- Use Cases
The KNIME Image Processing Plugin allows you to read in more than 120 different kinds of images (thanks to the Bio-Formats API) and to apply well known methods on images, like preprocessing. segmentation, feature extraction, tracking and classification in KNIME. In general these nodes operate on multi-dimensional image data (e.g. videos, 3D images, multi-channel images or even a combination of them), which is made possible by the internally used ImgLib2-API.
Several nodes are available to calculate image features (e.g. zernike-, texture- or histogram features) for segmented images (e.g. a single cell). These feature vectors can then be used to apply machine learning methods in order to train and apply a classifier.
Currently the Image Processing Plugin for KNIME provides ca. 100 nodes for (pre)-processing, filtering, segmentation, feature extraction, various views (2D, 3D), etc. and integrations for various other image processing tools are available (see used and integrated libraries)
Future directions include a full, bidirectional integration of ImageJ2. Such an integration allow the users to use directly use/update ImageJ2 Plugins inside KNIME as well as recording and running KNIME Workflows in ImageJ2. Please see ImageJ2 Integration (BETA) for more information.
For the first steps please consider the KNIME Image Processing User Manual (incomplete draft!).
Some worklfows will optionally need the Math-Formula node for the further analysis which can be installed via the KNIME-update site. The example workflows have been created with the latest version of KNIME (currently KNIME 2.8).
Reproduced examples provided by CellProfiler
|07/10/2014||KNIME Image Processing 1.2.0 is now available. Please see http://tech.knime.org/forum/knime-image-processing/knime-image-processin... for details.|
|04/05/2014||Announcement of ImageJ-Ops: http://developer.imagej.net/2014/04/04/announcing-imagej-ops|
|02/11/2014||Another very small bugfix-release 1.1.2.|
|01/13/2014||The bugfix-release 1.1.1 is now available. Issues resolved with this version are listed here.|
|12/06/2013||KNIME Image Processing 1.1.0 has been released with KNIME 2.9.0. Besides several fixed bugs and improvements, a few new nodes have been added (see changelog). Moreover, the list of available tutoriales and example workflows has been extended.|
KNIME Tesseract (OCR) Integration Beta version released. The integrations enables users to read in images containing text and convert them to real characters, which then can e.g. can be processed using the KNIME Text Processing Extension.
For more details click here.
KNIME Image Processing 1.0.4 (KNIME 2.7) and KNIME Image Processing 1.0.5 (KNIME 2.8) released. Basically we fixed a lot of bugs but we also provide new nodes or enhancements of existing nodes, like Labeling to PNG Images, Labeling to RGB Img, Labeling Filter and Local Thresholder. Additionally we improved our MemoryManagement (available with KNIP 1.0.5) and the support of ColorTables.
If you face any problems, feel free to contact us via the forum or email.
KNIME Image Processing 1.0.3 released. We fixed several bugs and added new features to existing nodes. For instance we moved the functionality of the Image Group By Node to the standard GroupBy Node of KNIME. We also fixed several bugs in the VTK integration, the ImageJ integrations and the OMERO integration.
Remark: If you want to use KNIME Image Processing 1.0.3, you have to update to KNIME 2.7.
KNIME Image Processing 1.0.2 released. Several bugs were fixed and a new caching system for images and labelings was introduced.
KNIME Image Processing 1.0.1 released. Several bugs were fixed and especially some major memory leaks were closed!
Release of a first mature version of the KNIME Image Processing Extension 1.0.0. Within releases of this major version number (i.e. 1.*.*) we try hard to be backwards compatible whenever possible, e.g. such that all workflows created once (with a 1.*.* release) can be restored with the newest plugin version.
If you have suggestions, problems, etc. don't hesitate to contact us! We are glad to help you.
|Martin Horn||Nycomed Chair for Bioinformatics and Information Mining and Research School Chemical Biology, University of Konstanz|
|Christian Dietz||Nycomed Chair for Bioinformatics and Information Mining, University of Konstanz|