93%。The objective of this study is to develop image algorithms for sorting broken cottonseeds. An automatic detection system based on machine vision was designed to distinguish normal cottonseeds from broken ones. Image algorithm was developed with introduction of three statistical characteristics, which includes mean, variance and the ratio of mean to variance. Image algorithm testing on a validation data showed that broken seeds were distinguished from normal ones with accuracy of up to 93%.
参考文献
相似文献
引证文献
引用本文
刘韶军,王库.基于机器视觉的棉种破损检测技术[J].农业机械学报,2009,40(12):186-189. Damaged Cottonseeds Using Machine Vision[J]. Transactions of the Chinese Society for Agricultural Machinery,2009,40(12):186-189.