Automatic identification and counting of small size pests in greenhouse conditions with low computational cost Chunlei Xia a,b , Tae-Soo Chon c , Zongming Ren d , Jang-Myung Lee b, ⁎ a The Research Center for Coastal Environmental Engineering and Technology of Shandong Province, Yantai Institute of Coastal Zone Research, Chinese Academy of Sciences, Yantai 264003, P.R. China b School of Electrical Engineering, Pusan National University, Busan (Pusan) 609–735, Republic of Korea c Department of Biological Sciences, Pusan National University, Busan (Pusan) 609–735, Republic of Korea d College of Life Science, Shandong Normal University, Jinan, 250014, P. R. China abstract article info Article history: Received 31 March 2014 Received in revised form 12 September 2014 Accepted 15 September 2014 Available online xxxx Keywords: Pest monitoring Computational complexity Mahalanobis distance Greenhouse management We propose an automatic pest identification method suitable for large scale, long term monitoring for mobile or embedded devices in situ with less computational cost. A procedure of segmentation and image separation was devised to identify common greenhouse pests, whiteflies, aphid and thrips. Initially, the watershed algorithm was used to segment insects from the background (i.e., sticky trap) images. Color feature of the insects were sub- sequently extracted by Mahalanobis distance for identification of pest species. Accuracy and computational costs were evaluated across different image resolutions. The correlation of determination (R 2 ) between the proposed identification scheme and manual identification were high, showing 0.934 for whitefly, 0.925 for thrips, and 0.945 for aphids even with low resolution images. Comparing with the conventional methods, pests were effi- ciently identified with low computational cost. Optimal image resolution for species identification regarding long-term survey was discussed in practical aspect with less computational complexity. © 2014 Elsevier B.V. All rights reserved. 1. Introduction Pest is one of the critical factors causing economic loss in greenhouse where crops are cultivated in congested conditions in limited areas. In- tegrated Pest Management (IPM) has been widely applied to the agri- cultural practices to achieve minimizing crop damage, environmental contamination, and economic loss concurrently (Allen and Rajotte, 1990). One of prerequisites for IPM, however, is to accurately investi- gate population densities of pest species. Objective identification of pest species and density estimation is essential for initiating any pest management program (Qiao et al., 2008). One of the most common methods for pest detection in greenhouse, however, has been mainly based on conventional sticky traps (Pinto-Zevallos and Vänninen, 2013). Counting the number of insects on sticky traps has been conven- tionally relied on visual judgment by humans (Wise et al., 2007). Due to complexity of insect morphology automatic identification has been considered as a difficult task. Especially with the small size pests, such as greenhouse insect pests, the efficiency of human counting is low and unreliable depending on observation conditions of observers (e.g., identification skill, fatigue). Therefore, implementation of auto- matic pest identification is vital to the modern agricultural production. Since the automatic pest identification system is mainly based on the visual information (e.g., pest shape, color), it would not produce any extra disturbances to environment including chemical/physical pollu- tions and could not raise degradation issues to the ecosystems. The eco- logical intensification could be achieved by employing the automatic pest identification in the agricultural practices that maximizes the pro- duction while minimizing anthropogenic environmental impacts con- currently (Bommarco et al., 2013). Since the last decade computer hardware and imaging devices sig- nificantly contributed to automatic identification of biological organ- isms (Gaston and O'Neill, 2004; MacLeod et al., 2010). Detection of agricultural pests has garnered special attention, especially greenhouse pests such as whitefly(Bemisia tabaci Genn), aphids (Aphis gossypii Glover) and thrips (Thrips tabaci L.). These greenhouse pests are small in size and difficult to recognize, but are critical in causing damage under congested cultivation conditions. Martin and Thonnat (2007) presented a cognitive vision approach that adjusts optimal parameters for segmenting whitefly out of leaves based on adaptive learning tech- niques. By employing machine vision and knowledge-base techniques, Boissard et al. (2008) proposed a multidisciplinary cognitive vision ap- proach applicable to whitefly detection in rose in situ. Solis Sánchez et al. (2009) utilized the geometric features (e.g., eccentricity, area size) to whitefly scouting by segmenting the insects from sticky trap images. Xia et al. (2012) developed a multifractal dimension to detect whitefly in situ, which was robust to field noise such as unequal illumi- nation changes and light reflections on trap surface. Ecological Informatics xxx (2014) xxx–xxx ECOINF-00520; No of Pages 8 ⁎ Corresponding author. Tel.: +82 51 510 2378. E-mail address: jmlee@pusan.ac.kr (J.-M. Lee). http://dx.doi.org/10.1016/j.ecoinf.2014.09.006 1574-9541/© 2014 Elsevier B.V. All rights reserved. Contents lists available at ScienceDirect Ecological Informatics journal homepage: www.elsevier.com/locate/ecolinf Please cite this article as: Xia, C., et al., Automatic identification and counting of small size pests in greenhouse conditions with low computational cost, Ecological Informatics (2014), http://dx.doi.org/10.1016/j.ecoinf.2014.09.006