Segmentation and classification of four common cotton contaminants in x-ray microtomographic images

Technologies currently used for cotton contaminant assessment suffer from some fundamental limitations. These limitations result in the misassessment of cotton quality. This may have a serious impact on the evaluation of the economic value of the cotton crop. This thesis work reports on the recent advances in the use of a 3D x-ray microtomographic system that employs image processing and pattern recognition algorithms to accurately detect and classify trash present in cotton. The proposed method offers a slow but attractive alternative to existing trash evaluation technologies, because of its ability to produce 3D representations of the samples, to robustly segment the trash from its background, and to accurately classify the contaminant types. A correct classification rate of 89% was achieved, when the classification algorithm was tested with 93 trash samples. This procedure, when realized in real time, could have a serious impact on the process control technologies (cotton lint cleaning), and indeed on the economic value of cotton.