本文選題：雞蛋 + 無(wú)損檢測(cè)��； 參考：《華中農(nóng)業(yè)大學(xué)》2017年博士論文

【摘要】：雞蛋品質(zhì)檢測(cè)是雞蛋商品化處理中的關(guān)鍵環(huán)節(jié),對(duì)提高雞蛋的經(jīng)濟(jì)價(jià)值和改善人們生活品質(zhì)有著重要意義,尤其是高通量在線檢測(cè),對(duì)提升我國(guó)的雞蛋加工生產(chǎn)自動(dòng)化水平和雞蛋產(chǎn)業(yè)發(fā)展具有積極作用。為了實(shí)現(xiàn)雞蛋品質(zhì)的高通量在線快速檢測(cè),本課題結(jié)合雞蛋加工實(shí)際生產(chǎn)需求,以雞蛋的新鮮度、散黃、尺寸形狀、破損等多個(gè)品質(zhì)為研究重點(diǎn),利用光譜分析和機(jī)器視覺(jué)技術(shù)對(duì)雞蛋的多個(gè)品質(zhì)進(jìn)行檢測(cè)。主要研究?jī)?nèi)容和結(jié)論如下:1)雞蛋新鮮度的光纖光譜快速定量檢測(cè)。利用自行搭建的光纖光譜檢測(cè)裝置采集雞蛋透射光譜信息,結(jié)合Savitzky-Golay卷積平滑濾波、多元散射校正、標(biāo)準(zhǔn)正態(tài)變換、一階微分及二階微分5種預(yù)處理方法,分別建立了偏最小二乘回歸PLSR和支持向量回歸SVR模型,比較不同模型精度,發(fā)現(xiàn)一階微分處理的SVR模型預(yù)測(cè)效果較好,且SVR模型在總體上優(yōu)于PLSR,表明SVR能夠較好地提取雞蛋新鮮度與光譜信息之間隱含的非線性關(guān)系;為了簡(jiǎn)化定量模型來(lái)達(dá)到快速檢測(cè)雞蛋新鮮度,使用線性降維主成分分析法PCA和流形學(xué)習(xí)中的非線性降維局部線性嵌入LLE分別對(duì)一階微分后的光譜數(shù)據(jù)再處理,比較了兩種降維后的模型結(jié)果說(shuō)明LLE更好地提取了光譜有效信息,提高了模型精度,降維效果比PCA更加明顯。LLE-SVR模型中訓(xùn)練集和預(yù)測(cè)集相關(guān)系數(shù)和均方根誤差分別為0.922、7.21和0.911、8.80,交叉驗(yàn)證均方根誤差比PCA-SVR下降了0.79。研究結(jié)果表明LLE-SVR模型可以用于光纖光譜快速定量檢測(cè)雞蛋新鮮度,為今后雞蛋新鮮度的高通量在線檢測(cè)作了理論研究。2)散黃蛋的光纖光譜快速在線識(shí)別。利用光纖光譜技術(shù)在5000枚蛋/h單通道的傳輸裝置上動(dòng)態(tài)采集雞蛋透射光譜數(shù)據(jù),比較了連續(xù)投影算法SPA和競(jìng)爭(zhēng)性自適應(yīng)重加權(quán)算法CARS分別對(duì)不同光譜預(yù)處理數(shù)據(jù)的波長(zhǎng)優(yōu)選情況,發(fā)現(xiàn)SPA選取的特征波長(zhǎng)個(gè)數(shù)總體低于CARS,然后結(jié)合所選的特征波長(zhǎng)采用偏最小二乘判別PLS-DA、分類(lèi)回歸樹(shù)算法CART、K近鄰分類(lèi)算法KNN和簇類(lèi)獨(dú)立軟模式算法SIMCA四種分類(lèi)方法建立多個(gè)分類(lèi)器,根據(jù)變量個(gè)數(shù)和識(shí)別率比較分類(lèi)器性能,優(yōu)選出5個(gè)分類(lèi)器,最后通過(guò)比較每個(gè)分類(lèi)器對(duì)單枚雞蛋的檢測(cè)時(shí)間,確定SNV-SPA-PLS-DA模型適用于在線識(shí)別散黃蛋,其特征變量只有3個(gè),單個(gè)雞蛋檢測(cè)時(shí)間為55.733ms,預(yù)測(cè)準(zhǔn)確率達(dá)到97.14%,為散黃蛋高通量在線光譜識(shí)別提供技術(shù)方法。3)雞蛋尺寸形狀高通量在線視覺(jué)檢測(cè)研究。設(shè)計(jì)了一套群體雞蛋圖像高通量在線采集系統(tǒng),其中運(yùn)用Visual C++編寫(xiě)軟件實(shí)現(xiàn)了上下位機(jī)的通訊及圖像獲取功能,使用STC89C52單片機(jī)接收光電開(kāi)關(guān)的觸發(fā)信號(hào),共同配合實(shí)現(xiàn)了自動(dòng)采集雞蛋圖像。在30000枚蛋/h六通道的傳輸裝置上動(dòng)態(tài)采集群體雞蛋圖像,采取較少但有效的預(yù)處理手段消除了高速傳輸對(duì)雞蛋圖像的影響,結(jié)合計(jì)算幾何學(xué)中的凸包算法和最小二乘橢圓擬合重建雞蛋外輪廓,解決了由于漏光引起蛋體圖像凹陷現(xiàn)象的問(wèn)題;通過(guò)分析長(zhǎng)軸、短軸產(chǎn)生畸變的原因,對(duì)提取的長(zhǎng)軸、短軸進(jìn)行了修正處理,并建立長(zhǎng)短軸像素點(diǎn)個(gè)數(shù)與實(shí)際測(cè)量尺寸的一元線性回歸模型,其兩者的相關(guān)系數(shù)分別為95.66%和94.39%,結(jié)合凸包算法相比于直接運(yùn)用最小二乘橢圓擬合得到的相關(guān)系數(shù)更大,表明結(jié)合凸包算法的最小二乘橢圓擬合提取雞蛋外形輪廓的精度更高。對(duì)84枚雞蛋圖像處理后進(jìn)行驗(yàn)證,得到雞蛋尺寸大小和外形扁平程度的分級(jí)準(zhǔn)確率分別為90.5%和89.3%,單個(gè)雞蛋的檢測(cè)時(shí)間只需52.762ms,實(shí)現(xiàn)了雞蛋尺寸形狀的高通量在線檢測(cè)分級(jí)。4)散黃蛋高通量在線視覺(jué)檢測(cè)研究。為了進(jìn)一步提高散黃蛋的檢測(cè)效率,本研究動(dòng)態(tài)采集15000枚蛋/h三通道傳輸裝置上群體雞蛋圖像,首先利用與雞蛋尺寸形狀檢測(cè)中相同的圖像處理方法消除無(wú)用背景的干擾,獲得僅含雞蛋的目標(biāo)圖像;提取雞蛋圖像RGB空間和HSV空間的顏色分量平均值作為特征參數(shù),分別利用隨機(jī)森林RF和偏最小二乘判別PLS-DA建立散黃蛋分類(lèi)模型,比較不同分類(lèi)模型結(jié)果,發(fā)現(xiàn)利用RGB與HSV聯(lián)合空間下的特征參數(shù)構(gòu)建分類(lèi)模型的效果最好,且RF分類(lèi)模型優(yōu)于PLS-DA。RGB與HSV聯(lián)合空間下的散黃蛋RF分類(lèi)模型預(yù)測(cè)識(shí)別率達(dá)到92.86%,單個(gè)雞蛋的檢測(cè)時(shí)間只需127.4ms,滿足15000枚蛋/h高通量在線檢測(cè)的要求,實(shí)現(xiàn)了高通量在線識(shí)別散黃蛋。5)破損蛋高通量在線視覺(jué)檢測(cè)研究。在15000枚蛋/h三通道傳輸裝置上動(dòng)態(tài)采集群體雞蛋圖像,由于破損區(qū)域的位置具有隨機(jī)性,因此單個(gè)雞蛋需要通過(guò)綜合采集三張圖像的檢測(cè)結(jié)果確定其是否破損。利用有效預(yù)處理方法獲取雞蛋目標(biāo)圖像,為了突顯雞蛋破損特征,使用了巴特沃斯高通濾波和灰度圖像增強(qiáng)方法,但是同時(shí)也顯現(xiàn)出斑點(diǎn)噪聲區(qū)域;提取不同區(qū)域的形狀特征參數(shù)(圓形度和最小外接矩形長(zhǎng)寬比),建立粒子群PSO優(yōu)化BP神經(jīng)網(wǎng)絡(luò)模型對(duì)破損區(qū)域和斑點(diǎn)噪聲區(qū)域進(jìn)行區(qū)分,區(qū)域類(lèi)型識(shí)別率達(dá)到99.44%,表明PSO-BP-ANN模型相比于BP-ANN的泛化能力更好、魯棒性更強(qiáng)。最后使用PSO-BP-ANN模型識(shí)別斑點(diǎn)噪聲區(qū)域并予以消除,保留雞蛋破損區(qū)域。對(duì)120枚雞蛋進(jìn)行驗(yàn)證,破損蛋識(shí)別率為91.67%,完好蛋識(shí)別率為95%,總體識(shí)別率達(dá)到93.33%,單枚雞蛋的平均檢測(cè)時(shí)間只需201.24ms,檢測(cè)效率滿足高通量在線檢測(cè)的要求。
[Abstract]:Egg quality detection is the key link in egg commercialization, which is of great significance to improving the economic value of eggs and improving people's quality of life. In particular, high flux on-line detection has a great effect on improving the level of egg processing automation and the development of egg industry in China. Line rapid detection, this topic combined with the actual production requirements of egg processing, with egg freshness, scatter yellow, size shape, damage and other qualities as the focus of research, using spectral analysis and machine vision technology to detect the multiple qualities of eggs. The main research content and conclusion are as follows: 1) fast quantitative detection of egg freshness by optical fiber spectrometry Using the self built optical fiber spectral detection device to collect the transmission spectrum information of eggs, combined with Savitzky-Golay convolution smoothing filtering, multiple scattering correction, standard normal transformation, first order differential and two order differential pre processing methods, the partial least squares regression PLSR and support vector regression SVR model are established respectively, and the different model precision is compared. It is found that the SVR model of first order differential treatment has better prediction effect, and the SVR model is better than PLSR in general. It shows that SVR can extract the nonlinear relationship between egg freshness and spectral information. In order to simplify the quantitative model to detect the freshness of eggs quickly, the linear dimensionality reduction principal component analysis (PCA) and manifold learning are used. The nonlinear reduced dimension locally linear embedding LLE reprocessed the spectral data after the first order differential. The results of two dimensionality reduction were compared. The results showed that LLE better extracted the spectral effective information and improved the model accuracy. The reduction effect was more obvious than that of the PCA. The correlation coefficient and the root mean square error of the training set, the prediction set and the mean square error in the.LLE-SVR model were more obvious. Not for 0.922,7.21 and 0.911,8.80, cross validation the root mean square root error is lower than PCA-SVR, 0.79. research results show that LLE-SVR model can be used for rapid quantitative detection of egg freshness by optical fiber spectroscopy, a theoretical study of high throughput on-line detection of egg freshness in the future,.2) fast on-line identification of optical fiber spectra of scattered yellow eggs. The spectrum technique is used to dynamically collect the transmission spectrum data on 5000 egg /h single channel transmission devices. The wavelength optimization of different spectral preprocessed data is compared between the continuous projection algorithm SPA and the competitive adaptive weight weighting algorithm CARS respectively. It is found that the number of characteristic wavelengths selected by SPA is generally lower than that of CARS, and then the selected characteristic waves are combined. Using partial least squares discriminant PLS-DA, classification regression tree algorithm CART, K nearest neighbor classification algorithm KNN and cluster independent soft mode algorithm SIMCA four classifiers to establish multiple classifiers, according to the number of variables and recognition rate to compare the performance of the classifier, 5 classifiers are selected, and the detection time of single eggs is compared by each classifier. The SNV-SPA-PLS-DA model is suitable for online identification of yellow eggs, with only 3 characteristic variables, a single egg detection time of 55.733ms, a prediction accuracy of 97.14%, a high throughput on-line spectral identification of hellyellow eggs,.3) high throughput online visual detection of egg size and shape. A set of high pass group egg image high pass is designed. The on-line acquisition system is used, in which Visual C++ software is used to realize the communication and image acquisition function of the upper and lower computer. The trigger signal of the photoelectric switch is received by the STC89C52 single chip microcomputer, and the automatic collection of egg images is realized together, and the egg images are dynamically collected on the transmission and installation of 30000 egg /h six channels. But the effective preprocessing method eliminates the influence of high speed transmission on the egg image. Combined with the convex hull algorithm and the least square ellipse fitting in the calculation geometry to reconstruct the outer contour of the egg, the problem of the image sag caused by the leakage of the egg is solved. The reason of the distortion of the long axis and the short axis is analyzed, and the long axis and the short axis are extracted. The correction processing is carried out, and the linear regression model of the number of long and short axis pixels and the actual measurement size is established. The correlation coefficients of the two are 95.66% and 94.39% respectively. The correlation coefficient of the convex packet algorithm is larger than the least square ellipse fitting, which shows the least square ellipse fitting combined with the convex hull algorithm. The accuracy of the outline of egg shape is higher. After processing 84 eggs, the accuracy rate of the size and flat degree of egg is 90.5% and 89.3% respectively. The detection time of the single egg is only 52.762ms, and the high flux on-line detection and grading.4 of the egg size and shape is realized. In order to further improve the detection efficiency of the egg scattered, this study dynamically collected the image of the group egg on the 15000 /h three channel transmission device of egg. First, the interference of the useless background was eliminated by the same image processing method which was the same with the size shape detection of eggs. The target image containing only eggs was obtained, and the RGB space and HSV of the egg image were extracted. The average value of color component of space is used as the characteristic parameter. The classification model of scattered yellow eggs is established by using random forest RF and partial least squares discrimination PLS-DA respectively. The results of different classification models are compared. It is found that the best effect of using the characteristic parameters under the combined space of RGB and HSV is the best, and the RF classification model is superior to the joint space of PLS-DA.RGB and HSV. The prediction recognition rate of the RF classification model is 92.86%, the detection time of single egg is only 127.4ms, it meets the requirement of high throughput on-line detection of 15000 eggs /h, and the on-line visual detection of the high flux on the damaged egg with high throughput on-line identification of the yellow egg.5 is realized. The group chicken is dynamically collected on the 15000 egg /h three channel transmission device. Egg image, because the location of the damaged area is random, so the single egg needs to collect three images to determine whether the egg is damaged. Using the effective preprocessing method to obtain the egg target image, in order to highlight the egg breakage features, the Butterworth high pass filter and the gray image enhancement method are used, but the same method is used. It also shows the spot noise area, and extracts the shape feature parameters of different regions (circle degree and the minimum outer rectangle length width ratio), and establishes the particle swarm optimization BP neural network model to distinguish the damaged area and the spot noise region, and the region type recognition rate reaches 99.44%, indicating that the PSO-BP-ANN model is more generalization ability than the BP-ANN. In the end, the PSO-BP-ANN model is used to identify the spot noise area and to remove the damaged area of the egg. The identification rate of broken egg is 91.67%, the recognition rate of the egg is 95%, the overall recognition rate is 93.33%, the average detection time of the single egg is only 201.24ms, the detection efficiency meets the high flux. Requirements for online testing.
【學(xué)位授予單位】：華中農(nóng)業(yè)大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TS253.7

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 盧偉;丁婧;羅慧;王玲;代德建;;基于振動(dòng)及EEMD-CMAC算法的鴨蛋散黃在線檢測(cè)[J];農(nóng)業(yè)工程學(xué)報(bào);2016年21期

2 朱寧;秦富;;蛋雞產(chǎn)業(yè)發(fā)展的國(guó)際趨勢(shì)及中國(guó)展望[J];中國(guó)家禽;2016年20期

3 霍曉娜;;2015年雞蛋市場(chǎng)分析及2016年展望[J];中國(guó)畜牧業(yè);2016年13期

4 虞華;張士洲;虞麗娜;;2015年我國(guó)禽蛋生產(chǎn)形勢(shì)回顧及走勢(shì)分析[J];飼料廣角;2016年02期

5 丁天華;盧偉;張超;杜健健;丁為民;王玲;;基于MUSIC功率譜和CPNN的雞蛋散黃無(wú)損檢測(cè)方法[J];南京農(nóng)業(yè)大學(xué)學(xué)報(bào);2015年06期

6 顧明;鄭林濤;尤政;;基于顏色空間轉(zhuǎn)換的交通圖像增強(qiáng)算法[J];儀器儀表學(xué)報(bào);2015年08期

7 郭振東;趙思言;張毅;付瑩瑩;趙紅艷;曲英龍;王中一;趙宗正;錢(qián)軍;劉林娜;;生物光譜技術(shù)在病原微生物檢測(cè)中的應(yīng)用進(jìn)展[J];軍事醫(yī)學(xué);2015年04期

8 吳雪;;雞蛋裂紋損傷檢測(cè)的聲振分析方法研究[J];食品與機(jī)械;2014年06期

9 高賢君;萬(wàn)幼川;鄭順義;楊元維;;航空攝影過(guò)程中云的實(shí)時(shí)自動(dòng)檢測(cè)[J];光譜學(xué)與光譜分析;2014年07期

10 遲玉杰;;淺析中國(guó)蛋品加工行業(yè)現(xiàn)狀及發(fā)展方向[J];中國(guó)家禽;2014年12期

相關(guān)博士學(xué)位論文 前10條

1 金程;雞蛋蛋殼裂紋檢測(cè)技術(shù)與裝置的研發(fā)[D];浙江大學(xué);2015年

2 章海亮;基于光譜和高光譜成像技術(shù)的土壤養(yǎng)分及類(lèi)型檢測(cè)與儀器開(kāi)發(fā)[D];浙江大學(xué);2015年

3 曹正鳳;隨機(jī)森林算法優(yōu)化研究[D];首都經(jīng)濟(jì)貿(mào)易大學(xué);2014年

4 劉衍民;粒子群算法的研究及應(yīng)用[D];山東師范大學(xué);2011年

5 王吉權(quán);BP神經(jīng)網(wǎng)絡(luò)的理論及其在農(nóng)業(yè)機(jī)械化中的應(yīng)用研究[D];沈陽(yáng)農(nóng)業(yè)大學(xué);2011年

6 詹宇斌;流形學(xué)習(xí)理論與方法及其應(yīng)用研究[D];國(guó)防科學(xué)技術(shù)大學(xué);2011年

7 徐惠榮;基于可見(jiàn)/近紅外光譜的水果糖度檢測(cè)模型優(yōu)化及應(yīng)用研究[D];浙江大學(xué);2010年

8 邵詠妮;水稻生長(zhǎng)生理特征信息快速無(wú)損獲取技術(shù)的研究[D];浙江大學(xué);2010年

9 劉建華;粒子群算法的基本理論及其改進(jìn)研究[D];中南大學(xué);2009年

10 吳桂芳;基于紅外光譜和場(chǎng)發(fā)射掃描電鏡技術(shù)的羊絨原料品質(zhì)分析的研究[D];浙江大學(xué);2009年

相關(guān)碩士學(xué)位論文 前10條

1 陳猛;雞蛋新鮮度和血斑蛋光譜技術(shù)在線檢測(cè)研究[D];浙江大學(xué);2015年

2 劉曉明;蛋品儲(chǔ)藏過(guò)程中新鮮度變化研究[D];齊魯工業(yè)大學(xué);2014年

3 張令標(biāo);基于高光譜成像技術(shù)的紅棗表面農(nóng)藥殘留無(wú)損檢測(cè)的研究[D];寧夏大學(xué);2014年

4 彭彥穎;雞蛋品質(zhì)近紅外光譜無(wú)損檢測(cè)研究[D];華東交通大學(xué);2012年

5 郭陽(yáng);PSO-BP神經(jīng)網(wǎng)絡(luò)在商業(yè)銀行信用風(fēng)險(xiǎn)評(píng)估中的應(yīng)用研究[D];廈門(mén)大學(xué);2009年

6 任明燦;基于計(jì)算機(jī)視覺(jué)雞蛋品質(zhì)檢測(cè)的研究[D];上海交通大學(xué);2007年

7 岑益科;基于機(jī)器視覺(jué)的雞蛋品質(zhì)檢測(cè)方法研究[D];浙江大學(xué);2006年

8 高彥平;圖像增強(qiáng)方法的研究與實(shí)現(xiàn)[D];山東科技大學(xué);2005年

9 余浩;基于正交信號(hào)校正算法的近紅外光譜預(yù)處理[D];浙江大學(xué);2004年

10 段峰;基于機(jī)器視覺(jué)的智能空瓶檢測(cè)機(jī)器人研究[D];湖南大學(xué);2002年

，

本文編號(hào)：2067285