Proceedings of the Korean Society for Agricultural Machinery Conference (한국농업기계학회:학술대회논문집)
- 1996.06c
- /
- Pages.812-819
- /
- 1996
MORPHOLOGICAL CHARACTERIZATION OF COTTON FIBER USING IMAGE ANALYSIS
-
Cho, Yong-Jin
(Korea Food Research Institute) ;
- Han, Young J. (Department of Agricultural and Biological Engineering Clemson University)
- Published : 1996.06.01
Abstract
This study was performed to quantify microscopically morphological characteristics of cotton fiber to identify parameters for quality evaluation using image analysis . The image of each fiber was captured by a Pc-based color imaging system using a conventional microscope. Ends of individual cotton fibers were glued on a microscope slide without any tension or straightening. A modified watershed technique was implemented to identify individual convolution segments, which were defined as sections of the fiber bordered by two neighboring convolutions. Length, area and perimeter of each convolution segment were measured directly from the image . Average width, shape factor and number of convolution segments in mm were calculated from the measured parameters. The performance of the image analysis algorithm was compared with visual varieties of cotton . The image analysis results agreed with visual inspection in 89.6% of the tested images.