分段激光诱导击穿光谱的水稻种子识别

发布时间：2018-08-01 16:43

【摘要】：水稻品种识别能有效防御假冒伪劣种子,提高水稻种子纯度。利用激光诱导击穿光谱,采用BP神经网络对水稻种子进行了类型识别研究。当波长范围为222.054nm至849.019nm的全谱数据为BP神经网络的输入值时,其识别率为91.2%。将全谱数据进行去噪后,其识别率提高到96.4%。采用分段光谱进行识别时,识别率降低且各段的识别率相差较大,但其识别所用时间大大减小。采用适当的分段光谱组合识别时,能提高其识别率,其识别率可达到92.4%,超过了全谱去噪前的识别率,而识别所用时间远小于全谱识别所用时间。结果表明:利用适当的分段组合激光诱导击穿光谱对水稻品种进行识别时,能在较短的时间内达到满意的识别效果。
[Abstract]:The identification of rice varieties can effectively prevent fake and inferior seeds and improve the purity of rice seeds. The classification of rice seeds was studied by using the laser induced breakdown spectrum and BP neural network. When the full spectrum data from 222.054nm to 849.019nm is the input value of BP neural network, the recognition rate is 91.2. After denoising the whole spectrum data, the recognition rate is increased to 96. 4%. When segmented spectrum is used, the recognition rate decreases and the recognition rate varies greatly, but the recognition time is greatly reduced. The recognition rate can be improved by using the appropriate piecewise spectral combination, and the recognition rate can reach 92.4, which exceeds the recognition rate before the full-spectrum denoising, and the recognition time is much smaller than that of the full-spectrum recognition. The results showed that the suitable combination of laser induced breakdown spectra could be used to identify rice varieties in a short time.
【作者单位】：长江大学物理与光电工程学院;
【基金】：荆州市科技发展计划项目(2015AB35) 长江大学大学生创新创业训练计划项目资助(20150100)
【分类号】：S511;TN249

【相似文献】