Automated Mango Leaf Infection Classification using Weighted and Deep Features with Optimized Recurrent Neural Network Concept

ABSTRACT

Automatic detection and classification of mango leaf diseases is a complex task and manual detection system has issues like absence of experts, high cost, and lot of variations in the symptoms of the leaf disease. Hence we propose an automated solution in which the input images are gathered from standard resources and feature enhanced using contrast enhancement followed by segmentation using optimized Fuzzy C Means (FCM). Parameter optimization is done by Deviation-based Updated Dingo Optimizer (D-UDOX). The weighted feature selection is done by D-UDOX. The weighted features are provided to the classifier of Optimized Recurrent Neural Network (WO-RNN). Also, deep features are collected from a segmented image using ResNet-150. The classification with the extracted deep features is performed by WO-RNN. The parameter modification is done using D-UDOX for RNN and ResNet-150. The result of the recommended model achieves 96% accuracy and 93% F1-score which is relatively better than contemporary works.

KEYWORDS:

• Mango leaf disease detection
• optimized fuzzy C means-based segmentation
• deviation-based updated dingo optimizer
• weight optimized recurrent neural network
• ResNet-150

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

A. Selvakumar

Mr. A. Selvakumar is currently pursuing his full time research in the School of Computer Science and Engineering at Vellore Institute of Technology (VIT) – Chennai campus. His areas of research is Computer Vision, Image Processing and Deep Learning. He is currently working on the domain of Smart Agriculture.

A. Balasundaram

Dr. A. Balasundaram obtained his Doctor of Philosophy (Ph.D) in Computer Science and Engineering at Anna University, India. He completed his Masters in Computer Science and Engineering from B.S. Abdur Rahman, Crescent University, Chennai, India. He is currently working as Senior Assistant Professor in School of Computer Science and Engineering and is also associated with the Research Center for Cyber Physical Systems at Vellore Institute of Technology (VIT) – Chennai campus. He has an overall experience of 14 years of which he has over 9 years of Industrial experience working across MNCs like Cognizant Technology Solutions (CTS), Tata Consultancy Services (TCS) and iGATE Global solutions and 5 years of academic experience. He has received five best paper awards so far across international conferences. He has also received the Star Performer award at Cognizant Technology Solutions and Quality and Delivery Excellence award at iGATE Global solutions. He has 26 SCIE publications and 56 documents indexed in SCOPUS so far. He is also an active reviewer for reputed international SCIE journals of Elsevier, IEEE and Springer. He is also a guest editor for special issues in a couple of SCI journals. His areas of interest include Deep Neural Networks, Computer Vision, Video Analytics, Image and Video Processing, Artificial Intelligence, Data warehousing and Data Mining. His current research areas include Healthcare Intelligence, Medical Image Analysis and Smart Agriculture.