IIITDMJ_Maize

The existing datasets lack the diversity required to train the model so that it performs equally well in real fields  under varying environmental conditions. To address this limitation, we propose to collect a small number of in-field data and use the GAN to generate synthetic data for training the deep learning network. To demonstrate the proposed method, a maize dataset 'IIITDMJ_Maize'  was collected using a drone camera under different weather conditions, including both sunny and cloudy days. The recorded video was processed to sample image frames that were later resized to 224 x 224. Keeping some raw images intact for evaluation purpose, images were further processed to crop only the portion containing diseases and selecting healthy plant images. With the help of agriculture experts, the raw and cropped images were subsequently categorized into four distinct classes -- (a) common rust, (b) northern leaf blight, (c) gray leaf spot, and (d) healthy. In total, 416 images were collected and labeled. Further, 50 raw (un-cropped) images of each category were also selected for testing the model's performance.