龍 燕,連雅茹,馬敏娟 宋懷波,何東健
基于高光譜技術和改進型區間隨機蛙跳算法的番茄硬度檢測
龍 燕1,2,3,連雅茹1,2,3,馬敏娟1,2,3宋懷波1,2,3,何東健1,2,3
(1. 西北農林科技大學機械與電子工程學院,楊凌 712100;2. 農業農村部農業物聯網重點實驗室,楊凌 712100;3. 陜西省農業信息感知與智能服務重點實驗室,楊凌 712100)
為了準確、快速的檢測番茄硬度,該文提出了一種基于改進型區間隨機蛙跳算法優選高光譜特征波長的番茄硬度檢測模型。在獲取番茄高光譜圖像后,首先對光譜數據進行多元散射校正(multiplicative scatter correction,MSC)和歸一化預處理。針對區間隨機蛙跳算法(interval random frog,iRF)所需迭代次數大、算法收斂慢等缺點,該文提出了改進型區間隨機蛙跳算法(modified interval random frog, miRF),并將其應用于特征波長選擇。最后建立偏最小二乘回歸模型(partial least squares regression, PLSR)預測番茄的硬度。iRF共選出特征波段100個,算法收斂時間為32.1 min,而miRF共選出特征波長47個,算法收斂僅需1.6 min。同時miRF-PLSR番茄硬度預測精度也更優,測試集相關系數達到了0.968 5,均方根誤差為0.004 0kg/mm2。試驗結果表明:結合高光譜技術和miRF算法可實現對番茄硬度的快速、無損檢測。
光譜分析;算法;模型;高光譜技術;番茄;硬度;特征波長;區間隨機蛙跳
番茄富含多種營養成分,不僅有著很高的食用價值,還有一定的的藥用價值。近年來,番茄已成為全球栽培最廣、消費量最大的蔬菜作物之一,而中國也是世界最大的番茄生產和消費國家之一[1]。番茄在成熟過程中由于水解酶的作用使細胞壁果膠含量下降[2],導致其硬度發生改變。因此,番茄果實硬度是判定其成熟度的重要指標之一。研究番茄硬度的測定方法可為番茄的質量評價以及番茄在儲藏、運輸過程中的硬度變化提供參考[3]。但傳統的硬度檢測方法一般采用果實硬度計進行測量,該方法耗費時間比較長且具有破壞性[4],從而難以應用于果品硬度的批量化檢測[5-6]。因此開發無損、高效的番茄硬度的檢測方法具有重要的意義。
高光譜成像技術具有無損、無污染、高效等優點[7-8],被廣泛應用于果品硬度的無損檢測[9-10]。郝勇等[11]采用基于小波變換的蒙特卡羅無信息變量消除方法對光譜變量進行篩選,建立偏最小二乘回歸模型預測梨的硬。Sun等[12]利用高光譜技術檢測甜瓜的糖度和硬度,對比分析了偏最小二乘回歸、支持向量機和人工神經網絡3種預測模型,試驗結果表明偏最小二乘回歸模型檢測準確度最高。孫靜濤等[13]結合高光譜技術和支持向量機檢測哈密瓜的硬度和可溶性固形物。
王世芳等[14]在近紅外漫反射780~2 500 nm波段利用杠桿率校正結合偏最小二乘回歸對果實質地進行定量分析,其中果肉平均硬度預測相關系數為0.761。王世芳,宋海燕等[15]利用6個近紅外特征波段建立番茄果肉硬度分析模型檢測番茄硬度,相關系數為0.938。王凡等[16]利用可見/近紅外全透射光譜(630~1 100 nm)對番茄多品質參數無損檢測,對光譜數據進行SG卷積平滑、標準正態變量變換和多元散射校正等預處理后,建立偏最小二乘預測模型,硬度的預測集相關系數可達0.940 5。
高光譜漫反射成像技術可同時探測目標的二維集合空間與一維光譜信息,結合圖像和光譜特點,能夠獲取番茄整體空間光譜信息,在番茄硬度無損檢測上具有明顯的優勢[17]。但現有的基于高光譜技術的番茄硬度檢測模型中,特征波段選擇方法還需改進,有效光譜信息的提取仍是研究難點。本文以不同成熟時期的番茄為研究對象,利用高光譜漫反射成像獲取番茄高光譜圖像數據,對傳統隨機蛙跳算法進行改進,提出了一種基于改進型區間隨機蛙跳的特征波長提取算法,建立番茄硬度偏最小二乘回歸檢測模型,以提供一種快速、準確的番茄硬度無損檢測方法。
試驗所用的樣品為“海星”番茄,均為果形勻稱、無缺陷、無損傷的番茄,來自陜西省咸陽市楊凌區某溫室大棚。試驗前先剔除畸形和表面損傷的樣品,再對樣品逐個清潔處理并編號,后將其置于溫度20 ℃,相對濕度50%的試驗條件下1 d。
參照中GB8852—1988的相關規定,可根據番茄顏色外觀將試驗樣品粗略劃分為“綠熟期”、“變色期”、“紅熟前中期”和“紅熟后期”。但實際上,番茄由于物理、化學損傷,放置時間久或番茄紅素的使用等,通過顏色并不能準確判斷番茄硬度。本試驗番茄樣品共120個,其中“綠熟期”20個、“變色期”20個、“紅熟前中期”40個、“紅熟后期”40個。


1.可見/進紅外成像光譜儀 2.CCD相機 3.光纖鹵素燈光源(150 W) 4.電控移動載物臺 5.暗箱 6.計算機
番茄硬度采用TA.XT Plus質構儀(Stable Micro systems Ltd公司,英國)進行測定。選擇型號為P/5的探頭,設置預壓速度、下壓速度和壓后上行速度分別為1、2、10 mm/s,觸發力為0.05 N,穿刺深度為20 mm,以探頭下壓時產生的應力大小作為反映番茄硬度的指標。由于番茄的果皮與成熟度有較大的相關性,本試驗選用帶皮刺穿法進行番茄的硬度測量[18]。質構儀預熱30 min后,將樣品番茄豎立于載物臺上。從番茄的結構來看,番茄帶液汁的腔室占據大部分,選擇赤道面帶汁液的地方作為測量點更易保證數據一致性。本試驗在赤道面帶汁液的地方選擇4個測量點,如圖2中a、b、c、d所示,并將4個測量點的平均值作為番茄硬度測定值。
圖3為本文研究所采用的質構儀及硬度測定過程中的應力變化曲線圖。表皮未被探頭刺穿前,番茄在壓力作用下產生一定的變形,當壓力值逐漸上升到達峰值點時番茄被刺穿,峰值的應力大小即可視為番茄的表皮硬度(錨1位置)。隨后,應力大小迅速下降并相對穩定直到穿刺深度達到設定值(錨2位置),此時測試探頭已刺入番茄果肉。本研究選取錨1位置和錨2位置之間的平均值來計算番茄的硬度值。

圖2 番茄硬度測量點示意圖

1.機械臂 2.探頭 3.測試平臺 4.控制按鈕 5.急停按鈕

由于原始光譜曲線兩端噪聲較大,截取信息量較豐富且平滑的881.71~1 695.11 nm(共246個波段)的光譜數據作為定標和建模。為了消除光譜噪聲,提高信噪比,本文采用MSC和歸一化對原始光譜數據進行預處理。

圖4 番茄圖像背景分割和感興趣區域的提取結果
模型的預測性能好壞,究其根本在于特征波長的選擇,當特征波長的選擇過少時,會導致部分有用信息的缺失;但當特征波長的選擇過多時,會出現波段信息的冗余導致模型精度低。因此,需要一種有效的手段來提取有效波長,提高建模的精度。
區間隨機蛙跳算法(interval random frog,iRF)算法是由Yun等提出的一種特征變量選取方法[19]。該算法[20-22]同時具有適者生存和隨機搜索的特性,能夠按照定義好的策略更新變量子集,當滿足迭代次數后,統計每個波段被選擇的概率并降序排列,實現了局部信息的傳遞,最終選擇最優波段。該算法主要的運算步驟包括以下5步:
1)隨機選取個光譜波段組成初始變量子集V,設定迭代次數。
2)基于初始變量子集,選出候選變量子集V,包含個波段:首先利用V建立PLS模型,計算每個波段的絕對回歸系數,并對各波段的絕對回歸系數降序排列:
a.若=,則V=V0;
b.若<,前個波段構成候選子集V;
c.若>Q,前個波段構成候選子集V;
3)令V=V(=1~),并利用更新V。重復上述過程直到次迭代結束。
4)計算次迭代后產生的個變量子集中各每個波段被選擇概率,并按降序排列。
5)依次聯合被選概率排列前10、前11,直到前246個波段,每一組波段均進行交叉驗證,分別得到聯合均方根誤差,均方根誤差最小組中的波段即為被選波段。
在原始iRF算法中初始波段子集的產生是隨機的,具有很大的不確定性,難以保證初始信息的有效性,導致結果再現性低,這就要求迭代次數必須足夠大,以保證算法遍歷整個數據集,因此算法的運行時間長、收斂速度慢。為了提高iRF算法的收斂速度和尋優精度,本文對該算法初始變量子集的構造進行改進。連續投影(successive projections algorithm,SPA)算法能夠從光譜信息中充分尋找含有最低限度冗余信息的變量組來概括大多數樣品的光譜信息,最大程度避免信息的重復[23-24]。因此,本文首先利用SPA算法對特征波段進行初選,將SPA初選結果作為iRF的初始變量子集,從而減少iRF算法的迭代次數。本文將這種利用SPA初選波段作為初始變量子集的區間隨機蛙跳算法稱為改進型區間隨機蛙跳算法。在 SPA算法初選iRF初始變量子集時,SPA特征波段的個數分別設置為10、20、30、40、50、60、70,通過試驗可知當SPA選出的波段數為40時,改進型區間隨機蛙跳算法(modified interval random frog, miRF)迭代次數最小,對番茄的硬度檢測準確度最高。
為確保模型預測結果的有效性,先利用“二審”回收算子法剔除異常樣本7個,并采用Kennard-Stone算法將番茄樣本劃分為訓練集(80%)和測試集(20%),分別用于建模和預測,表1所示為番茄樣本硬度信息表。本文采用偏最小二乘回歸法建立番茄硬度的預測模型。該方法能直接反映光譜數據對化學指標的預測相關性,是常用的光譜定量分析建模方法[25]。模型的優劣主要由測試集的相關系數和均方根誤差評定,訓練集的均方根誤差作為輔助評價指標。測試集相關系數越高且均方根誤差越小,表示模型的效果越好,同時訓練集的均方根誤差亦是越小越好。

表1 番茄樣本硬度信息表
經過SPA算法篩選共產生40個光譜變量作為miRF的初始變量子集,并設置窗口大小為1,最大主成分數為4,迭代次數500,利用miRF進行特征波段的提取,并與傳統iRF算法進行比較。表2統計了iRF和miRF的運行時間和所需的迭代次數,miRF算法實現收斂僅需1.6 min,迭代500次;而iRF算法迭代10 000次后才達到收斂,算法運行時間為32.1 min,是miRF算法的20倍左右。試驗結果表明miRF算法在高效性方面具有很大的優勢。

表2 iRF和miRF算法的比較
圖5a為各波段被選擇為特征波段的概率,其中橫坐標為波段數,縱坐標為該波段被選擇的概率。圖5b為聯合均方根誤差的計算結果,最小均方根誤差所在位置為第38個區間,所含波段數為47,均方根誤差為0.005 3 kg/mm2。

注:圖中正方形標出了最小均方根誤差
本文利用iRF算法和miRF算法分別提取了100個和47個光譜特征波段,統計圖如圖6所示。可以看出,2種方法提取的特征波段所在范圍大概一致,多集中在1 582~1 655 nm范圍內,其次是1 160~1 190 nm和1 353~1 383 nm范圍內,說明這些區域是對番茄硬度敏感的區域。
本文利用PLSR建立番茄硬度預測模型。為證明本文算法miRF-PLSR的有效性,將其分別與SPA-PLSR,iRF-PLSR的番茄硬度預測模型比較。
本文所用計算機型號為90GKCTO1WW,主頻為3 GHz,內存為8 GB,軟件平臺為Matlab2018a。SPA-PLSR共選出特征波段40個,占全波段的16.26%;iRF-PLSR共選出特征波段100個,占全波段的40.65%,模型運行時間為32.1 min;miRF-PLSR共選出特征波段47個,占全波段的19.1%,模型運行時間為1.6 min。由此可見,miRF算法不僅有效降低了模型的復雜度,而且大大減少了算法運行時間。

注:圖中正方形標出的為被選波段
硬度預測值與實測值散點圖如圖7所示,圖中橫坐標為硬度實測值,縱坐標為硬度預測值。本文根據測試集的相關系數R和均方根誤差RMSEP對試驗結果進行評價,同時利用訓練集的均方根誤差作為輔助評價指標。表3為3種番茄硬度預測模型結果比較。由表3可以看出,SPA-PLSR的擬合精度較低,測試集相關系數和均方根誤差分別為0.803 9和0.007 7 kg/mm2。iRF-PLSR模型測試集相關系數和均方根誤差分別為0.936 6和0.004 4 kg/mm2。本文miRF-PLSR模型的擬合效果最好,訓練集的均方根誤差為0.004 1 kg/mm2,測試集相關系數和均方根誤差分別為0.968 5和0.004 0 kg/mm2。

注:圖中星號表示訓練集樣本,實心方塊代表測試集樣本

表3 3種模型結果比較
本文利用高光譜技術對番茄硬度進行無損檢測,提出了miRF特征波長提取方法,并通過與SPA、iRF算法進行比較,分析了它們對番茄硬度預測模型時效性和準確度的影響,證明了miRF算法的可行性和優越性。
利用SPA算法建立的PLSR模型預測精度較低(R和RMSEP分別為0.803 9和0.007 7 kg/mm2),主要原因是算法選擇的特征波長較少,導致部分有用信息的缺失,影響了模型的精度。iRF算法根據每個波段被作為特征波段的概率進行選擇,能在一定程度上改善SPA算法導致的光譜信息缺失問題,所建模型的預測精度得到了明顯的優化,R為0.936 6,比SPA-PLSR模型提高了0.132 7,RMSEP為0.004 4 kg/mm2。但其初始子集隨機產生,導致算法所需迭代次數較多(10 000次),算法收斂速度慢(32.1 min)。
本文提出的miRF算法對iRF初始變量子集進行有效的構造,融合了SPA算法和傳統iRF算法的優勢來提取光譜的有效信息。因此miRF算法的所需迭代次數減小到500次,收斂時間僅需1.6 min。miRF算法中,SPA篩選產生的初始變量子集,包含了40個光譜變量的,大部分波段分布在對番茄硬度敏感的區域內。但iRF隨機產生的變量子集中,波段的分布毫無規律,大部分波段游離在敏感區域外,這就導致算法收斂時間過長、模型精度降低。傳統的iRF算法最終選擇的波段數是100個,而改進的miRF算法最終選擇的波段數是47個,相對于iRF算法減少了53個,有效地消除了光譜中的冗余信息。且iRF的最小聯合均方根誤差為0.006 0 kg/mm2,而miRF的最小聯合均方根誤差為0.005 3 kg/mm2,減小了 0.000 7。因此改進后的模型預測精度更好(RMSEC為0.004 1 kg/mm2,R和RMSEP分別為0.968 5和0.004 0 kg/mm2)。
綜上所述,本文提出的特征波長提取方法在一定程度上克服了光譜信息缺失或冗余的問題,提高了番茄硬度檢測的時效性和準確度。對其他果蔬的硬度無損檢測也具有一定的參考價值。
該文利用高光譜技術對番茄硬度進行無損檢測,提出了改進型區間隨機蛙跳算法(modified interval Random Frog, miRF)提取特征波長,并通過與連續投影(successive projections algorithm,SPA)算法、區間隨機蛙跳算法(interval Random Frog,iRF)進行比較,分析了它們對番茄硬度預測的速度和精度的影響,主要結論如下:
1)證明了iRF算法提取特征波長在番茄硬度預測模型中的可行性和優越性。iRF-PLSR模型的測試集相關系數為0.936 6,比SPA-PLSR模型提高了0.132 7,同時測試集的均方根誤差減小到0.004 4 kg/mm2。
2)為克服傳統iRF算法收斂時間過長和模型實用性差的不足,本文從初始變量子集構造選擇方面對iRF進行改進,建立miRF-PLSR番茄硬度預測模型。miRF在特征波長選擇上的有效性,使得該模型在時效性上優于傳統的iRF-PLSR算法,算法收斂時間由32.1 min降低至1.6 min。預測效果也更好,訓練集的均方根誤差為0.004 1 kg/mm2,測試集的相關系數和均方根誤差分別為0.968 5和0.004 0 kg/mm2。該研究為番茄硬度無損檢測提供了新思路,也為番茄自動采收、自動分級設備的開發提供理論依據。
[1] 霍建勇. 中國番茄產業現狀及安全防范[J]. 蔬菜,2016(6):1-4. Huo Jianyong. China's tomato industry status and safety precautions[J].Vegetables, 2016(6): 1-4. (in Chinese with English abstract)
[2] 楊生保,唐亞萍,楊濤,等. 加工型番茄果實硬度特異材料的果實特性及果肉組織特征[J]. 農業工程學報,2017,33(18):285-290. Yang Shengbao, Tang Yaping, Yang Tao, et al. Fruit characteristic and flesh tissue feature of special firmness type processing tomato cultivar[J]. Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE), 2017, 33(18): 285-290. (in Chinese with English abstract)
[3] Sohrabi Mohammad Mahdi, Ahmadi Ebrahim, Monavar Hosna Mohammadi. Nondestructive analysis of packaged grape tomatoes quality using PCA and PLS regression by means of fiber optic spectroscopy during storage[J]. Journal of Food Measurement and Characterization, 2018, 12(2): 949-966.
[4] Xie Chuanqi, Chu Bingquan, He Yong. Prediction of banana color and firmness using a novel wavelengths selection method of hyperspectral imaging[J]. Food Chemistry, 2018, 245: 132-140.
[5] 郭文川,董金磊. 高光譜成像結合人工神經網絡無損檢測桃的硬度[J]. 光學精密工程,2015,23(6):1530-1537. Guo Wenchuan, Dong Jinlei. Nondestructive detection on firmness of peaches based on hyperspectral imaging and artificial neural networks[J]. Optics and Precision Engineering, 2015, 23(6): 1530-1537. (in Chinese with English abstract)
[6] 胡孟晗,董慶利,劉寶林. 基于高光譜反射、透射和交互作用成像模式的藍莓硬度和彈性模量預測的比較[J]. 光譜學與光譜分析,2016,36(11):3651-3656. Hu Menghan, Dong Qingli, Liu Baolin. Comparison of predicting blueberry firmness and elastic modulus with hyperspectral reflectance, transmittance and interactance imaging modes[J]. Spectroscopy and Spectral Analysis, 2016, 36(11): 3651-3656. (in Chinese with English abstract)
[7] Sun Jun, Tang Kai, Wu Xiaohong, et al. Nondestructive identification of green tea varieties based on hyperspectral imaging technology[J/OL]. Journal of Food Process Engineering, 2018, 41(5): e12800.
[8] Wang Nannan, Sun Dawen, Yang Yichao, et al. Recent Advances in the application of hyperspectral imaging for evaluating fruit quality[J]. Food Analytical Methods, 2016, 9(1): 178-191.
[9] Li Bo, Cobo-Medina Magdalena, Lecourt Julien, et al. Application of hyperspectral imaging for nondestructive measurement of plum quality attributes[J]. Postharvest Biology and Technology, 2018, 141: 8-15.
[10] 李瑞,傅隆生. 基于高光譜圖像的藍莓糖度和硬度無損測量[J]. 農業工程學報,2017,33(增刊1):362-366. Li Rui, Fu Longsheng. Nondestructive measurement of firmness and sugar content of blueberries based on hyperspectral imaging[J]. Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE), 2017, 33(Supp1): 362-366. (in Chinese with English abstract)
[11] 郝勇,孫旭東,潘圓媛,等. 蒙特卡羅無信息變量消除方法用于近紅外光譜預測果品硬度和表面色澤的研究[J]. 光譜學與光譜分析,2011,31(5):1225-1229. Hao Yong, Sun Xudong, Pan Yuanyuan, et al. Detection of firmness and surface color of pear by near infrared spectroscopy based on monte carlo uninformative variables elimination method[J]. Spectroscopy and spectral analysis, 2011, 31(5): 1225-1229.(in Chinese with English abstract)
[12] Sun Meijun, Zhang Dong, Liu Li, et al. How to predict the sugariness and hardness of melons: A near-infrared hyperspectral imaging method[J]. Food Chemistry, 2017, 218: 413-421.
[13] 孫靜濤,馬本學,董娟,等. 高光譜技術結合特征波長篩選和支持向量機的哈密瓜成熟度判別研究[J]. 光譜學與光譜分析,2017,37(7):2184-2191. Sun Jingtao, Ma Benxue, Dong Juan, et al. Study on maturity discrimination of hami melon with hyperspectral imaging technology combined with characteristic wavelengths selection methods and SVM[J]. Spectroscopy and Spectral Analysis, 2017, 37(7): 2184-2191. (in Chinese with English abstract)
[14] 王世芳,宋海燕,張志勇,等. 基于近紅外光譜的冷藏期番茄果實質地定量分析模型[J]. 農產品加工,2017(3):16-19. Wang Shifang, Song Haiyan, Zhang Zhiyong, et al. The quantitative analysis model of fruit texture of tomato in cold storage period based on near infrared spectroscopy[J]. Farm Products Processing. 2017 (3): 16-19. (in Chinese with English abstract)
[15] 王世芳,宋海燕,張志勇,等. 基于近紅外光譜的常溫貯藏期番茄果肉硬度動力學模型[J]. 食品與發酵工業,2017,43(9):83-86. Wang Shifang, Song Haiyan, Zhang Zhiyong, et al. Kinetic model of tomato hardness during storage at room temperature by near-infrared spectroscopy[J]. Food and Fermentation Industries. 2017, 43(9): 83-86. (in Chinese with English abstract)
[16] 王凡,李永玉,彭彥昆,等. 便攜式番茄多品質參數可見/近紅外檢測裝置研發[J]. 農業工程學報,2017,33(19):295-300. Wang Fan, Li Yongyu, Peng Yankun, et al. Development of portable device for simultaneous detection on multi-quality attributes of tomato by visible and near-infrared[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2017, 33(19): 295-300. (in Chinese with English abstract)
[17] 張若宇. 番茄可溶性固形物和硬度的高光譜成像檢測[D]. 杭州:浙江大學,2014. Zhang Ruoyu. Detection of Soluble Solids Content and Firmness of Tomato Using Hyperspectral Imaging[D]. Hangzhou: Zhejiang University, 2014. (in Chinese with English abstract)
[18] 王虹,周心智,楊麗,等. 質構儀測定番茄硬度方法的比較[J]. 南方農業,2009,3(6):s40-43. Wang Hong, Zhou Xinzhi, Yang Li, et al. Comparison of methods for determining tomato hardness by texture analyzer[J]. South China Agriculture, 2009, 3(6): 40-43. (in Chinese with English abstract)
[19] Yun Yonghuan, Li Hongdong, E. Wood Leslie R., et al. An efficient method of wavelength interval selection based on random frog for multivariate spectral calibration[J]. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2013, 111: 31-36.
[20] Wang Hongbo, Ren Xuena, Tu Xuyan. Bee and frog co-Evolution algorithm and its application[J]. Applied Soft Computing, 2017, 56: 182-198.
[21] Sharma Tarun Kumar, Pant Millie. Identification of noise in multi noise plant using enhanced version of shuffled frog leaping algorithm[J]. International Journal of System Assurance Engineering and Management, 2018, 9(1): 43-51.
[22] Sharma Tarun Kumar, Pant Millie. Opposition based learning ingrained shuffled frog-leaping algorithm[J]. Journal of Computational Science, 2017, 21:307-315.
[23] Pan Leiqing, Sun Ye, Xiao Hui, et al. Hyperspectral imaging with different illumination patterns for the hollowness classification of white radish[J]. Postharvest Biology and Technology, 2017, 126: 40-49.
[24] Cheng Junhu, Sun Dawen. Rapid and non-invasive detection of fish microbial spoilage by visible and near infrared hyperspectral imaging and multivariate analysis[J]. LWT-Food Science and Technology, 2015, 62(2): 1060-1068.
[24] Zheng Xiaochun, Li Yongyu, Wei Wensong, et al. Detection of adulteration with duck meat in minced lamb meat by using visible near-infrared hyperspectral imaging[J]. Meat Science, 2019, 149: 55-62.
Detection of tomato hardness based on hyperspectral technology and modified interval random frog algorithm
Long Yan1,2.3, Lian Yaru1,2,3, Ma Minjuan1,2,3, Song Huaibo1,2,3, He Dongjian1,2,3
(1.7121002.7121003.712100)
Tomato has become the most cultivated and consumed vegetable crop in the world, and China has become one of the largest producers and consumers of tomatoes in the world. The pectin content in cell wall of tomato during ripening is closely related to fruit hardness, which is one of the important indicators to determine the maturity and reflect the quality of tomato. The requirement of tomato maturity classification and evaluation promotes the development of non-destructive, fast and accurate detection methods of tomato hardness.Hyperspectral imaging integrates spectroscopy and imaging technology in an analysis system, which transfers tomato maturity assessment from subjective, manual classification and measurement methods. Hyperspectral imaging has been widely used in the rapid acquisition of information to classify, detect or identify the quality of various fruits. A novel method for tomato hardness detection based on hyperspectral imaging and modified interval Random Frog was proposed in this paper. Firstly, hyperspectral images of 120 tomato samples in different mature periods were captured by hyperspectral imaging system covering near-infrared region (865.11nm-1 711.71nm). And the hardness data of tomato was obtained by texture analyzer. Secondly, the spectral data were pretreated by multiplicative scatter correction (MSC) and normalized preprocessing to eliminate noise and improve signal-to-noise ratio. The validity of the characteristic wavelength plays a crucial role in the prediction performance of the model. Therefore, we need an effective method to extract the effective wavelength to improve the accuracy of the model. Interval random frog (iRF) algorithm considers all possible spectral wavelengths and ranks all the wavelengths based on selected probability. But one of the disadvantages of this method is large number of iterations and slow convergence. In view of above disadvantages, the traditional iRF algorithm was optimized in terms of constructing initial variable subset method. A modified interval Random Frog (miRF)was proposed to extract the characteristic wavelength effectively. Finally, a prediction model was developed based on partial least squares regression (PLSR) method to detect tomato hardness. The results indicated that the convergence efficiency and accuracy of miRF has a significantly improvement compared with the iRF method. The iRF has selected 100 feature bands, accounting for 40.65% of the full band, and its runtime was 32.1min. miRF has selected 47 feature bands, accounting for 19.1% of the full band, and its runtime was 1.6 min. It can be seen that miRF greatly reduces the running time of the algorithm. The characteristic wavelengths selected by iRF and miRF methods were mainly distributed in 1 582 nm-1 655 nm, followed by 1 160 nm-1 190 nm and 1 353 nm-1 383 nm, indicating that above regions were sensitive bands to tomato hardness. In order to prove the effectiveness of the proposed algorithm, the results of miRF-PLSR were compared with those of iRF-PLSR and SPA-PLSR. The prediction set correlation coefficients (R) of the SPA-PLSR model and the iRF-PLSR model were 0.803 9 and 0.936 6 respectively. And theRof miRF-PLSR model was 0.968 5. The root mean square error (RMSEP) of the SPA-PLSR model and the iRF-PLSR model were 0.007 7 kg/mm2and 0.004 4 kg/mm2respectively. And the RMSEP of miRF-PLSR model was 0.004 0 kg/mm2. The experiments results show that the miRF-PLSR model has the best prediction results in all models.
spectrum analysis; algorithms; models; hyperspectral technology; tomato; hardness; characteristic wavelength; miRF(modified interval Random Frog)
10.11975/j.issn.1002-6819.2019.13.032
S37;TP391
A
1002-6819(2019)-13-0270-07
2019-01-21
2019-05-29
陜西省農業科技創新與攻關(2016NY-157);中央高校基本科研業務費專項(2452016077)
龍 燕,副教授,主要從事農產品無損檢測技術、生物圖像與計算機視覺方面的研究。Email:longyan@nwsuaf.edu.cn
龍 燕,連雅茹,馬敏娟,宋懷波,何東鍵.基于高光譜技術和改進型區間隨機蛙跳算法的番茄硬度檢測[J]. 農業工程學報,2019,35(13):270-276. doi:10.11975/j.issn.1002-6819.2019.13.032 http://www.tcsae.org
Long Yan, Lian Yaru, Ma Minjuan, Song Huaibo, He Dongjian.Detection of tomato hardness based on hyperspectral technology and modified interval random frog algorithm[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2019, 35(13): 270-276. (in Chinese with English abstract) doi:10.11975/j.issn.1002-6819.2019.13.032 http://www.tcsae.org