An adaptive image preprocessing algorithm for defect detection in Douglas-fir veneer

Analysis of computer images of wood can usually be enhanced by the early elimination of uninteresting areas in the images. SISM and NSISM are algorithms that identify clear regions in images of wood so that such regions can be largely ignored in subsequent processing. Both perform well on most images, but falter on some. This paper describes how NSISM was refined to make it perform better on troublesome image areas without compromising its performance on more typical areas. Making such refinements to any scanning algorithm is a difficult undertaking that is usually characterized by modest performance gains. However, the economic viability of a scanning system may depend critically upon whether such gains can be achieved.