Detection of Corn Leaf Infection Using CNN with Various Optimizers

Corn, a grain categorized within the grass family, stands as a fundamental staple crop globally. It plays a crucial role in supplying sustenance for both humans and livestock, in addition to serving as a raw material for various industries. In 2017, Africa produced 7.4% of the 1135 million tons produced worldwide in 40 million hectares. Throughout its growing process, corn plant is impacted by numerous illnesses. Lack of early detection of its diseases may result in a loss in productivity and even crop failure. It is proposed to analyze the leaves of the corn plant for identifying the diseases by exploiting deep learning methods. A wide range of deep learning algorithms are being utilized to detect the corn leaf with infection with good range of accuracy. To categorize the leaf, image processing models are mostly used for these kind of disease detections. Since it has in-built convolutional layer, CNN can reduce the image with high dimensionality without losing any kind of information. In this proposed work CNN with Adam optimizer has been implemented for better results and achieved 91.68 % of accuracy.