Gaussian regressed generative adversarial network based hermitian extreme gradient boosting for plant leaf disease detection

Abstract

Identifying diseases from images of plant leaves is one of the most important research topics in the field of agriculture. Cassava is a rich plant in protein and vitamins, particularly in the leaves, and it is also employed as a substitute for rice. Since, the leaf is the most susceptible portion of a plant, it is said to be affected easily in comparison with the other parts. Therefore, the detection of plant leaf diseases may decrease the possibility that the plant will undergo additional damage. Many research works have been designed for Cassava plant leaf disease diagnosis, but the accuracy of leaf disease detection was not improved with the minimum amount of error and time. In this paper, a novel technique called Gaussian Regressed Generative Adversarial Networks based Hermitian Extreme Gradient Boosting (GRGAN-HEGB) is introduced for accurate cassava plant disease detection. The GRGAN-HEGB technique is composed of three parts: preprocessing, feature extraction, and classification. At first, the numbers of real cassava leaf images are collected from the Cassava Disease Classification dataset. Then, the collected cassava leaf images are preprocessed using the Gaussian Process Regressed Generative Adversarial Network (GPR-GAN) model. Feature extraction is performed by employing Continuous Hermitian Contingency Correlation (CH-CC) model to extract the most influential features such as texture, shape, and colour for disease pattern detection. Lastly, the Cophenetic Optimized Extreme Gradient Boosting classification process is performed to classify the input cassava leaf images with extracted features. As a result, the accuracy of leaf disease detection is improved with a short processing time. Experimental evaluation is carried out using the cassava disease classification dataset by considering different metrics such as disease detection accuracy, disease detection time, precision, and recall. The statistical results confirm that the proposed technique achieves higher accuracy by 12 %, precision by 2 %, and recall by 2 % with minimum disease detection processing time by 10 % than the conventional classification methods.