AUTHOR=Li Wenyong , Yang Zhankui , Lv Jiawei , Zheng Tengfei , Li Ming , Sun Chuanheng TITLE=Detection of Small-Sized Insects in Sticky Trapping Images Using Spectral Residual Model and Machine Learning JOURNAL=Frontiers in Plant Science VOLUME=Volume 13 - 2022 YEAR=2022 URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2022.915543 DOI=10.3389/fpls.2022.915543 ISSN=1664-462X ABSTRACT=Integrated pest management (IPM) is one of the most effective approaches at reducing the use of pesticides in greenhouses by utilizing the natural population distribution of insects in the field. Whitefly (Bemisia tabaci) and thrips (Frankliniella occidentalis) are two most prominent pests in greenhouse facilities of northern China. Traditionally, growers estimated the population of these pests by counting insects caught on sticky traps, not only a challenging task but also an extremely time-consuming one. To alleviate this situation, this study proposed an automated detection approach to meet the need for continuous monitoring of pests in greenhouse conditions. Whitefly and thrips were identified using a support vector machine classifier with an accuracy of 93.9% and 89.9%, a true positive rate of 93.1% and 80.1%, and a false positive rate of 9.9% and 12.3%, respectively. Identification performance was further tested via comparison between manual and automatic counting with a coefficient of determination, R2, of 0.9785 and 0.9582. The location and identification approach using a spectral residual model was shown to be a robust method for counting of whiteflies and thrips in natural greenhouse situations. This study clearly demonstrates the potential of developing a vision-based identification system to facilitate rapid gathering of information pertaining to numbers of the abundance of small-sized pests in greenhouse agriculture and make a reliable estimation of overall population density.