Soybean aphid (Aphis glycines) is one of the most important insect pests of soybeans in North America. Insecticide application is performed if the aphids count exceeds the economic threshold of 250 per plant. Precise estimates of aphid densities are needed for field conditions to maximize insecticide application efficiency. The current method of identifying and counting aphids on a plant is a labor-intensive and time consuming process. The objective of this study was to use image processing technique to detect and count different sized soybean aphids on a soybean leaf. The trials were conducted with soybean plants grown in a greenhouse. Three sets of data were collected on different dates using replicate plants from 4 soybean varieties infested with a range of aphid densities. Images of infested soybean trifoliate leaves were captured with different cameras under 2 different illumination conditions with different cameras used across the different data sets. The images captured were processed in MATLAB™ R2014a software using the Image Processing Toolbox to identify and count aphids. In order to evaluate the accuracy of the algorithm, the aphids counted with the sensing system were compared to a count generated manually by a trained expert. The algorithm counting with SONY™ camera images correlated (r2=0.96) very well with manual counts. The misclassification percentage was low for most cameras with different resolutions under high illumination conditions. The results also showed that images captured with an inexpensive regular digital camera gave satisfactory results under high illumination conditions.