当前位置: 首页 > 文章 > 基于计算机视觉的稻谷品种识别技术的研究 江苏大学学报(自然科学版) 2004,25 (2) 102-104
Position: Home > Articles > Study on identification of rice varieties using computer vision Journal of Jiangsu University (Natural Science Edition) 2004,25 (2) 102-104

基于计算机视觉的稻谷品种识别技术的研究

作  者:
黄星奕;李剑;姜松
单  位:
江苏大学生物与环境工程学院
关键词:
稻谷品种;识别;计算机视觉
摘  要:
稻谷品种目前均由人工检测,工作量巨大,而且检测结果主观性强,一致性差 研究出用计算机视觉技术代替人眼对稻谷进行品种识别,提出把图像的颜色特征和形状特征结合起来进行稻谷品种识别的方法,通过贝叶斯决策方法建立识别分类器,识别正确率达到88 3%以上
译  名:
Study on identification of rice varieties using computer vision
作  者:
HUANG Xing-yi, LI Jian, JIANG Song (School of Biological and Environmental Engineering, Jiangsu University, Zhenjiang, Jiangsu 212013, China)
关键词:
rice variety; identification; computer vision
摘  要:
The rice variety has been identified exclusively by human inspection so far. The result of human inspection is subjective. A new method of identification was proposed based on Bayes decision theory using computer vision. Color features and shape features were used simultaneously as input of the Bayes classifier. Tests show that identification rate is up to 883%. This method is proved to be objective and consistent.

相似文章

计量
文章访问数: 8
HTML全文浏览量: 0
PDF下载量: 0

所属期刊

推荐期刊