Discrimination of Nitrogen Concentration of Fertilized Corn with Extracted Algae and Polymer Based on Its Leaf Color Images

Abstract

Determination of nitrogen levels in plants is essential for variable rate fertilizer application in precision agriculture. In the past, several techniques have been developed for nitrogen concentration estimation in plants and crops employing vision system, however, they are computationally expensive and hence requires a considerable amount of time to produce accurate results. The technique developed in this work the determination of nitrogen levels in plants could be achieved effectively in real-time time by advance image processing techniques, machine visions and support vector machine (SVM) with MATLAB. The developed technique processes leaf's colored image via examining it Red, Green and Blue (RGB) values and compares them with standard intensity levels. The experimental results show effectiveness of the developed technique and accurately detect low or high concentration levels in corn. In addition, this method depends on two techniques for a final result, i.e. color intensity and SVM. If the answer is not similar between the two techniques the process will be repeated until the detection is similar. This study could be applied to a variety of crops, since this technique does not require large collection of data for training and special expertise for its on-field application.

Machine Vision Based Plant Disease Classification Through Leaf Imagining

“…Features were extracted and compared to determine if the leaf image was a high or low level of nitrogen. This research has improved plant health monitoring [21]. The novel study manipulated techniques of artificial intelligence algorithms and combined machine and deep learning to determine the evolution of COVID-19 keeping in view the of protective tools and confinement.…”