Identification of trash types and computation of trash content in ginned cotton using soft computing techniques

This paper discusses the use of soft computing techniques such as Fuzzy Logic and Neural Network based approaches in the identification of various types of trash (non-lint material/foreign matter), and the computation of trash content in ginned cotton. Lint is the cotton fiber; non-lint or foreign matter is essentially everything other than lint. Trash content is the percentage of sample surface covered by non-lint particles. The effectiveness of a hybrid neurofuzzy structure, namely the Adaptive Network-Based Fuzzy Inference System (ANFIS) to classify trash types is compared with other techniques.