An Enhanced CNN-LSTM Based Hybrid Deep Learning Model for Corn Leaf Eye Spot Disease Classification

Due to the growing number of illnesses detected in the corn crop as a result of expanding demand and supply, corn leaf disease determinantion has been a primary point of concern for the researchers past decades. Corn leaf eye spot (CLES) is one such disease which has a drastic impact on corn crops growth. A system to find and to divide a 6000-image dataset of CLES disease in different categories based on four separate stages has been developed using a deep learning (DL) based hybrid model consisting of of convolutional neural networks (CNN) and another DL based concept labelled as long short-term memory (LSTM). The hybrid model’s application produced the best accuracy of 95.88% for the start stage of CLES illness severity stages multi-classification. In accordance to get accurate results, the suggested model is an efficient approach for image classification.