Identification of Aedes aegypti and Aedes albopictus eggs based on image processing and elliptic fourier analysis

Abstract

AbstractDengue hemorrhagic fever is a worldwide epidemic caused by dengue virus and spread by infected female mosquitoes. The two main mosquito species vectors of the dengue virus are Aedes aegypti and Aedes albopictus. Conventionally, the identification of these two species’ egg is time-consuming which makes vector control more difficult. However, although attempts on efficiency improvements by providing automatic identification have been conducted, the earliest stage is at the larval stage. In addition, there are currently no studies on classifying to distinguish the two vectors during the egg stage based on their digital image. A total of 140 egg images of Aedes aegypti and Aedes albopictus were collected and validated by rearing them individually to become adult mosquitoes. Image processing and elliptic Fourier analysis were carried out to extract and describe the shape difference of the two vectors’ eggs. Machine learning algorithms were then used to classify the shape signatures. Morphometrically, the two species’ eggs were significantly different, which Aedes albopictus were smaller in size. Egg-shape contour reconstructions of principal components and Multivariate Analysis of Variance (MANOVA) revealed that there is a significant difference (p value $$< 0.000$$ < 0.000 ) in shape between two species’ eggs at the posterior end. Based on Wilk’s lambda of the MANOVA results, the classification could be done using only the first 3 principal components. Classification of the test data yielded an accuracy of 85.00% and F1 score 84.21% with Linear Discriminant Analysis applying default hyperparameter. Alternatively, k-Nearest Neighbors with optimal hyperparameter yielded a higher classification result with 87.50% and 87.18% of accuracy and F1 score, respectively. These results demonstrate that the proposed method can be used to classify Aedes aegypti and Aedes albopictus eggs based on their digital image. This method provides a foundation for improving the identification and surveillance of the two vectors and decision making in developing vector control strategies.