A fractal approach to predict fat content in meat images

摘要

Intramuscular fat content in meat in uences some important meat quality characteristics. Chemical analysis is currently used to determine intramuscular fat percentage in beef meat Nevertheless, this is a tedious and expensive technique. For the food industry it will be very useful a cheaper and non-destroying technique to determine fat content. In this paper we investigate the feasibility of a new method to predict fat content. We model meat structure as a fractal, and assume the projected image can be described by a fractional brownian motion (FBM). Experimental results shown that this assumption is satised over an acceptable scale range. Hurst coefcient of the FBM appear to present an high correlation with fat percentage.