Abstract
Rice is a staple food in Asia and it contributes significantly to the Gross Domestic Product (GDP) of Malaysia and other developing countries. Brown Planthopper (BPH) causes high levels of economic loss in Malaysia. Identification of BPH presence and monitoring of its abundance has been conducted manually by experts and is time-consuming, fatiguing and tedious. Automated detection of BPH has been proposed by many studies to overcome human fallibility. However, all studies regarding automated recognition of BPH are investigated based on intact specimen although most of the specimens are imperfect, with missing parts have distorted shapes. The automated recognition of an imperfect insect image is more difficult than recognition of the intact specimen. This study proposes an automated, deep-learning-based detection pipeline, PENYEK, to identify BPH pest in images taken from a readily available sticky pad, constructed by clipping plastic sheets onto steel plates and spraying with glue. This study explores the effectiveness of a convolutional neural network (CNN) architecture, VGG16, in classifying insects as BPH or benign based on grayscale images constructed from Euclidean Distance Maps (EDM). The pipeline identified imperfect images of BPH with an accuracy of 95% using deep-learning’s hyperparameters: softmax, a mini-batch of 30 and an initial learning rate of 0.0001.
Highlights
A staple food in Malaysia and the most important crop in South East Asia, is being damaged by a rice planthopper complex which has become a challenge to farmers at the national level
Seven different convolutional neural network (CNN) structures were devised to create a novel pipeline for identification and classification of heterogenous brown planthopper (BPH) to test the filters
Based on empirical analysis and insight to accurately model the characteristics of BPH images, Euclidean Distance Maps (EDM) is selected for further evaluation with CNN VGG16 for BPH classification
Summary
A staple food in Malaysia and the most important crop in South East Asia, is being damaged by a rice planthopper complex which has become a challenge to farmers at the national level. One study developed an automated identification and counting system for different insect pests captured with light-traps and proposed a novel segmentation method for middle-sized touching insects from an image [20]. In trap-based pest monitoring especially with sticky pads, there are many challenges such as low image quality, inconsistencies derived from illumination, movement of the trap, movement of the pests, camera out of focus, the appearance of other objects, decay or damage to the insect, the presence of benign insects and many more. Various datasets have been utilized to push this area forward [30], [31]; yet decayed and damageed pest datasets are largely missing Concerned by this gap in research, this study proposes an identification and classification of imperfect pest’s pipeline with CNN as the image classifier
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
