Submitted to: Proceedings International Fuzzy Systems Association World Congress
Publication Type: Proceedings
Publication Acceptance Date: 1/31/1999
Publication Date: N/A
Citation: N/A Interpretive Summary: The recent research efforts at the Southwestern Cotton Ginning Research Laboratory (SWCGRL)has resulted in improving our ability to identify trash categories of bark1 (fibrous), bark2 (non-fibrous), leaf, and pepper in cotton. A soft computing approach yields better and faster classification of the trash types compared to previous work. A methodology to predict the etrash content in cotton samples and obtain comparable results with AMS measurements is currently being developed.
Technical Abstract: The paper discuses the identification of various trash types in ginned cotton. Several soft computing techniques such as Neural Networks and Fuzzy Logic based approaches are examined for their effectiveness in identifying non-lint material (foreign matter) in cotton samples. Shape descriptors such as shape factor, extent, and solidity measures are used to oidentify trash types as bark1, bark2, leaf and pepper categories.