摘要
应用计算机视觉技术对梨的碰压伤进行了检测,提出通过区域标记技术区别多处碰压伤。为提高碰压伤面积的测量精度,根据梨的外形及碰压伤的特征,建立了碰压伤面积测量的数学模型。实验表明,本方法能够准确地检测梨的多处碰压伤,大部分测量相对误差可控制在10%内。
The application of computer vision technology to detection of pear bruising was studied. It was proposed to separate different bruising spots in the same pear with the aid of regional labeling way. To improve measuring precision of bruising area, a mathematic model for calculating bruising area was put forward according to pear appearance and the characteristics of bruising. Results from experiments confirmed that, different bruising spot can be precisively detected with these methods motioned above, and most of measuring relative errors can be controlled within 10 %.
出处
《农业工程学报》
EI
CAS
CSCD
北大核心
1999年第1期205-209,共5页
Transactions of the Chinese Society of Agricultural Engineering
关键词
计算机视觉
梨
碰压伤
检测
computer vision, pear, bruising detection