Two simple filters are contributed to compute the exponential of an image: the first one to raise the image to the power of a constant, the other one to raise the image to the power of the values provided in another image.


Exponentiation Filters

This document describes the implementation of a class for the Insight Toolkit (ITK) that takes an image
with multi-component pixels and outputs a scalar image for each component. This can be useful when
examining images of vectors, tensors, etc. This ﬁlter may be easier to use and require fewer pixel visitations than an itk::ImageAdaptor with a similar purpose, but it requires additional memory allocation.


An ITK Class that Splits Multi-Component Images

In this article we describe higher order accurate derivative and gradient image ﬁlters for the InsightToolkit. These filters are central difference-based numerical derivative approximations that account for additional Taylor series terms and are based on the expressions given by Khan and Ohba.


Higher Order Accurate Derivative and Gradient Calculation in ITK

Recently, Birkfellner et al. proposed a novel image-to-image merit function (stochastic rank correlation, SRC) for robust intensity-based 2D/3D image registration. In this work, we summarize the basic idea of SRC, and present a generic ITK-based implementation of this image-to-image metric including tests for software veriﬁcation. Moreover, we provide two simple examples that demonstrate the usage of this metric: a) within the native ITK 2D/3D image registration method, and b) within a recently published extended ITK-based 2D/3D registration framework. It is, however, important to note, that this paper neither covers a comprehensive evaluation of SRC, nor a comparison with other metrics. It rather shows that SRC appears to succeed on a femoral and a porcine data set in the course of ITK-based 2D/3D image registration.


An ITK-based Implementation of the Stochastic Rank Correlation (SRC) Metric

This document presents a system to "scribble" on an image to mark foreground and background pixels and then feed these pixels to a graph cuts segmentation technique. The interaction is done using the Visualization Toolkit and the processing is done using the Insight Toolkit. The graph cut function itself is the maxflow-v2.21 algorithm written by Yuri Boykov and Vladimir Kolmogorov. This version of their algorithm is released under a GPL license. 

The code for this paper can be found here: 
https://github.com/daviddoria/InteractiveImageGraphCutSegmentation/commit/259cd239169c5ea8c44cc68908886eca10cc8239

Updates will be published here: https://github.com/daviddoria/InteractiveImageGraphCutSegmentation

Note: You must use the latest git version of VTK as of the date of this publication to avoid compiler errors due to newly added functions.

Interactive Image Graph Cut Segmentation

Topological considerations for segmentation results are important for such applications as proper brain segmentation from digital image data. We present an enhancement of the FastMarchingImageFilter which allows for topologically constrained evolution of the level set. Identical to the original functionality of the FastMarchingImageFilter, the evolution of the level set of a single or multiple genus zero, well-composed seed objects proceeds according to the specified parameters. With our proposed enhancements, the user can either choose to prevent the level set from merging with itself such that the original topology of the initial seed object(s) is not violated or that no handles are created during the evolution process. However, in contrast to earlier approaches which relied on the concept of the simple point implicitly requiring the definition of a user-specified foreground/background connectivity, we use the related, but more restrictive concept of well-composed sets to topologically constrain the evolution of the level set. Utility of our submission is demonstrated on both 2-D and 3-D brain images. Note that this submission is a companion piece to a more theoretical discussion of our work given in [9]

Escher's Ants as Metaphor: Topological Marching for the Well-Composed, Genus Zero Crowd

This paper describes an intensity image filter for computing the variance of pixel values contained within a neighborhood centered at each input pixel. The output image contains the calculated variance at each input pixel location. Variance calculations can be restricted by setting an image mask. This paper is accompanied with source code for the filter and test, test images and parameters, and expected output images. 

Variance Image Filter

This paper describes a set of pixel accessors that transform RGB pixel values to a different color space. Accessors for the HSI, XYZ, Yuv, YUV, HSV, Lab, Luv, HSL, CMY, and CMYK color spaces are provided here. This paper is accompanied with source code for the pixel accessors and test, test images and parameters, and expected output images. 

Note: Set() methods are incorrect. Will provide revision by 12.17.2010.

RGB Image Color Space Transformations

This paper describes an intensity image filter for computing the entropy of pixel values contained within a neighborhood centered at each input pixel. The output image contains the calculated entropy for each input pixel location. This paper is accompanied with source code for the filter and test, test images and parameters, and expected output images. 

Entropy Image Filter

Distributed anisotropic diffusion provides a wrapper program around ITK's anisotropic diffusion filters that allows an input image to be spread across the memory of several computers and the processors of all of the computers to work simultaneously on the output. Distributed anisotropic diffusion allows the Visible Woman Head dataset to be smoothed with 100 iterations of the vector gradient magnitude anisotropic diffusion filter in 47 minutes on an 8 node 64 core cluster versus 53 minutes for just 10 iterations of standard vector gradient magnitude anisotropic diffusion on a single node.