AUTOMATING THE IDENTIFICATION OF INSECTS - A NEW SOLUTION TO AN OLD PROBLEM

In this paper we describe a semi-automated digital image analysis syst em which is capable of discriminating five closely related species of Ichneumonidae. Specimens were distinguished by differences in their wi ngs. The system functions by (a) extracting the significant variation (principal components) among a training set of images of the same spec ies, (b) using these principal components to efficiently represent the morphology of wings of that species, and (c) exploiting the fact that images of the same species will share characteristic principal compon ents, while images of different species will not. Such an approach all ows the construction of modular species classifiers, to which like spe cies correlate strongly, while dissimilar species do not. A recognitio n accuracy of 94% was achieved when the system was tested on 175 image s of wings of the five ichneumonids. The wing images were caricatured to accentuate their venation and pigmentation patterns.