9012 Categorization of Extraneous Matter in Cotton using Machine Vision Systems

Thursday, January 8, 2009: 8:20 AM
Conf. Room 12 (Marriott Rivercenter Hotel)
Murali Siddaiah1, D. P. Whitelock2, Michael A. Lieberman2, S. E. Hughs2 and Steve Grantham3, (1)New Mexico State University, Mesilla Park, NM, (2)USDA, ARS, Southwestern Cotton Ginning Research Laboratory, Mesilla Park, NM, (3)USDA, AMS, Cotton Program, Memphis, TN
The Cotton Trash Identification System (CTIS) developed at the Southwestern Cotton Ginning Research Laboratory was evaluated for identification and categorization of Extraneous Matter in cotton. The system’s bark/grass categorization was compared to Agricultural Marketing Service’s, Extraneous Matter calls assigned by human classers for 210 cotton bale samples.  AMS classer’s were tasked in assigning Extraneous Matter calls on four surfaces for a given bale. Scanner acquired images of the same four surfaces at 400 and 800 DPI resolutions were analyzed to evaluate the CTIS performance. The system used an EPSON® perfection 3170 photo scanner for the acquisition of cotton images. Soft computing techniques were used to identify Extraneous Matter in the acquired cotton images (4 in. x 7 in.), and categorize the objects into bark/grass, stick, leaf, and pepper trash categories. The CTIS measurements were also evaluated against High Volume Instrument measurements for percent trash.  The primary goal of the project was to develop an understanding of the relationship between a cotton classers extraneous matter calls and levels of extraneous matter as identified by the CTIS.