An approach to automatic classification of Culicoides species by learning the wing morphology

Abstract

Fast and accurate identification of biting midges is crucial in the study of Culicoides -borne diseases. In this work, we propose a two-stage method for automatically analyzing Culicoides (Diptera: Ceratopogonidae) species. First, an image preprocessing task composed of median and Wiener filters followed by equalization and morphological operations is used to improve the quality of the wing image in order to allow an adequate segmentation of particles of interest. Then, the segmentation of the zones of interest inside the biting midge wing is made using the watershed transform. The proposed method is able to produce optimal feature vectors that help to identify Culicoides species. A database containing wing images of C. obsoletus , C. pusillus , C. foxi , and C. insignis species was used to test its performance. Feature relevance analysis indicated that the mean of hydraulic radius and eccentricity were relevant for the decision boundary between C. obsoletus and C. pusillus species. In contrast, the number of particles and the mean of the hydraulic radius was relevant for deciding between C. foxi and C. insignis species. Meanwhile, for distinguishing among the four species, the number of particles and zones, and the mean of circularity were the most relevant features. The linear discriminant analysis classifier was the best model for the three experimental classification scenarios previously described, achieving averaged areas under the receiver operating characteristic curve of 0.98, 0.90, and 0.96, respectively.

MosCla app: An android app to classify Culicoides species

“…For our study, left and right wings were used indistinctly because the systematic selection of one side may bias the results in case of differential directional asymmetry between species. The comparison of wings from catalogs and original descriptions with status (left or right) are mostly unknown and the distribution and color of spots on both wings are similar [17]. Thus, we formed an experimental dataset with a total of 45 and 42 wing images of Culicoides Pusillus and Culicoides Obsoletus, respectively.…”

“…The Culicoides species classification is obtained by considering the morphological characteristics of their wings. We used a set of computer vision functions for digital image processing to obtain morphological features from the wings images [17] and a machine learning classifier to distinguish amongst the species under analysis. Thus, the image preprocessing, wing particle detection and zones segmentation, feature calculation and selection, and the machine learning classifier (MLC) are essential aspects to describe here.…”

“…3) Feature calculation: a set of seven morphological features [17] (number of particles, number of zones, elongation, solidity, circularity, hydraulic radius, and eccentricity) were computed from the binary images. All the values were normalized using the min-max method [21] to bring them into the range [0,1].…”

Automatic ladybird beetle detection using deep-learning models

“…The method was validated on a data set of 293 samples, reaching an ACC score of 78.79%. Similarly, in [ 29 ], a morphological analysis of biting midges wing was carried out to discern among four different species. The linear discriminant analysis model was the best classifier on a data set with 192 samples, obtaining an AUC score of 0.96.…”

Attraction and Repellent Behaviors of Culicoides Biting Midges toward Cow Dung, Carbon Dioxide, and Essential Oils

“…Culicoides biting midges (Diptera: Ceratopogonidae) are the smallest blood-sucking arthropods and their length rarely exceeds 3 mm [ 1 ]. The wings of adult Culicoides display various patterns by species, which can be useful for classifying the species [ 2 ]. Culicoides are vectors that transmit epizootic arthropod-borne viruses (arboviruses) such as the Akabane virus, the bovine ephemeral fever, the bluetongue virus, and the Schmallenberg virus to livestock [ 1 , 3 , 4 ].…”