Skip to main content
ARS Home » Plains Area » Las Cruces, New Mexico » Cotton Ginning Research » Research » Publications at this Location » Publication #165861
Title: SMALL TRASH IDENTIFICATION IN COTTON USING IMAGING TECHNIQUES

Author
item SIDDAIAH, MURALI - NMSU, LAS CRUCES, NM
item Hughs, Sidney
item Lieberman, Michael
item Foulk, Jonn

Submitted to: National Cotton Council Beltwide Cotton Conference
Publication Type: Proceedings
Publication Acceptance Date: 1/9/2004
Publication Date: 6/1/2004
Citation: Siddaiah, M., Hughs, S.E., Lieberman, M.A., Foulk, J.A. 2004. Small trash identification in cotton using imaging techniques. In: Proceedings of the National Cotton Council, 2004 Beltwide Cotton Conferences, January 5-9, 2004, San Antonio, Texas. p. 2394-2401.

Interpretive Summary: The advanced Fiber Information System is currently the only commercial technique available in the cotton industry for the identification of trash objects based on size categories. Online categorization of number of trash and dust counts in various size categories could be useful for the ginning and the spinning industries for process control. The Cotton Trash Identification System can be implemented for the online categorization of trash objects into various size categories equivalent to AFIS measurement.

Technical Abstract: This paper discusses the identification of small trash objects in cotton using machine vision-based systems. Trash objects were categorized into various size categories based on the equivalent diameter of the objects. The trash distribution from the Cotton Trash Identification System developed at the Southwestern Cotton Ginning Research Laboratory was compared to Advance Fiber Information System and High Volume Instrument measurements. The machine vision-based systems can evaluate cotton trash, dust, and total counts and were compared to similar Advance Fiber Information System data. The Cotton Trash Identification System developed uses a high resolution camera and can identify objects of smaller size (0.005 mm2, 2 pixels) as compared to High Volume Instrument Trashmeter software (0.045 mm2, 1 pixel). Categorization of trash objects in cotton, in real-time, allows for process control and could have a significant impact on the cotton industry.