Oil Quality Analysis Using Image Processing

Now-a-days, people are demanding good quality of cooking oil (edible oil). For a healthy heart, quality of cooking oil we consume plays a very important role. As the cost of good quality cooking oil is more, there is a possibility of adulteration of oil by the traders. FSSAI also decided to crack down on the sale of adulterated edible oil. The campaign was made by FSSAI all over India in August 2020. But, the test results are expected in a month's time. The aim of the project is to determine the change in various parameters of an oil based on the presence of adulterants or some other oil residues. Determination of the presence of adulterants would be helpful in avoiding many health conditions. Changing the ratios of the oils in the mixture can show a change in the parameters that are being measured as the chemical contents of the oils are changed. The objective is to design a system to detect the adulteration and its percentage using machine learning method in various types of oil using oil image. So, the initiative is made to develop a machine learning image processing system. In this method, oil images were used to detect the adulteration in the oil. Features are collected for different ratios of adulteration, and these features obtained by image processing are used for detection of adulteration and its percentage. Variation in the features like RGB, mean, variance and entropy is measured and plotted in Minitab for various percentage of adulterations.