Efficient Plant Disease Detection Using Ceta‐Coyote Calibrated Deep Convolutional Neural Network Classifier

Early plant disease detection is crucial to mitigate the disease progression and avoid the negative impacts on crops. Consequently, this research proposes the Ceta‐Coyote calibrated deep convolutional neural network (CtCODCN) for early plant leaf disease detection. Specifically, the proposed approach exploits the inherent feature extraction capability of CtCODCN and effectively learns the complex relationship between features, leading to improved disease detection. Besides, the Ceta‐Coyote optimization (CtCO) adaptively fine‐tunes the hyperparameters of the CtCODCN and improves the overall detection accuracy. In addition, the Local Binary and Ternary Residual Wavelet (LBTRW) approach extracts the textural and color data via capturing the smaller intensity variations by utilizing the wavelet features, local binary pattern (LBP), local ternary pattern (LTP), and Residual network‐101 (ResNet‐101). Moreover, the proposed approach utilizes advanced mechanisms to minimize the computational complexity and the error rate of the plant disease detection. The extensive experiments demonstrate the proposed CtCODCN model's effectiveness, evaluated in terms of metrics, achieving 98.270% of accuracy, 98.680% of sensitivity, and 97.04% of specificity, respectively, while using real‐time tomato images. Further, the proposed approach obtains the metric values of 96.39%, 99.64%, and 96.14% while using real‐time soya bean images, demonstrating the optimized performance of the proposed model.