A method for counting and classifying aphids using computer vision

Aphids are insects that attack crops and cause damage directly, by consuming the sap of plants, and indirectly, by vectoring microorganisms that can cause diseases. Cereal crops are hosts for many aphid species, including Rhopalosiphum padi (an economically important aphid species). Recording and classifying aphids are necessary for evaluating and predicting crop damage. Thus, serving as a basis for decision making on the utilization of control measures. It can also be useful to evaluate plant resistance to aphids. Traditionally, the recording process is manual and depends on magnification and well-trained staff. The manual counting is also a time-consuming process and susceptible to errors. With this in mind, this paper presents a method and software to automate the counting and classification of Rhopalosiphum padi using image processing, computer vision, and machine learning methods. The text also presents a comparison of manually counts from experts and values obtained with the software, considering 40 samples. The results showed strong positive correlation in counting and classification (r, = 0.92579) and measurement (r = 0.9799). Concluding, the software proved to be reliable and useful to aphid population monitoring studies.