A Novel Approach for Honey Adulteration Detection Using Thermal Imaging and Convolutional Neural Networks

For life to be sustained and nourished, food is necessary. Food composition and quality are impacted when adulterants are added. Adding sugar syrups to honey in order to increase its quantity and lower its price is one of the most prevalent forms of food adulteration in honey. Health issues as well as other negative consequences may result from this. This technology will ensure that customers have access to safe and nutritious food by offering a dependable and reasonably priced solution for thedetection of honey adulteration. Additionally, it will lessen the detrimental effects on the environment and economy by preventing the selling of tainted honey. The non-invasive, non-ionizing, complementary diagnostic and real-time monitoring method known as thermal imaging makes it possible to see and measure variations in the temperature of honey. The honey's temperature changes can be detected by a thermal camera. With the use of a Convolutional Neural Network (CNN) algorithm, we present a novel method for identifying honey adulteration. The proposed system consists of two main stages: Preprocessing and Classification. The honey sample's input picture is treated during the preprocessing phase to improve its characteristics and eliminate noise. During the classification phase, the CNN algorithm receives the processed image and determines if it iscontaminated or not. The suggested approach can be used in food quality control systems because it is quick and requires little human involvement. This approach can protect consumers' health and well-being by assisting in ensuring the safety and qualityof food products.