%0 Journal Article
%T Morphological feature selection and neural classification
%A D. Lefkaditis
%A G. Tsirigotis
%J Journal of Engineering Science and Technology Review
%D 2009
%I Kavala Institute of Technology
%X This paper presents the development procedure of the feature extraction and classification module of an intelligent sortingsystem for electronic components. This system was designed as a prototype to recognise six types of electronic componentsfor the needs of the educational electronics laboratories of the Kavala Institute of Technology. A list of features that describethe morphology of the outline of the components was extracted from the images. Two feature selection strategies were examinedfor the production of a powerful yet concise feature vector. These were correlation analysis and an implementationof support vector machines. Moreover, two types of neural classifiers were considered. The multilayer perceptron trainedwith the back-propagation algorithm and the radial basis function network trained with the K-means method. The best resultswere obtained with the combination of SVMs with MLPs, which successfully recognised 92.3% of the cases.
%K Recognition
%K Neural Network
%K Classification
%U http://www.jestr.org/downloads/volume2/fulltext2709.pdf