结合高光谱与CNN的小麦不完善粒识别方法
发布时间：2019-02-20 22:03
【摘要】：通过结合高光谱数据与卷积神经网络(CNN)实现小麦不完善粒(黑胚粒、虫蚀粒及破损粒)的快速准确鉴别。实验采集小麦正常粒(484粒)、黑胚粒(100粒)、虫蚀粒(100粒)及破损粒(100粒)在493~1 106 nm的116个波段的高光谱图像,每间隔5个波段抽取1个图像,分别建立24个波段的训练集,应用CNN建立不完善粒小麦的识别模型。实验结果显示,利用该识别模型,黑胚、虫蚀和破损粒的识别率分别保持在94%、95%和92%以上。在上述工作的基础上,进一步通过修改学习率和迭代次数改进CNN模型。优化后,黑胚、虫蚀及破损粒在各波段下的平均识别率分别提高了0.624%、0.47%和0.776%。将24个波段高光谱图像混合重新构建训练集,并重新训练CNN模型,黑胚、虫蚀及破损粒的总识别率则分别提高了0.31%、0.13%和0.46%。综上所述,基于高光谱数据和改进CNN模型可以有效提高小麦不完善粒的识别精度。
[Abstract]:Combined with hyperspectral data and convolution neural network (CNN), the rapid and accurate identification of wheat imperfect grains (black embryo, wormwood and damaged grains) was achieved. The hyperspectral images of wheat normal grain (484), black embryo (100), wormwood (100) and damaged grain (100) at 493 ~ 1 106 nm were collected. The training sets of 24 bands were established, and the identification model of imperfect grain wheat was established by CNN. The experimental results show that the recognition rates of black embryo, insect erosion and damaged particles are over 95% and 92%, respectively. On the basis of the above work, the CNN model is further improved by modifying the learning rate and iteration times. After optimization, the average recognition rates of black embryo, insect erosion and damaged particles in each band were increased by 0.624% and 0.776%, respectively. The training set was reconstructed by mixing 24 band hyperspectral images and the CNN model was retrained. The total recognition rates of black embryo, insect erosion and damaged particles were increased by 0.31% and 0.46%, respectively. In conclusion, based on hyperspectral data and improved CNN model, the identification accuracy of wheat imperfect grains can be improved effectively.
【作者单位】： 北京工商大学计算机与信息工程学院食品安全大数据技术北京市重点实验室;
【基金】：国家自然科学基金(61473009) 北京市自然科学基金(4174086)资助项目
【分类号】：TP183;TP391.41
本文编号：2427331
[Abstract]:Combined with hyperspectral data and convolution neural network (CNN), the rapid and accurate identification of wheat imperfect grains (black embryo, wormwood and damaged grains) was achieved. The hyperspectral images of wheat normal grain (484), black embryo (100), wormwood (100) and damaged grain (100) at 493 ~ 1 106 nm were collected. The training sets of 24 bands were established, and the identification model of imperfect grain wheat was established by CNN. The experimental results show that the recognition rates of black embryo, insect erosion and damaged particles are over 95% and 92%, respectively. On the basis of the above work, the CNN model is further improved by modifying the learning rate and iteration times. After optimization, the average recognition rates of black embryo, insect erosion and damaged particles in each band were increased by 0.624% and 0.776%, respectively. The training set was reconstructed by mixing 24 band hyperspectral images and the CNN model was retrained. The total recognition rates of black embryo, insect erosion and damaged particles were increased by 0.31% and 0.46%, respectively. In conclusion, based on hyperspectral data and improved CNN model, the identification accuracy of wheat imperfect grains can be improved effectively.
【作者单位】： 北京工商大学计算机与信息工程学院食品安全大数据技术北京市重点实验室;
【基金】：国家自然科学基金(61473009) 北京市自然科学基金(4174086)资助项目
【分类号】：TP183;TP391.41
【相似文献】
相关期刊论文 前1条
1 张玉荣;陈赛赛;周显青;王伟宇;吴琼;王海荣;;基于图像处理和神经网络的小麦不完善粒识别方法研究[J];粮油食品科技;2014年03期
，本文编号：2427331
本文链接：https://www.wllwen.com/kejilunwen/ruanjiangongchenglunwen/2427331.html
