scikit-image: image processing in Python

Abstract

scikit-image is an image processing library that implements algorithms and utilities for use in research, education and industry applications. It is released under the liberal Modified BSD open source license, provides a well-documented API in the Python programming language, and is developed by an active, international team of collaborators. In this paper we highlight the advantages of open source to achieve the goals of the scikit-image library, and we showcase several real-world image processing applications that use scikit-image. More information can be found on the project homepage, .

Will It Blend? Visualization and Accuracy Evaluation of High-Resolution Fuzzy Vegetation Maps

“…GDAL was used to provide interoperability with the GIS raster and vector data formats used for mapping, and Scikit-image library for image processing tasks (Van Der Walt et al, 2014). Visualization rendering, colour blending and confusion matrices were computed directly in Python code, and dominance profiles were plotted with help of MatPlotLib library.…”

An ALMA Survey of DCN/H13CN and DCO+/H13CO+ in Protoplanetary Disks

“…Likewise, phase selfcalibration of the SPWs covering the DCN and DCO + lines was performed using solutions obtained from combining the line-free portions of the SPWs in the lower sideband of the 1.4 mm setting and phase self-calibration of the IM Lup HCN data was performed using solutions from combining the line-free portions of the upper sideband SPWs. As a preliminary step for choosing CLEAN and spectral extraction masks for the lines, the radius of the millimeter dust disk was estimated by using the Python package scikit-image (van der Walt et al 2014) to fit ellipses to the 3σ contours of the 258 GHz continuum images, where σ is the rms measured from a signal-free portion of the continuum map. Since the radii, listed in Table 5, are based on the detected extent of the millimeter dust emission, they are not necessarily similar to the often-derived characteristic radius values, which describe the radius at which the surface density transitions between a power-law profile in the inner disk and an exponentially declining profile in the outer disk (Hughes et al 2008).…”

Quantifying disorder in colloidal films spin-coated onto patterned substrates

“…To do so, in each AFM image, the positional coordinates of the particles are obtained [a sample of which is shown in Fig. 1(c) with tiny spots at the centroid of each detected particle], using home-made routines which are based on the scikit-image processing library [39]. First, we observed from the pair correlation function g(r) that there is no long-range translational order in any of the deposits, and that they were qualitatively indistinguishable.…”