Take two surface pictures of corn seed and research feature parameters of two surfaces and their influence.7 The corn breed is identified by three layer BP neural network.
6、对一粒玉米种子两面各拍一幅图像，研究两面特征，分析它们之间差异及对品种特征的影响。 7、用三层BP神经网络识别玉米品种，通过训练确定网络参数，优化组合输入参数，识别率为93％。
参考来源 - 玉米品种的计算机视觉识别研究·2,447,543篇论文数据，部分数据来源于NoteExpress
The mathematics model of identifying corn breed was established using fuzzy pattern recognition.
应用模糊数学中的模糊模式识别建立识别玉米种子品种的数学模型。
The experimental result is that the correct recognition ratios of corn breed all reach above 80%, which proves that the model is a rational and effective way to identify corn breed.
试验中玉米种子品种的正确识别率均能达到80%以上，证明该模型合理可靠，是实现玉米种子品种分类的有效途径。
应用推荐