C. Sommer

This study investigates the use of texture, i.e. the grey level variation in digital images, as a basis for identification of strongylid eggs. Texture features were defined by algorithms applied to digital images of eggs from the bovine parasitic nematodes, Ostertagia ostertagi, Cooperia oncophora, and Oesophagostotnum radiatum. The resulting data served to establish classification criteria by linear discrimination analysis, and the criteria were subsequently evaluated by crossvalidations. From 25 texture features, ten features were selected by their significant discriminatory powers. Using a classification criterion based on these ten texture features, an average of 91.2% of eggs from the three species were correctly classified. All O. radiatum eggs were correctly classified, 11.8% of O. ostertagi and C. oncophora were reciprocally misclassified, and 2.9% of O. ostertagi were identified as O. radiatum. When the ten texture features were used singly an average of 51.2 to 37.9% of the species could be classified correctly. When texture was used together with the shape and size features, a higher percentage of eggs were correctly classified compared with the classification based on either texture, or shape and size. Hence, all O. radiatum were correctly classified as well as 88.3% of O. ostertagi and 91.2% of C. oncophora, resulting in an average of 93.1% correctly classified eggs. The rapid and accurate measurements of texture features may serve as a basis for identification or enhance performance of classification criteria based on egg shape/size.

This study reports on morphological variability of Eimeria species, which may be given either by drawings or as quantitative data. The drawings may be used to facilitate identification by eye of ‘unknown’ Eimeria specimens, whereas quantitative data may serve as a reference set for identification by multivariate statistical techniques. The morphology of 810 Eimeria specimens was defined in binary (b/w) digital images by pixels of their oocyst outline. A Fourier transform of pixel positions yielded size and shape features. To classify coccidia, the quantitative data were employed in an agglomerative clustering by average linkage algorithm with equal weight assigned to size and shape. An inverse Fourier transform served to reconstruct oocyst outlines, i.e. outlines of average shape and size, from mean values of features in resulting clusters. Clusters were subsequently identified based on their average morphology by comparison with drawings of species in an earlier taxonomical work. Five hundred oocyst outlines were simulated for each cluster representing a species, and shape/size variability was presented in contour diagrams. Differences in species shapes, and correspondence in length and width, were seen after reconstruction by inverse Fourier transform and comparison with earlier studies.