期刊名称：International Journal of Computer Technology and Applications
电子版ISSN：2229-6093
出版年度：2012
卷号：3
期号：3
页码：1118-1124
出版社：Technopark Publications
摘要：Contaminants in cotton plays important role for its poor quality. The digital image processing teqniques based on computer vesion provides a good way to eliminate such contaminants from cotton. This paper presents a robust algorithm for detection of contaminants in cotton. By converting the RGB images to YDbDr color space. YDbDr is composed of three components Y, Db and Dr. Y is the luminance, Db and Dr are the chrominance componants. By using YDbDr its helpful to distinguish luma and chroma information from RGB image. Iterative threshold segmentation is applied to binarize the image Y, Db, Dr. Performing fusion technique to the three binary images can fuse Luminance and chrominance image information together. For machine vision system. YCbCr and HSI color space has been implemented previously. In which the performance parameters like speed and accuracy of detection and also the detection of small contaminants or insects has to be improved. It is proved by experimental results that the YDbDr is effective and credible
