InFeST – ImageJ Plugin for Rapid Development of Image Segmentation Pipelines
In this paper we present a ImageJ plugin for easy development of image segmentation (clustering) pipelines. Main focus of our approach is to provide scientists working with various images (especially biological and medical ones) with a tool making development of segmentation pipelines fast and easy. We accomplish this by introducing an extra abstraction layer to the ImageJ image segmentation approach – the feature space projection – that enables us to work with complex image descriptors and manage, visualize and test them directly from the plugin. Furthermore we give three separate ways of expressing such projections – one based on Java language, one based on external scripting and one on our custom simple Micro Matrix Language. The plugin can also serve as a fast method of rapid prototyping of image filters while its full ImageJ macro support makes it really easy to include it in ones current image processing methods.
KeywordsimageJ image processing segmentation feature space projection
Unable to display preview. Download preview PDF.
- 1.Andlauer, T.F.M., Sigrist, S.J.: Quantitative analysis of Drosophila larval neuromuscular junction morphology. Cold Spring Harbor Protocols 2012(4), 490–493 (2012)Google Scholar
- 2.Carreras, I.A.: Advanced WEKA Segmentation (2011), http://fiji.sc/wiki/index.php/Advanced_Weka_Segmentation
- 3.Dello, S.A.W.G., Stoot, J.H.M.B., van Stiphout, R.S.A., Bloemen, J.G., Wigmore, S.J., Dejong, C.H.C., van Dam, R.M.: Prospective volumetric assessment of the liver on a personal computer by nonradiologists prior to partial hepatectomy. World Journal of Surgery 35(2), 386–392 (2011)CrossRefGoogle Scholar