Classification of yield affecting biotic and abiotic paddy crop stresses using field images

Abstract

On-time recognition and early control of the stresses in the paddy crops at the booting growth stage is the key to prevent qualitative and quantitative loss of agricultural yield. The conventional paddy crop stress identification and classification activities invariably rely on human experts to identify visual symptoms as a means of categorization. This process is admittedly subjective and error-prone, which in turn may lead to incorrect action in stress management decisions. The proposed work presented in this paper aims to develop an automated computer vision system for the recognition and classification of paddy crop stress types from the field images using the state-of-the-art color features. The work examines the impact of eleven stress types, two biotic and nine abiotic stresses, on five different paddy crop varieties during the booting growth stage using field images and analyzes the stress responses in terms of color variations using lower-order color moments and two visual color descriptors defined by the MPEG-7 standard, the Dominant Color Descriptor (DCD) and Color Layout Descriptor (CLD). The Sequential Forward Floating Selection (SFFS) algorithm has been employed to reduce the overlapping between the features. Three different classifiers, the Back Propagation Neural Network (BPNN), the Support Vector Machine (SVM), and the k-Nearest Neighbor (k-NN) have been deployed to distinguish among stress types. The average stress classification accuracies of 89.12%, 84.44% and 76.34% have been achieved using the BPNN, SVM, and k-NN classifiers, respectively. The proposed work finds application in the development of decision support systems and mobile apps for the automation of crop and resource management practices in the field of agricultural science.