Crop Disease Detection using Image Classification based on Deep Learning
M Pavan Kumar1, M Praneetha2, M Rahul3 , M Raman4
1234 Artificial Intelligence & Machine Learning, Malla Reddy University
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Crop diseases affect farmers worldwide, reducing crop yields and coming about in critical financial misfortunes.For effective disease management, early detection and accurate diagnosis of crop diseases are crucial, but traditional methods of disease identification can be labor-intensive and time-consuming. Recent developments in deep learning and computer vision have shown great potential for automating the detection and diagnosis of crop diseases. Deep learning models can analyze large volumes of image data and automatically learn to identify symptoms of the disease, to diagnose crop diseases in the field in a timely and accurate manner. Developing a deep learning model for crop disease detection, an extensive set of tagged image data of healthy and sick plants needs to be collected.
The dataset is utilized to prepare a deep learning demonstration, such as a convolutional neural network (CNN), to consequently extricate highlights from pictures and classify them as solid or unhealthy. Once the demonstration has been prepared, it can be utilized to classify unused pictures of plants as healthy or infected and recognize the particular illness influencing an unhealthy plant. This could offer assistance to agriculturists and rural specialists to rapidly and precisely distinguish trim diseases and take suitable activities to oversee them. In conclusion, deep learning-based crop illness discovery may be a promising range of investigation with the potential to essentially move forward the productivity and viability of crop disease administration. With advanced inquire about and advancement, it may be conceivable to make vigorous and solid deep learning models that can be conveyed in real-world agrarian settings, giving agriculturists with the instruments they got to secure their crops and jobs.