<XML><RECORDS><RECORD><REFERENCE_TYPE>0</REFERENCE_TYPE><REFNUM>8081</REFNUM><AUTHORS><AUTHOR>Jalba,A.C.</AUTHOR><AUTHOR>Wilkinson,M.H.F.</AUTHOR><AUTHOR>Roerdink,J.B.T.M.</AUTHOR><AUTHOR>Bayer,M.M.</AUTHOR><AUTHOR>Juggins,S.</AUTHOR></AUTHORS><YEAR>2005</YEAR><TITLE>Automatic diatom identification using contour analysis by morphological curvature scale spaces</TITLE><PLACE_PUBLISHED>Machine Vision and Applications, Online First</PLACE_PUBLISHED><PUBLISHER>N/A</PUBLISHER><PAGES>-46 - -46</PAGES><LABEL>Jalba:2005:8081</LABEL><KEYWORDS><KEYWORD>Diatom identification - Mathematical morphology - Contour analysis - Curvature scale spaces - Multi-scale analysis - Decision tr</KEYWORD></KEYWORDS<ABSTRACT>Abstract A method for automatic identification of diatoms (single-celled algae with silica shells) based on extraction of features on the contour of the cells by multi-scale mathematical morphology is presented. After extracting the contour of the cell, it is smoothed adaptively, encoded using Freeman chain code, and converted into a curvature representation which is invariant under translation and scale change. A curvature scale space is built from these data, and the most important features are extracted from it by unsupervised cluster analysis. The resulting pattern vectors, which are also rotation-invariant, provide the input for automatic identification of diatoms by decision trees and k-nearest neighbor classifiers. The method is tested on two large sets of diatom images. The techniques used are applicable to other shapes besides diatoms.</ABSTRACT></RECORD></RECORDS></XML>