期刊名称：International Journal of Computer Information Systems and Industrial Management Applications
印刷版ISSN：2150-7988
电子版ISSN：2150-7988
出版年度：2011
卷号：3
页码：1-8
出版社：Machine Intelligence Research Labs (MIR Labs)
摘要：Quality evaluation of cumin seeds using machine vision technique suffer from system operational issues like occlusion or overlapping of seeds during test preparation by the operator of system. When due care is not taken by the system operator in spreading the seeds on the test tray, occlusion of the seeds occur. This severely deteriorates the system performance by dramatic change in quality value. The proposed ¦Á- trimmed mean filter based outlier rejection technique which makes the system occlusion resilient
