基于Harris算子的籽粒尖端识别方法

Identification of Tipcap of Agricultural Kernel Based on Harris Algorithm

通过籽粒尖端形态特征分析,提出了一种基于Harris角点检测的籽粒尖端识别方法。Harris算子在一个局部区域中检测角特征,作为籽粒最明显的角结构,尖端在Harris角点检测中具有最大的响应值,使其对尖端不明显的籽粒也有良好的响应。通过对玉米、南瓜和西葫芦等具有尖端特征的750粒籽粒的测试结果表明,提出算法的尖端检测综合准确率为95.6%。

By analyzing morphological feature of tipcap of agricultural kernel,a tipcap identification algorithm based on Harris corner detector was developed.Harris algorithm detected the corner within a local region.As the most obvious corner structure,the tipcap had the maximal response to Harris corner detector,which made it can detect the kernels without the obvious tipcap accurately.The kernels with tipcap of corn,pumpkin and summer squash were selected for the test.The experimental results on 750 kernels showed that the proposed method got overall accuracy of 95.6% for tipcap of kernels.