by covalent bonds, restricting them from dissociating in solution, thereby leading to a lack of electrically charged components upon dissolving in water. They are predominantly organic molecules, such as glucose, creatinine, and urea. Electrolytes, on the other hand, are compounds that can break down into ions in water.
01:05Estimation of the Physical Quantities
On many occasions, physicists, other scientists, and engineers need to make estimates of a particular quantity. These are sometimes referred to as guesstimates, order-of-magnitude approximations, back-of-the-envelope calculations, or Fermi calculations. The physicist Enrico Fermi was famous for his ability to estimate various kinds of data with surprising precision. Estimating does not mean guessing a number or a formula at random. Instead, estimation means using prior experience and sound...
02:30Racemic Mixtures and the Resolution of Enantiomers
A racemic mixture, or racemate, is an equimolar mixture of enantiomers of a molecule that can be separated using their unique interaction with chiral molecules or media. Racemic mixtures are denoted by the (±)- prefix. This ‘optical rotation descriptor’ applies to the whole solution of a racemic mixture rather than a specific stereoisomer. Enantiomers typically have the same physical and chemical properties. Hence, they are not easily separable. However, enantiomers can exhibit different...
01:20Inverse z-Transform by Partial Fraction Expansion
The inverse z-transform is a crucial technique for converting a function from its z-domain representation back to the time domain. One effective method for finding the inverse z-transform is the Partial Fraction Method, which involves decomposing a function into simpler fractions with distinct coefficients. These fractions correspond to known z-transform pairs, facilitating the inverse transformation process.
To begin the process, the poles of the function are identified and the function is...
To begin the process, the poles of the function are identified and the function is...
01:18Kinematic Equations - III
The first two kinematic equations have time as a variable, but the third kinematic equation is independent of time. This equation expresses final velocity as a function of the acceleration and distance over which it acts. The fourth kinematic equation does not have an acceleration term and provides the final position of the object at time t in terms of the initial and final velocities. This equation is useful when the value of the constant acceleration is unknown.
Using the kinematic equations,...
Using the kinematic equations,...
01:14Extraction: Partition and Distribution Coefficients
The distribution law or Nernst's distribution law is the law that governs the distribution of a solute between two immiscible solvents. This law, also known as the partition law, states that if a solute is added to the mixture of two immiscible solvents at a constant temperature, the solute is distributed between the two solvents in such a way that the ratio of solute concentrations in the solvents remains constant at equilibrium.
For extracting a solute from an aqueous phase into an organic...
For extracting a solute from an aqueous phase into an organic...