Estimation system of food texture using neural network and fuzzy logic

Abstract

This paper discusses on a system which estimates food textures using hybrid model of neural network and fuzzy logic. The system consists of equipment which obtains a load change and a sound signal while a sharp probe is stabbing a food, and a computer system which estimates numerical degrees of the food textures. Firstly, the neural network assumes numerical membership degrees of the food. The fuzzy logic infers a numerical degree of the food texture considering the estimated membership degrees. In the experiment, the validity of our proposed system is discussed. Finally future prospect is mentioned.