Estimation of Ammonia in Water Samples Using Image Analysis

Abstract

Ammonia plays an important role in the stability of the ecosystem. However, high concentration of ammonia in the water is toxic to the ecosystem. Hence it is important to monitor the amount of ammonia in water bodies. In this paper we use image processing and analysis to detect the amount of ammonia in water by identifying the color of the water. 7 different ammonia concentrations equal to 0.0, 0.25, 0.5, 1.0, 2.0, 4.0 and 8.0 ppm were used for testing purposes. Two color models RGB (Red, Green, Blue) and HSV (Hue, Saturation, Value) are used in the analysis. Three features are extracted from the images which are mean intensity, standard deviation and skewness. It has been observed that the proposed method using mean intensity and three color channels R, G, and B is able to identify the correct ammonia concentration in the test samples with an accuracy of 100 %.