Skip to Main Content
A technique is described which may be employed to establish a fully automated system for the recognition of airborne pollens. As different pollen taxa have only marginal differences, a full 3D volume data set of the pollen grain was recorded with a confocal laser scanning microscope (LSM) at a voxel size of about (0.2 μm)3. This represents an intrinsic and complete data set. 14 invariant gray-scale features based on an integration over the 3D Euclidian transformation group with nonlinear kernels were extracted from these volume data sets. The classification was done with support vector machines. The use of these general gray scale features allows one to easily adapt the system to other objectives (e.g., pollen of a special area) or even other objects than pollen (e.g., spores, bacteria, etc.) just by exchanging the reference database. When using a reference database with the 26 most important German pollen taxa (385 samples), the recognition rate is 92%. With a special database for allergological purposes recognizing only Corylus, Alnus, Betula, Poaceae, Secale, Artemisia and "allergological nonrelevant", the recognition rate is 97.4%.