發(fā)布時(shí)間：2018-06-25 10:56

  本文選題：玉米種子 + 高光譜圖像��； 參考：《江南大學(xué)》2017年碩士論文

【摘要】：玉米是世界總產(chǎn)量最高的糧食作物,被廣泛應(yīng)用到食品的生產(chǎn)、工業(yè)原料的制造以及畜牧業(yè)飼料的加工。玉米種子品類的鑒別工作在減少種子混雜現(xiàn)象、保證農(nóng)業(yè)生產(chǎn)的順利進(jìn)行方面具有重要價(jià)值。高光譜圖像技術(shù)具有圖譜合一的特點(diǎn),可同時(shí)獲得玉米種子的圖像信息和光譜信息,在玉米種子品種識(shí)別中得到了越來越多的重視,并且取得了很高的識(shí)別精度。種子分類特征的充分挖掘獲取是識(shí)別模型精度和魯棒性的保證。盡管高光譜圖像技術(shù)可獲得種子的圖像特征和光譜特征等,但是現(xiàn)有的種子品種識(shí)別多是利用高光譜圖像的單一光譜特征,導(dǎo)致高光譜圖像技術(shù)的優(yōu)勢(shì)沒有被充分利用。另一方面,高光譜圖像波段數(shù)目眾多,給推廣應(yīng)用到種子品種識(shí)別在線檢測(cè)設(shè)備上時(shí)帶來了困難。本文旨在將高光譜圖像技術(shù)與基于張量(Tensor)分析的多特征波段選擇方法相結(jié)合,研究一種具有快速性、高準(zhǔn)確和高魯棒性等特點(diǎn)的玉米種子無損檢測(cè)方法。主要的研究?jī)?nèi)容包括:1.利用聯(lián)合偏度算法(JS)選擇高光譜圖像的最優(yōu)波段,用于開發(fā)種子品類的分級(jí)系統(tǒng)。本課題利用高光譜圖像采集系統(tǒng)獲取17類共1632粒玉米種子在400-1000nm波段范圍內(nèi)的高光譜圖像。利用聯(lián)合偏度算法選擇了高光譜圖像的最優(yōu)波段,建立聯(lián)合特征條件下的最小二乘支持向量機(jī)(LS-SVM)種子分類模型。實(shí)驗(yàn)結(jié)果表明:基于聯(lián)合偏度的波段選擇算法的分類精度要高于無信息變量消除法和連續(xù)投影算法,為種子高光譜圖像識(shí)別技術(shù)的準(zhǔn)確和快速的識(shí)別提供了可行的途徑。2.利用有監(jiān)督的多線性判別分析(MLDA)波段選擇算法研究了玉米種子的高光譜圖像聯(lián)合特征的種子分類識(shí)別。將MLDA與JS選擇后的特征集構(gòu)建LS-SVM種子分類模型,比較相同條件下的識(shí)別精度。實(shí)驗(yàn)結(jié)果表明:MLDA波段選擇方法在相同波段下比JS波段選擇方法具有更高的效率。在相同的精度條件下,MLDA波段選擇方法可以獲得更少的波段數(shù)目,這對(duì)于開發(fā)更高效的種子高光譜圖像識(shí)別系統(tǒng)是有利的。3.利用多模型與MLDA波段選擇算法結(jié)合的策略研究了親緣關(guān)系玉米種子的分類鑒選。首先,對(duì)874-1734nm波段范圍內(nèi)的兩大類親緣關(guān)系玉米品種建立類間切換模型進(jìn)行初分,再通過構(gòu)建兩個(gè)類內(nèi)的子模型實(shí)現(xiàn)細(xì)分。同時(shí),為了提高檢測(cè)的速度和減少模型構(gòu)建的空間計(jì)算量,采用MLDA波段選擇方法來選擇最優(yōu)波段。結(jié)果表明:多模型在全波段和最優(yōu)波段下都取得了較高的識(shí)別效果,在不同場(chǎng)景下也具有較高的魯棒性。表明利用多模型和MLDA波段選擇方法結(jié)合的策略可實(shí)現(xiàn)親緣關(guān)系玉米種子高光譜圖像的純度鑒選。
[Abstract]:Corn is the highest grain crop in the world. It is widely used in food production, industrial raw material manufacture and animal husbandry feed processing. The identification of maize seed species has important value in reducing seed mixing and ensuring the smooth progress of agricultural production. The hyperspectral image technology is characterized by the combination of maps and spectra, which can obtain the image information and spectral information of maize seeds at the same time. More and more attention has been paid to the recognition of maize seed varieties, and high recognition accuracy has been obtained. The sufficient mining of seed classification features ensures the accuracy and robustness of the recognition model. Although the hyperspectral image technology can obtain the image features and spectral features of seeds, most of the existing seed varieties recognition is based on the single spectral characteristics of hyperspectral images, resulting in the advantage of hyperspectral image technology has not been fully utilized. On the other hand, the number of bands in hyperspectral images is very large, which makes it difficult to popularize and apply to the on-line detection equipment for seed variety recognition. The aim of this paper is to combine hyperspectral image technology with multi-feature band selection method based on Zhang Liang (Tensor) analysis to study a method of maize seed nondestructive detection with the characteristics of rapidity, high accuracy and high robustness. The main research contents include: 1. The joint bias algorithm (JS) is used to select the optimal bands of hyperspectral images to develop a seed classification system. In this paper, the hyperspectral images of 17 kinds of 1632 corn seeds in 400-1000nm band were obtained by using a hyperspectral image acquisition system. The optimal band of hyperspectral images is selected by using the joint bias algorithm, and the seed classification model of least squares support vector machine (LS-SVM) under the condition of joint feature is established. The experimental results show that the classification accuracy of band selection algorithm based on joint bias is higher than that of non-information variable elimination method and continuous projection algorithm, which provides a feasible way for accurate and fast recognition of seed hyperspectral images. A supervised multilinear discriminant analysis (MLDA) band selection algorithm was used to study the seed classification and recognition of the hyperspectral images of maize seeds. The LS-SVM seed classification model is constructed by using MLDA and JS selected feature sets, and the recognition accuracy is compared under the same conditions. The experimental results show that the proportion of MLDA band selection method is more efficient than JS band selection method in the same band. Under the same precision condition, less band number can be obtained by using MLDA band selection method, which is beneficial to the development of a more efficient seed hyperspectral image recognition system. The classification and selection of related maize seeds were studied by combining multiple models with MLDA band selection algorithm. Firstly, the inter-class switching model was established for two kinds of kinship maize varieties in 874-1734nm band, and then submodels were constructed to realize subdivision. At the same time, in order to improve the speed of detection and reduce the spatial computation of model construction, MLDA band selection method is used to select the optimal band. The results show that the multi-model has a higher recognition effect in both the full and optimal bands, and has a higher robustness in different scenarios. The results showed that the combination of multiple models and MLDA band selection method could be used to identify the purity of the hyperspectral images of related maize seeds.
【學(xué)位授予單位】：江南大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：S513;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 丁希斌;張初;劉飛;宋星霖;孔汶汶;何勇;;高光譜成像技術(shù)結(jié)合特征提取方法的草莓可溶性固形物檢測(cè)研究[J];光譜學(xué)與光譜分析;2015年04期

2 褚璇;王偉;張錄達(dá);郭浪花;Peggy Feldner;Gerald Heitschmidt;;高光譜最優(yōu)波長(zhǎng)選擇及Fisher判別分析法判別玉米顆粒表面黃曲霉毒素[J];光譜學(xué)與光譜分析;2014年07期

3 譚克竹;柴玉華;宋偉先;曹曉達(dá);;基于高光譜圖像處理的大豆品種識(shí)別(英文)[J];農(nóng)業(yè)工程學(xué)報(bào);2014年09期

4 韓仲志;萬劍華;張洪生;鄧立苗;杜宏偉;楊錦忠;;基于玉米籽粒近紅外光譜的品種與產(chǎn)地識(shí)別研究[J];中國(guó)糧油學(xué)報(bào);2014年01期

5 孫通;許文麗;胡田;劉木華;;基于UVE-ICA和支持向量機(jī)的南豐蜜桔可溶性固形物可見-近紅外檢測(cè)[J];光譜學(xué)與光譜分析;2013年12期

6 張初;劉飛;孔汶汶;章海亮;何勇;;利用近紅外高光譜圖像技術(shù)快速鑒別西瓜種子品種[J];農(nóng)業(yè)工程學(xué)報(bào);2013年20期

7 王立國(guó);魏芳潔;;結(jié)合遺傳算法和蟻群算法的高光譜圖像波段選擇[J];中國(guó)圖象圖形學(xué)報(bào);2013年02期

8 朱啟兵;馮朝麗;黃敏;朱曉;;基于圖像熵信息的玉米種子純度高光譜圖像識(shí)別[J];農(nóng)業(yè)工程學(xué)報(bào);2012年23期

9 黃敏;朱曉;朱啟兵;馮朝麗;;基于高光譜圖像的玉米種子特征提取與識(shí)別[J];光子學(xué)報(bào);2012年07期

10 孫旭東;郝勇;蔡麗君;劉燕德;;基于抽取和連續(xù)投影算法的可見近紅外光譜變量篩選[J];光譜學(xué)與光譜分析;2011年09期

相關(guān)博士學(xué)位論文 前1條

1 楊兵;基于張量數(shù)據(jù)的機(jī)器學(xué)習(xí)方法研究與應(yīng)用[D];中國(guó)農(nóng)業(yè)大學(xué);2014年

相關(guān)碩士學(xué)位論文 前2條

1 唐金亞;種子高光譜圖像識(shí)別中的化學(xué)計(jì)量學(xué)方法研究[D];江南大學(xué);2016年

2 馬亞楠;果蔬中內(nèi)部害蟲的高光譜圖像檢測(cè)技術(shù)研究[D];江南大學(xué);2015年

，

本文編號(hào)：2065671