3D

The OpenCV CUDA module is a set of classes and functions to utilize CUDA computational capabilities. It is implemented using NVIDIA* CUDA* Runtime API and supports only NVIDIA GPUs. The OpenCV CUDA module includes utility functions, low-level vision primitives, and high-level algorithms. The utility functions and low-level primitives provide a powerful infrastructure for developing fast vision algorithms taking advantage of CUDA whereas the high-level functionality includes some state-of-the-art algorithms (such as stereo correspondence, face and people detectors, and others) ready to be used by the application developers.

The CUDA module is designed as a host-level API. This means that if you have pre-compiled OpenCV CUDA binaries, you are not required to have the CUDA Toolkit installed or write any extra code to make use of the CUDA.

nctuTW is a "high-throughput computer method of reconstructing the neuronal structure of the fruit fly brain. The design philosophy of the proposed method differs from those of previous methods. We propose first to compute the 2D skeletons of a neuron in each slice of the image stack. The 3D neuronal structure is then constructed from the 2D skeletons. Biologists tend to use confocal microscopes for optimal images in a slice for human visualization; and images in two consecutive slices contain overlapped information. Consequently, a spherical object becomes oval in the image stack; that is, neurons in the image stack do not reflect the true shape of the neuron. This is the main reason we chose not to work directly on the 3D volume.

The proposed method comprises two steps. The first is the image processing step, which involves computing a set of voxels that is a superset of the 3D centerlines of the neuron. The shortest path graph algorithm then computes the centerlines. The proposed method was applied to process more than 16 000 neurons. By using a large amount of reconstructions, this study also demonstrated a result derived from the reconstructed data using the clustering technique." (Extracted from reference publication)

Illustrative image shows gold standard (top) and method results (bottom). 

This plugin filters a 3D image stack (or 2D image) to produce a score for how "tube-like" each point in the image is. This is useful as a preprocessing step for tracing neurons or blood vessels, for example. For 3D image stacks, the plugin uses the eigenvalues of the Hessian matrix to calculate this measure of "tubeness", using a metrics mentioned in Sato et al 1997 ¹: if the larger two eigenvalues (λ₂ and λ₃) are both negative then value is √(λ₂λ₃), otherwise the value is 0. For 2D images, if the large eigenvalue is negative, we return its absolute value and otherwise return 0.

This plugin is now bundled as part of Fiji.