Main content area

Objective Evaluation of the Trash and Color of Raw Cotton by Image Processing and Neural Network

Tae Jin Kang,, Soo Chang Kim,
Textile research journal 2002 v.72 no.9 pp. 776-782
cotton, Gossypium, color, image analysis, neural networks, cotton gin trash
The trash and color of raw cotton are very important and decisive factors in the current cotton grading system. In this paper, an image system is developed that can characterize trash from a raw cotton image captured by a color CCD camera and acquire color parameters. The number of trash particles and their content, size, size distribution, and spatial density can be evaluated after raw cotton images of the physical standards are thresholded and connectivity is checked. The color grading of raw cotton can be influenced by trash if the image of raw cotton includes trash. Therefore, the effect of trash on color grading is investigated using a color difference equation that measures the color difference between a trash-containing image and a trash-removed image. Color grading of raw cotton involves a trained artificial neural network, which turns out to have a good classifying ability, suggesting that the application of an artificial neural network for color grading is highly valid.