Root Rot Lentil and Healthy Lentil Detection Using Image Processing

The hardest thing to do in agriculture is to figure out which leaves are healthy and which ones are damaged. Bangladesh makes 80\\% of its money from farming. Most farmers cannot read or write. They didn't know how much fertilizer to put on a lentil with root rot or a healthy lentil. They sometimes spray medicine on the plants, which is terrible for them. As a result, agriculture has become much less productive. In this paper, a picture-segmenting algorithm is given that can automatically find and classify plant leaf diseases. Also included are surveys of different ways to classify diseases that can be used to find plant leaf diseases. The Convolution Neural Network model is used to segment images, an essential part of finding plant leaf diseases. Every country's growth is based on its agricultural production. To keep agricultural production at a certain level and keep growing sustainably, scientists need to study how to find and treat diseases. Standard methods in the literature for classifying leaf images involve extracting attributes and training classifier models, which makes them less accurate. The technique suggested gets rid of any unnecessary data from the image collection. Using the mixture model for region growth, we first find the area of interest based on the colors of the leaves in the image. After extracting the features, a deep convolution neural network model is used to classify the leaf photos. A convolutional neural network model can be used with the deep learning model to find different patterns in color photos. Examining the execution strategy of the proposed model using an unauthorized dataset. According to the results of the simulating replica, the suggested model outperforms the well-known current methods in the field, with mean classification accuracy and area under the characteristics curve of 95.35\\% and 94.7\\%, respectively.

---

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).