Identification and Counting of Soybean Aphids from Digital Images Using Shape Classification

Abstract

Abstract. Soybean aphids are serious pests, causing negative yield impacts in the crop. Assessing their population is essential for making appropriate pesticide application decisions. Manual identification and counting, which is commonly performed to determine the economic threshold level, is time-consuming, laborious, and causes visual fatigue. In this study, an automatic image processing method was developed to identify and count aphids as well as exoskeletons and leaf spots on soybean leaves based on shape analysis. Aphid-infested soybean trifoliates were obtained at three infestation rates (low, medium, and high). Images of the front sides of the leaves were captured in the laboratory with three cameras (digital single-lens reflex or DSLR, consumer-grade digital, and smartphone) under two lighting conditions (direct and indirect). The shape parameters considered were area, perimeter, convex area, eccentricity, aspect ratio, solidity, hollowness, and roundness. Among the shape parameters tested, hollowness was the best in identifying aphids and was therefore used for developing the object classification algorithm. Of the three cameras tested, images from the consumer-grade digital camera produced the best identification accuracy (>82.4%), followed by the DSLR camera (>81.2%) and smartphone camera (>37.9%). Statistical analysis revealed that the accuracies did not differ significantly under different lighting conditions (p = 0.43), but the accuracies differed for the smartphone camera compared to the DSLR and consumer-grade digital cameras (p = 8.87 × 10-10). The results of automatic and manual counting were very well correlated (r = 0.92). The automatic image processing method achieved more rapid counting (<2 s per image after loading the image) compared to manual counting (~5 min per image). The developed approach for aphid identification and counting can be easily applied to other pest identification issues with minor modifications to the algorithm. Keywords: Aphids, Classification, Image processing, Segmentation, Shape analysis, Soybean.