| Home

Overview


Original Research

AN ADAPTIVE THRESHOLDING AND HYBRID DEEP LEARNING MODEL FOR RICE BLAST FUNGAL DETECTION USING BOA & ROA ALGORITHM

VIDHYA M 1, Dr. DAHLIA SAM 2, and Dr. RAJAVARMAN V. N 3.

Vol 18, No 04 ( 2023 )   |  DOI: 10.17605/OSF.IO/TZB8R   |   Author Affiliation: Research Scholar, Department of Computer Science and Engineering, Dr. M. G. R. Educational and Research Institute, Chennai, Tamilnadu, India 1; Professor, Department of Information Technology, Dr. M. G. R. Educational and Research Institute, Chennai, Tamilnadu, India 2; Professor, Department of Computer Science and Engineering, Dr. M. G. R. Educational and Research Institute, Chennai, Tamilnadu, India 3.   |   Licensing: CC 4.0   |   Pg no: 1130-1147   |   Published on: 24-04-2023

Abstract

In agriculture research of automatic leaf disease detection is essential research topic as it may prove benefits in monitoring large fields of crops, and thus automatically detect symptoms of disease as soon as they appear on plant leaves. The term disease is usually used only for destruction of live plants. Agriculture not only provides food for the human existence, it is also a big source for the economy of any country. Millions of dollars are being spent to safeguard the crops annually. Insects and pests damage the crops and, thus, are very dangerous for the overall growth of the crop. One method to protect the crop is early fungal detection so that the crop can be protected from pest attack. The best way to know about the health of the crop is the timely examination of the crop. To obtain this an Intelligent IoT-aided deep learning system for the detection of rice blast fungal employing a hybrid heuristic algorithm is proposed. The proposed work encompasses with multiple stages that are explained as follows. Initially, the paddy images are gathered from the standard data sources. Next, the pre-processing of the collected images is done by adaptive mean filtering and contrast enhancement. Further, the adaptive thresholding and morphological operation are adopted for leaf segmentation purposes, where the threshold value is tuned by Fitness-based Billiards-inspired Rat Swarm Optimizer (FBRSO). Consequently, from the segmented image, the Region of Interest (ROI) is cropped. Finally, the cropped ROI is subjected to the Optimized MobileNetv2 and Multi-Scale Residual Attention Network (OMMRAN), where it includes MobileNetV2 and Multi-Scale Residual Attention Network, in which some of the hyper parameters are tuned by FBRSO approach. The performance is validated and compared with other existing approaches. Hence, the results demonstrate that it enhances the system robustness by easily detecting the rice diseases effectively. Thereby supports increased productivity and determine more precise result.


Keywords

Rice Blast Fungal Detection; IoT-assisted Image Collection; Adaptive Thresholding; Fitness-Based Billiards-Inspired Rat Swarm Optimizer; Region Of Interest; Optimized Mobilenetv2 And Multiscale Residual Attention Network