A method is needed to accurately and rapidly determine the gravimetric bark content of a cotton sample. Gravimetric bark content represents the percent bark mass through out the volume of a cotton sample. The current method for measuring gravimetric bark content is a labor intensive, lengthy process. Machine vision, on the other hand, is a fast, inexpensive method to measure this bulk cotton property. Ten acquired images of surfaces throughout each sample are used. Classical digital image processing tech niques isolate foreign matter regions in monochrome video images. Geometric prop erties (area and perimeter) are used to identify which foreign matter is bark and to predict the gravimetric bark content in forty-eight cotton samples with varying bark and total foreign matter content. We suggest a model with six features and intercept, which has an estimated error of 0.46% bark mass.
All Science Journal Classification (ASJC) codes
- Chemical Engineering (miscellaneous)
- Polymers and Plastics