Classification of Nitrogen Deficiency in Wheat Crop Images Using Different Machine Learning Approaches with ORANGE Tool

A key criterion for determining the health of the wheat crop is the nitrogen content. In agricultural modeling, the leaf color chart (LCC) is used to compare the color of the leaf to its matching color in order to track the success of the crop. Nitrogen is essential for plant development and growth, as well as for disease defense. In this paper, support vector machine, convolutional neural network, k-nearest neighbor, and random forest are compared, to assess the nitrogen deficiency level in accordance with the leaf color chart level. A mobile phone camera was used to obtain many samples of photos of wheat leaves. The training, testing, and validation datasets were used in this study. There are total of 1347 images. The comparison is performed using orange data mining tool. According to the findings, convolutional neural networks and random forests are more accurate than support vector machines and k-nearest neighbors.