The Texture Feature Extraction of Mardin Agricultural Field Images by HOG Algorithms and Soil Moisture Estimation based on the Image Textures

Knowing the soil surface moisture values of agricultural land will allow to determine disease risks in the soils and wet and dry farming. The main purpose of this study is that determining a relationship between measurements of local soil moisture and images in agricultural Mardin region and prediction of soil moisture with the determined relationship. The images are derived from TARBIL (http://www.tarbil.org) database. The texture feature vectors are extracted from the images by using Histogram of Oriented Gradients (HOG) algorithm. The obtained feature vectors are then classified into three (much, middle and little) groups by using k-Nearest Neighbor (k-NN) and Multilayer Perceptron (MLP) classifiers. Finally, the best average performance is observed as 92.73 %.