Identification of Cotton Leaf Lesions Using Deep Learning Techniques

Abstract

The use of deep learning models to identify lesions on cotton leaves on the basis of images of the crop in the field is proposed in this article. Cultivated in most of the world, cotton is one of the economically most important agricultural crops. Its cultivation in tropical regions has made it the target of a wide spectrum of agricultural pests and diseases, and efficient solutions are required. Moreover, the symptoms of the main pests and diseases cannot be differentiated in the initial stages, and the correct identification of a lesion can be difficult for the producer. To help resolve the problem, the present research provides a solution based on deep learning in the screening of cotton leaves which makes it possible to monitor the health of the cotton crop and make better decisions for its management. With the learning models GoogleNet and Resnet50 using convolutional neural networks, a precision of 86.6% and 89.2%, respectively, was obtained. Compared with traditional approaches for the processing of images such as support vector machines (SVM), Closest k-neighbors (KNN), artificial neural networks (ANN) and neuro-fuzzy (NFC), the convolutional neural networks proved to be up to 25% more precise, suggesting that this method can contribute to a more rapid and reliable inspection of the plants growing in the field.

Artificial-intelligence and sensing techniques for the management of insect pests and diseases in cotton: a systematic literature review

“…Recently, Caldeira et al . (2021) used CNN (GoogleNet and Resnet50 with 86.6 and 89.2% of accuracy, respectively) for cotton disease classification. The results were better for the processing of images compared with traditional approaches such as SVM, KNN, ANN and neuro-fuzzy.…”

“…More recent works have focused on the use of CNN, which has led to greater accuracy in the classification of pests and diseases (Caldeira et al ., 2021; Liang, 2021). The results were better compared with traditional approaches for the processing of images.…”

“…Revathi and Hemalatha (2014) 3). Nonetheless, in 2021, CNNs got the best performance (Caldeira et al, 2021;Liang, 2021).…”

Circle Fitting Based Image Segmentation and Multi-Scale Block Local Binary Pattern Based Distinction of Ring Rot and Anthracnose on Apple Fruits

“…Deep learning has been applied to plant disease image recognition ( Tan et al, 2015 ; DeChant et al, 2017 ; Lu et al, 2017 ; Liu et al, 2018 ; Bansal et al, 2021 ; Caldeira et al, 2021 ; Chen et al, 2021 ; Trivedi et al, 2021 ; Narmadha et al, 2022 ). It can reduce image preprocessing operations and achieve satisfactory disease recognition results.…”

“…Image processing technology has been widely applied in the diagnosis, identification, and monitoring of plant diseases ( Sankaran et al, 2010 ; Barbedo, 2016 ; Vishnoi et al, 2021 ), such as wheat diseases ( Li et al, 2012 ; Johannes et al, 2017 ; Deng et al, 2021 ), maize diseases ( DeChant et al, 2017 ; Chen et al, 2021 ), rice diseases ( Phadikar et al, 2013 ; Lu et al, 2017 ; Narmadha et al, 2022 ), cotton diseases ( Camargo and Smith, 2009 ; Caldeira et al, 2021 ), soybean diseases ( Pires et al, 2016 ; Shrivastava et al, 2017 ; Araujo and Peixoto, 2019 ), cucumber diseases ( Vakilian and Massah, 2013 ; Zhang S. W. et al, 2017 ; Kainat et al, 2021 ), tomato diseases ( Yamamoto et al, 2017 ; Trivedi et al, 2021 ), grape diseases ( Tian et al, 2007 ; Oberti et al, 2014 ; Zhu et al, 2020 ), and citrus diseases ( Pydipati et al, 2006 ; Sankaran et al, 2013 ). Moreover, image processing technology has been used to make disease severity assessments ( Li et al, 2011 ; Barbedo, 2014 ; Vieira et al, 2014 ; Shrivastava et al, 2015 ; Ganthaler et al, 2018 ), conduct pathogen identification ( Chesmore et al, 2003 ; Deng et al, 2012 ; Wang et al, 2021 ), and perform automatic counting of pathogen spores ( Li X. L. et al, 2013 ; Li et al, 2017 ).…”