【摘要】：水稻品種識別能有效防御假冒偽劣種子,提高水稻種子純度。利用激光誘導(dǎo)擊穿光譜,采用BP神經(jīng)網(wǎng)絡(luò)對水稻種子進(jìn)行了類型識別研究。當(dāng)波長范圍為222.054nm至849.019nm的全譜數(shù)據(jù)為BP神經(jīng)網(wǎng)絡(luò)的輸入值時,其識別率為91.2%。將全譜數(shù)據(jù)進(jìn)行去噪后,其識別率提高到96.4%。采用分段光譜進(jìn)行識別時,識別率降低且各段的識別率相差較大,但其識別所用時間大大減小。采用適當(dāng)?shù)姆侄喂庾V組合識別時,能提高其識別率,其識別率可達(dá)到92.4%,超過了全譜去噪前的識別率,而識別所用時間遠(yuǎn)小于全譜識別所用時間。結(jié)果表明:利用適當(dāng)?shù)姆侄谓M合激光誘導(dǎo)擊穿光譜對水稻品種進(jìn)行識別時,能在較短的時間內(nèi)達(dá)到滿意的識別效果。
[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.
【作者單位】： 長江大學(xué)物理與光電工程學(xué)院;
【基金】：荊州市科技發(fā)展計劃項目(2015AB35) 長江大學(xué)大學(xué)生創(chuàng)新創(chuàng)業(yè)訓(xùn)練計劃項目資助(20150100)
【分類號】：S511;TN249

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 周南;周亢;丁圭吉;;關(guān)于激光誘導(dǎo)裂析譜專題的歐洲-地中海會議2007(Ⅰ)[J];分析試驗室;2009年08期

2 周南;周亢;丁圭吉;;關(guān)于激光誘導(dǎo)裂析譜專題的歐洲-地中海會議2007(Ⅱ)[J];分析試驗室;2009年09期

3 ;激光誘導(dǎo)腦電波[J];激光與光電子學(xué)進(jìn)展;2009年06期

4 周政卓,邱明新,黃賽棠,畢琦秀,顧加O，

本文編號：2158196