Methods for Determining Nitrogen, Phosphorus, and Potassium (NPK) Nutrient Content Using Scale-Invariant Feature Transform (SIFT)

Nutrient Content NPK is macronutrient content that important for the growth of a plant. The measurement of NPK conducted periodically, but the measurement using laboratories test need a relatively long time. This Research is conducted to determine the nutrient content of the soil, consisting of nitrogen, phosphor, and calcium (NPK) using digital image processing based on Scale-Invariant Feature Transform (SIFT) and backpropagation artificial neural network. The data sample in this research taken from the rice field soil in Daerah Istimewa Yogyakarta province where the soil has taken at the length of 30 cm to 110 cm with 120 cm interval, and -30° to 30° degree with interval 10°. The model from this measurement system based on texture's characteristic that extracted using Scale Invariant Feature Transform from soil's image that already passed the preprocessing process. The characteristic result will be the input from the artificial neural network with a variation on the parameter's model. The model tested for the purpose of knowing the influence of the distance and degree where the image was taken and the influence of the parameter's artificial neural network. The result from the research, is an accurate value of the measurement for each nutrient in the soil, nitrogen (94.86), phosphor (58.93) and calcium (63.57), with the mean 72,46. The corresponding result obtained from the image taken with an optimal height of 70 cm and degree 0°. © 2020 Elsevier B.V., All rights reserved.