Bean Leaf Disease Classification and Visualization using Deep learning techniques on Sequential Model
Kanwarpartap Singh Gill, Vatsala Anand, Rupesh Gupta, Vivek Pahwa
Abstract
For many households in rural areas, the common bean is a significant source of revenue. Beans are farmed on around 6.3 million hectares of land each year in Eastern, Central, and Southern parts of the world, making it one of the most important, commonly grown, and eaten grain legumes in those regions. Beans are one of the foremost vital plants and seeds that are utilized around the world for cooking. Beans are a incredible source of protein that offer numerous wellbeing benefits, but there are numerous diseases related with beans leaf that ruin its formation. Thus, a proper classification and visualization of bean leaf illnesses is proposed to tackle the disease related issue within the early stage. The proposed research show that the Sequential model has great classification execution for beans leaf diseases, with the recommended model's classification accuracy being more than 90%. The model is implemented using a collection of 2134 images having 3 classes of bean leaf. The model has been evaluated in terms of performance parameters such as loss, accuracy, and confusion matrix comparison.