An automatic visual inspection system designed for dirt inspection in the p
ulp and paper industry is presented. A new hierarchical region oriented seg
mentation algorithm is introduced. The algorithm is tuned according to the
singular characteristics of the pulp samples. A criterion based on the maxi
misation of the local contrast is defined in order to perform a defect regi
on segmentation of the pulp and paper images. Some optimisations are introd
uced to avoid an excessive computational load. (C) 1999 Elsevier Science Lt
d. All rights reserved.