S. Guillaume et al., CHARACTERIZATION OF MILL PRODUCTS BY ANALYSIS OF IN-FLOW DIGITALIZED IMAGES, Journal of food engineering, 27(3), 1996, pp. 311-322
A sensor has been designed and tested in a pilot mill to characterize
granular products in the food industry. It consists of: a mechanical s
ystem which takes a representative part of the product a CCD camera to
capture images, a software package for image analysis and data proces
sing. The method consists of comparing a sample with a predetermined '
quality class'. The decision system is built on example learning: real
cases fed into the system allow its configuration. Three qualify clas
ses have been defined, they correspond to the rolls gap (0.30, 0.40, 0
.50 mm) of the first break rolls of a semolina pilot mill. In these co
nditions, the classification accuracy rate achieved by the system is h
igher than 80%.