Figure 2
The diagram illustrates the process of a convolutional neural network used for identifying tomato diseases. It starts with an input layer where an image of a tomato leaf is fed into the system. This is followed by a feature extraction layer where convolution and pooling operations are performed to extract features from the image. The convolution layers apply filters to the input image, highlighting important features. The pooling layers reduce the dimensionality of the feature maps. This process is repeated through multiple convolution and pooling layers. The global average pooling layer then condenses the extracted features into a single value per feature map. Finally, the output layer uses a softmax function to classify the disease, providing probabilities for different diseases such as Disease 1, Disease 2, up to Disease n.Phase of CNN method for tomato disease identification