Enhancing Rice Leaf Disease Classification: A CNN-SVM Approach

According to precision, recall, the F1-S support, support scale, and accuracy scores, the abstract gives a brief description of how well the classification model performed in classifying different rice leaf diseases. Precision ratings are continuously high, averaging between 93% and 94% for distinct illness classes, reflecting the model's efficiency in making accurate positive predictions. This implies that the model's predictions about a certain disease are very likely to be true. Recall values, which measure the model's proficiency at properly identifying every case of a specific illness class, also exhibit excellent performance, routinely averaging between 93 % and 94% This shows how well the model captures actual disease cases. The F1-Score maintains an exceptional average of about 94
^%
across all illness classes, indicating a harmonic equilibrium between precision as well as recall. This balanced measure takes into account both recall and accuracy. Support values provide context for the forecasts made by the model by indicating the number of cases for every illness class. A large number of cases are used to apply the model, enabling useful evaluations. Accuracy values, which gauge how accurately a model's predictions are made overall, constantly reach a high level of 98%, reiterating the model's dependability in identifying diseases of rice leaves. In conclusion, the abstract highlights the categorization model's excellent performance. High recall, precision, and F1-Score values demonstrate the model's accuracy in disease identification for each of the distinct disease classes.