Component

This workflow classifies objects based on object-level features (e.g. intensity based, morphology based, etc) and user annotations. It needs segmentation images besides the raw image data. Segmentation images can be obtained from ilastik pixel classification, or binary segmentation images from other tools. Within the object classification, one can prefilter objects through thresholds (on pixel probability image) or object sizes (on segmentation image). Outputs are predicted classification label images. Selected features can also be exported. Advanced users also have possibilities to add customized (object) features for classification in a simple plugin fashion through python scripts.

Simple spatial filters can be used to suppress noise in raw image data (i.e. by averaging intensities). The best choice of filter depends on the nature of the noise, but Gaussian filtering works well for Poisson noise (i.e. commonly observed photon-counting shot noise); whereas a median filter is ideal for salt-and-pepper noise. A larger filter radius leads to stronger noise suppression but more blurring. The URL above describes the simple 2D spatial filters available in ImageJ, but similar filters are available in most software. For 3D data, 3D versions of these filters work best (since there are more pixels to average within the same radius).

This tool allows for extraction of image series from Olympus Slide Scanners. These VSI files usually contain several images that are too big to load into memory (>50k x 50k pixels). It was written and tested on Fiji and is available from a Fiji Update Site: http://fiji.sc/List_of_update_sites

The Macro processes a composite picture in ImageJ/Fiji and outputs a color-balanced merged RGB image.

To calculate the white balance, a rectangle at coordinates (x=100, y=100) and of size (w=100 pixels, h=100 pixels) is used. These values can be changed to make sure that a background region is taken for the calculation in the line: makeRectangle(100,100,100,100). The user could be prompted to draw the region by removing the signs // in the line: // waitForUser("Please draw a region in the background");

If your images are corrupted by a strong dominant Gaussian noise you can try this simple filter. It is based on thresholding in the DCT domain and is usually vastly superior to typical Gaussian filtering in term of detail preservation / noise reduction trade-off. The filter unfortunately introduces some block like artifacts that can be mitigated by averaging out overlaping shifted windows (as implemented in the Matlab version) and performing maximum intensity projection after the filtering: As such the filter is way more adapted to process 3D stacks that you plan to maximum intensity project than to process single z slice images.