Identification of trash in cane using machine vision

BILLET CANE, leaf, and tops form the overwhelming bulk of sugar millfeedstocks, but currently there is no accurate and reliable non-invasive methodof directly estimating the amount of trash (combined leaf and tops) they contain,or distinguishing between the amounts of leaf and tops. This paper reports on anovel technique that can reliably and non-invasively distinguish between billetcane, leaf, and tops on the basis of high resolution colour imagery. Thetechnique distinguishes between billet cane and both leaf and tops using detailedsurface texture. The features distinguishing cane from leaf and tops areconsistent across all cane varieties examined and do not require calibration forcane variety. Texture is not a good discriminator between leaf and tops.However, leaf and tops can be distinguished on the basis of hue since thedifferences in water content and degree of senescence which distinguish leaf andtops are associated with hue. Texture and hue based discriminators are thenmerged in a probabilistic framework to produce a combined classifier capable ofachieving true positive identification rates between 80% and 90% and falsepositive identification rates below 10% for cane, leaf, and tops in unseen testimages.