EyeSmell: Rice Spoilage Detection using Azure Custom Vision in Raspberry Pi 3

Abstract

Rice is the staple food of the Filipinos. According to the Bureau of Agricultural and Fisheries Product Standards, an average Filipino consumes 4-5 servings of rice per day. But because there is no accurate way of detecting rice spoilage before consumption, Filipinos only rely on their senses to know whether the rice is spoiled or not. This makes them at risk of foodborne illness due to rice spoilage. But with the latest technology advancements, machine learning could be used to help lessen the risk and cases of food illness caused by rice spoilage. This study focuses on the implementation of Azure Custom Vision API to detect rice spoilage. Gas sensor readings and images captured during data gathering were correlated with a resulting value of 1 which corresponds to a very strong correlation. The system was tested by the researchers using 20 different rice samples that includes 10 samples of spoiled rice and 10 samples of not spoiled rice which resulted in a detection accuracy of 85%. The system is implemented with its own container using a Raspberry Pi 3B with a camera module through Python programming language.