Fiji/ImageJ plugins — Directional Image Analysis (2D)

Daniel Sage · Center for Imaging and Biomedical Imaging Group, Ecole Polytechnique Fédérale de Lausanne (EPFL)

Benchmarking

Compares the distribution of orientation measured by six tools, all with the cubic-spline gradient and the structure-tensor window σ = 1 wherever the tool exposes those choices, on four images of the test set. Two comparisons:

• masked — only pixels inside the structure masks; without Directionality (no mask support);
• full — every pixel of the image, without the direct gradient, whose unsmoothed histogram is dominated by the flat background.

Results

Inside the structure mask

Over the whole image

The six tools

1. OrientationJ (Fiji) — the Java plugin; its saved orientation maps are binned here.
2. OrientationPy — the Python successor, 2D and 3D; spline gradient, σ = 1, fiber orientation.
3. GST operator — gst_operator.py, the features() of the minimal Python version: Gaussian-derivative gradient and Gaussian window, separable convolutions in space.
4. scikit-image — feature.structure_tensor (finite-difference gradient), same tensor formula.
5. direct gradient — the plugin run with σ = 0: the per-pixel angle perpendicular to the spline gradient, no tensor smoothing.
6. Directionality (Fiji) — local-gradient method, its own histogram; no mask support, whole image.

All tools share the OrientationJ angle convention (verified on calibration sinusoids): degrees in [−90, +90], counter-clockwise from the horizontal of the displayed image. Histograms: 180 bins of 1°, normalized to probability per bin.