唐振三,袁劍龍,康亮河,程李香,呂汰,楊晨,張峰
基于圖像特征識別的馬鈴薯薯皮粗糙度分級研究
唐振三1,袁劍龍1,康亮河2,程李香1,呂汰3,楊晨3,張峰1
1甘肅農業大學農學院/干旱生境作物學國家重點實驗室/甘肅省作物遺傳改良與種質創新重點實驗室,蘭州 730070;2甘肅農業大學信息科學技術學院,蘭州 730070;3天水市農業科學研究所,天水 741000
【目的】馬鈴薯薯皮粗糙度分級研究可以提供塊莖外觀品質性狀無損檢測方法,為客觀評價品質質量和高通量篩選品種提供理論和實踐基礎?!痉椒ā恳?9份馬鈴薯品種(系)為供試材料,利用相機采集有/無芽眼的薯皮圖像。基于MATLAB R2016a軟件對薯皮圖像預處理,隨機選擇8份材料用相關函數指標比較圖像灰度化、增強及去噪效果。利用灰度共生矩陣(gray level co-occurrence matrix,GLCM)提取圖像特征參數角二階矩(angular second moment,ASM)、熵(entropy,ENT)、對比度(contrast,CON)和相關度(correlation,COR),并確定矩陣最適像素距離(d)。比較兩類薯皮圖像特征參數間的差異,選擇差異較小的薯皮圖像特征集進行統計分析和分類識別。構建支持向量機(support vector machines,SVM)和BP神經網絡(backpropagation neural network,BPNN)模型對薯皮粗糙度分級分類,模型分級精度評價指標為準確率、精準率、召回率及調和平均數?!窘Y果】加權平均值法進行灰度處理后的薯皮圖像紋理結構清晰,圖像清晰度評價值為2.5698±0.5959,顯著高于平均值法(1.8035±0.4856)和最大值法(1.0535±0.4088);直方圖均衡化增強后的薯皮圖像灰度級范圍由100—200擴大為0—200,灰度分布更加廣泛;中值濾波對3×3窗口下的薯皮圖像椒鹽噪聲去噪效果明顯,峰值信噪比(peak signal-to-noise ratio,PSNR)最大((28.6250±3.9784)Bp),顯著高于3×3和5×5窗口下對高斯噪聲去噪后的PSNR。通過GLCM(d=4)提取的兩類薯皮圖像特征參數間差異顯著,選擇其中差異較小的無芽眼薯皮圖像特征集進行統計分析和分類識別,結果表明該特征集變異系數差異明顯,對比度變異系數最大(0.40),其次是角二階矩(0.24)和相關度(0.23),熵變異系數最?。?.18)。將該特征集作為分類模型輸入變量用于薯皮分類,相較于BP神經網絡,SVM對馬鈴薯薯皮粗糙度的整體分類性能較高,準確率為87.5%。其中,對光滑皮和重麻皮的預測準確度和識別能力最高,精準率均為100%,召回率分別為85.7%和100%,調和平均數分別為92.3%和100%?!窘Y論】綜合利用本研究提出的圖像處理技術及GLCM提取的紋理特征參數能有效表征馬鈴薯塊莖薯皮粗糙度差異;通過構建SVM分類模型可實現基于機器視覺的馬鈴薯薯皮粗糙度分級,且準確率達87.5%。
馬鈴薯;薯皮粗糙度;圖像特征;機器視覺;支持向量機
【研究意義】馬鈴薯是世界第四大糧食作物。薯皮粗糙度是馬鈴薯塊莖重要外觀品質性狀,是品種特異性測試及商業分類分級的重要標準和依據[1]。【前人研究進展】薯皮粗糙度由遺傳因子和環境因子相互作用決定,是細胞生長、分裂、分化和代謝相互作用的最終體現[2]。目前馬鈴薯分級篩選主要側重塊莖形狀、大小及缺陷的簡單人工分級和機械分級,人工分級依賴視覺感官定性分類,通量和精準度低;機械分級雖可避免人工差異,但會造成不同程度的二次損傷,降低馬鈴薯商品性[3-4]。新興的基于圖像處理的機器視覺技術可通過對圖像顏色、紋理、形狀等特征信息的挖掘,快速實現待測物精準高效無損鑒別[4-5]。圖像處理中,紋理粗糙度是圖像不依賴顏色和亮度變化的視覺特征,表現出局部不規則、宏觀有規律的特性,可以反映圖像像素間的空間分布關系[6]。利用灰度共生矩陣(gray level co-occurrence matrix,GLCM)提取的紋理特征參數角二階矩(angular second moment,ASM)、熵(entropy,ENT)、對比度(contrast,CON)和相關度(correlation,COR)等,通過與機器學習算法結合,建立BP神經網絡、支持向量機(support vector machines,SVM)等分類模型可快速實現農產品無損傷檢測[7-15],已被廣泛應用于玉米籽粒識別分類、病蟲害識別、種子質量檢測及水果自動分揀系統構建等領域[12,16-19]?!颈狙芯壳腥朦c】目前,基于圖像處理的機器視覺技術可在馬鈴薯生產加工過程中實現精準高效的質量控制和定量鑒別。但研究方向主要集中在馬鈴薯塊莖形狀大小、表皮缺陷及病害鑒別等方面[3-5,16,20-21],薯皮粗糙度分級應用中尚無涉及。【擬解決的關鍵問題】擬通過基于圖像處理的機器視覺技術對馬鈴薯薯皮粗糙度分級展開研究,找出合適的薯皮圖像處理方法及特征參數,構建高識別率分類模型用于薯皮粗糙度分類,為馬鈴薯薯皮粗糙度分級識別提供高效精準且系統的客觀評價方法,加快馬鈴薯自動化生產和商品化處理效率。
以79份馬鈴薯品種(系)為供試材料(表1),2021年種植于甘肅省渭源縣五竹鎮鹿鳴村(海拔2 260 m,年平均降雨量520—560 mm,年平均氣溫5.8 ℃,年平均日照時數約2 412 h,無霜期145 d,黑壚土)。
使用專業可調LED光源拍攝箱(60 cm×60 cm×60 cm)拍照,SMART SENSOR光照度計(測量范圍1—200 000 lx,分辨率1 lx)測定光照強度為(9 000± 50)lx。選擇相機型號Canon EOS 760 D,鏡頭EF-S 18-135 mm f/3.5—5.6 IS STM。相機參數設定:快門速度1/100 s,光圈值(F)6.3,焦距50 mm,感光度(ISO)100,相機固定于拍攝物體上方,物距60 cm,圖像像素6 000×4 000。各塊莖圖像選取6個像素大小為1 000×1 000的區域作為參試樣本圖像。
參照馬鈴薯品種特異性、一致性和穩定性測試指南(GB/T 19557.28—2018),將采集的馬鈴薯人工分級[1],用作分類模型結果對照。
用MATLAB R2016a對薯皮圖像預處理(灰度化、增強和降噪);將處理后的圖像劃分為有、無芽眼兩類,芽眼圖像按1 000×1 000像素區域分塊,再根據有無芽眼對每個區域進行分類。利用GLCM提取兩類薯皮圖像紋理粗糙度特征并比較差異,選擇對分類識別影響較小的圖像作為SVM和BP神經網絡分類模型輸入變量用于薯皮粗糙度分類識別,采用混淆矩陣指標(準確率、精準率、召回率和F1值)評價分類精度(圖1)。

圖1 技術路線
1.3.1 薯皮圖像預處理 采用最大值法、平均值法和加權平均值法進行圖像灰度處理[22],從中隨機選取8份材料通過能量梯度函數比較三者處理效果[23-24];采用直方圖均衡化法進行圖像灰度增強[25];采用中值濾波在3×3和5×5窗口下對添加高斯噪聲和椒鹽噪聲的薯皮圖像降噪,計算峰值信噪比(peak signal-to- noise ratio,PSNR)評價預處理后的圖像質量,PSNR 值越高,越接近原圖[26-28]。
1.3.2 薯皮圖像分類處理 根據有無芽眼特征對預處理薯皮圖像進行區分,對含芽眼的薯皮圖像按1 000×1 000像素大小分塊,再將各區域按有無芽眼進行分類。
1.3.3 薯皮圖像紋理特征參數提取及差異比較 將待處理圖像灰度保持256級,選取圖像0°、45°、90°和135°方向均值作為GLCM方向參數(q)[14,29-30];利用GLCM計算選取的8份參試材料特征參數在不同像素距離處的取值以確定矩陣最適像素距離(d),然后通過GLCM提取有、無芽眼的薯皮圖像特征參數角二階距、對比度、相關度和熵進行差異比較。公式詳見(1)—(4)[22,30-33]。
角二階距:GLCM元素值平方和,反映圖像灰度分布均勻程度和紋理粗細程度。

對比度:反映圖像清晰度和紋理溝紋深淺程度。

相關度:度量GLCM元素在行或列方向上的相似程度,反映圖像局部灰度相關性。

熵:圖像所含信息量的度量,反映圖像紋理非均勻程度或復雜程度。

1.3.4 薯皮粗糙度分類識別 采用SVM和BP神經網絡對薯皮粗糙度分類評價,在特征參數中隨機選取55份數據用作訓練,剩余24份數據用作測試驗證。在SVM中,設定輸入參數和輸出參數為4,徑向基函數作為核函數,懲罰系數ζ和非負松弛項g分別設定為25和35;設定BP神經網絡輸入層、輸出層和隱含層節點數分別為4、1、6,最大迭代數為1 000。相關公式見文獻[34]。
1.3.5 數據處理及分類模型精度評價 用Microsoft Excel 2010和SPSS 22.0進行薯皮圖像粗糙度特征數據的統計描述和方差分析;用準確率(accuracy,Acc)、精準率(precision,Pre)、召回率(recall,Re)和調和平均數(F1)評價模型分類結果。公式詳見(5)—(8)[35]:
Acc=(TP+TN)/(TP+TN+FP+FN) (5)
Pre=TP/(TP+FP) (6)
Re=TP/(TP+FN) (7)
F1=2Pre×Re/(Pre+Re) (8)
式中,TN、FN、TP和FP分別為真反例、假反例、真正例和假正例。
參照馬鈴薯品種特異性、一致性和穩定性測試指南(GB/T 19557.28—2018),將79份馬鈴薯品種(系)人工分為重麻皮(6份)、麻皮(26份)、略麻皮(27份)和光滑皮(20份),列出分級結果的部分馬鈴薯薯皮圖像(表2)。
由表3可知,加權平均值法處理后的圖像紋理結構最清晰,效果最好。平均值法、最大值法和加權平均值法處理的圖像灰度清晰度差異顯著,加權平均值法與平均值法和最大值法的均值差最大,分別為0.7663和1.1516(表4)。
薯皮圖像均衡化增強后,灰度級范圍由100—200(表5,C-1、C-2、C-3和C-4)擴大為0—200,灰度分布更為均勻廣泛(表5,D-1、D-2、D-3和D-4)。相較于表5原始圖像A-1、A-2、A-3和A-4,增強后的薯皮圖像B-1、B-2、B-3和B-4紋理更加清晰突出。
利用中值濾波對圖像去噪,發現中值濾波對含椒鹽噪聲的圖像去噪效果顯著,在3×3窗口下中值濾波濾除椒鹽噪聲的PSNR均值差最大,且在3×3窗口下中值濾波對椒鹽噪聲濾除效果最好,最接近原始圖像(表6和表7)。
像素距離d=4時,GLCM提取的8個參試材料薯皮圖像特征參數變化基本趨于一致,表現出穩定性(圖2)。
2.4.1 薯皮圖像特征參數差異比較 利用GLCM提取有、無芽眼的薯皮圖像特征參數進行差異比較。相較于無芽眼的薯皮圖像,芽眼薯皮圖像特征參數除角二階矩外,對比度、熵和相關度均存在極顯著差異(圖3)。
2.4.2 特征參數變異系數 為避免芽眼對薯皮紋理特征的識別影響,選擇差異較小的無芽眼薯皮圖像進行分類識別。經統計分析,薯皮圖像紋理特征參數變異系數差異明顯,對比度變異系數最大(0.40),其次是角二階矩(0.24)和相關度(0.23),熵變異系數最?。?.18)(表8)。

表2 薯皮圖像
A:重麻皮;B:麻皮;C:略麻皮;D:光滑皮
A: Heavy hemp skin; B: Hemp skin; C: Slightly hemp skin; D: Smooth skin

表3 灰度方法處理的馬鈴薯薯皮圖像效果比較
A:原始圖像;B:平均值法;C:最大值法;D:加權平均值法
A: Original images B: Average method; C: Maximum method; D: Weighted-average method

表4 灰度圖像清晰度差異比較
A:平均值法;B:最大值法;C:加權平均值法。不同小寫字母表示多重比較差異顯著(<0.05)
A: Average method; B: Maximum method; C: Weighted-average method. Different lowercase letters indicate significant differences in multiple comparisons (<0.05)
A:原始圖像;B:直方圖均衡化處理后圖像;C:處理前圖像灰度直方圖;D:處理后圖像灰度直方圖
A: Original images; B: Images after histogram equalization; C: Gray scale histogram of images before processing; D: Gray scale histogram of images after processing
分類模型中,相較于BP神經網絡,SVM在薯皮分類中準確率較高(87.5%),表明該模型對薯皮類別整體分類性能較好,且對光滑皮和重麻皮類別的預測準確度和識別能力最高,精準率均為100%,召回率分別為85.7%和100%,F1值分別為92.3%和100%(表9)。
薯皮圖像采集過程中,受環境條件、攝像設備等因素影響,圖像質量可能存在差異。像素距離大小主要取決于拍攝圖像尺寸、感光度(ISO)、鏡頭光圈等參數的設置[36-37]。像素距離太小,放大尺寸的圖像會出現模糊現象;低光環境下拍攝,為提高相機鏡頭感光性能,應選較大像素距離。

表6 圖像降噪處理比較
A:重麻皮;B:麻皮;C:略麻皮;D:光滑皮 A: Heavy hemp skin; B: Hemp skin; C: Slightly hemp skin; D: Smooth skin

A:G16;B:大西洋;C:布爾班克;D:G67;E:夏波蒂;F:G121;G:隴薯10號;H:G33 A: G16; B: Atlantic; C: Burbank; D: G67; E: Shepody; F: G121; G: Longshu no.10; H: G33

表7 去噪圖像峰值信噪比(PSNR)差異比較
A:3×3椒鹽噪聲;B:5×5椒鹽噪聲;C:3×3高斯噪聲;D:5×5高斯噪聲。不同小寫字母表示多重比較差異顯著(<0.05)
A: The 3×3 salt and pepper noise; B: The 5×5 salt and pepper noise; C: The 3×3 gaussian noise; D: The 5×5 gaussian noise. Different lowercase letters indicate significant differences in multiple comparisons (<0.05)

表8 灰度共生矩陣提取薯皮特征參數表現及變異系數

表9 分類精度結果
合理的圖像處理是圖像特征準確識別的前提。圖像灰度化是圖像處理的基本方法,選擇合適灰度化方法可提高圖像灰度效果控制[38]。本研究采用的加權平均值法考慮了R(Red)、G(Green)、B(Blue)三通道權值分配,處理后的圖像相較于平均值法和最大值法,紋理清晰度最高,更符合人眼視覺感受。由于圖像灰度分布在較窄區間,亮度過于集中,使薯皮紋理模糊。采用直方圖均衡化在0—255灰度級范圍內調整圖像灰度直方圖分布,拓展像素集中區域,歸并低頻像素,可使圖像灰度分布均勻且動態范圍擴大,圖像明暗對比明顯。但對低頻灰度級過度簡并,可能會造成圖像邊緣細節信息丟失。圖像灰度集中區域存在直方圖高峰,均衡化后灰度級過度拉伸會導致圖像對比度過度增強和出現偽影[39-40]。去噪可規避圖像處理中噪聲干擾造成的圖像信息丟失并保護圖像邊緣細節[26]。在實際應用中,忽略噪聲類型盲目采用濾波算法去噪難以達到預期效果。本研究采用的中值濾波是一種非線性信號處理方法,對椒鹽噪聲、脈沖噪聲有明顯的抑制作用。為驗證中值濾波的去噪效果,利用PSNR客觀衡量去噪后的圖像質量,為選擇合適的去噪方法提供科學依據,以實現圖像有效去噪[41-42]。

A:角二階距;B:對比度;C:熵;D:相關度。ns:不顯著;**:差異極顯著(P<0.01)
薯皮圖像紋理特征識別中,紋理是不依賴于顏色、亮度變化而反映圖像同質現象的視覺特征[12]。利用共生矩陣提取紋理特征用于圖像相似性度量檢索時,在0°、45°、90°和135°四個方向上求取特征均值且歸一化,可使圖像發生旋轉和縮放時對共生矩陣提取的紋理特征影響非常小,且對視覺變化、仿射變化及噪聲干擾起到穩定作用[34,43]。薯皮凸起、凹陷、裂變等缺陷會對薯皮紋理分布和連續性產生擾動,使紋理分布不均勻。薯皮缺陷常與周圍區域形成明顯對比,紋理特征存在差異,在紋理識別中,可能會對SVM和BP神經網絡模型分類性能產生影響,增大識別難度。模型應用中應針對薯皮缺陷調整訓練策略,選擇適當的SVM核函數和懲罰系數,或者在BP神經網絡中利用交叉驗證方法選擇最佳隱藏層節點數和層數,以此提高模型學習能力,以便更好地識別圖像紋理特征[44]。
利用分類模型進行薯皮分類,有限的樣本量會使模型過擬合,導致分類結果不穩定、泛化性能低,無法在實際場景中應用。選擇合適的分類模型是有效降低樣本量過小導致模型過擬合和泛化性能低的重要方法[3,15,38]。本研究采用SVM和BP神經網絡模型對不同薯皮類別的馬鈴薯分類,SVM模型對薯皮的整體分類性能顯著高于BP神經網絡,更適于解決小樣本非線性可分問題。其可避免過度依賴樣本數據,降低模型對訓練集的過擬合,提高對新樣本數據的分類準確度。另外,為避免樣本量影響分類模型的可靠性和實用性,通過設定薯皮圖像像素大小,從單一樣本中獲取多幅圖像擴充樣本數據集,可使分類模型魯棒性和泛化性能達到平衡。
加權平均值法、直方圖均衡化法和中值濾波法能夠實現圖像灰度化、增強及去噪效果;灰度共生矩陣提取的圖像紋理特征參數角二階矩、對比度、熵和相關度作為分類模型輸入值用作馬鈴薯薯皮識別,可有效表征馬鈴薯薯皮粗糙度差異。小樣本集中,支持向量機模型識別性能優于BP神經網絡,分類準確率達87.5%,更適合薯皮粗糙度分類。
[1] 國家市場監督管理總局, 中國國家標準化管理委員會. 植物品種特異性、一致性和穩定性測試指南馬鈴薯: GB/T 19557.28—2018. 北京: 中國標準出版社, 2018.
State Administration for Market Regulation; Standardization Administration of the People's Republic of China. Guidelines for the conduct of tests for distinctness, uniformity and stability-Potato (L.): GB/T 19557.28-2018. Beijing: Standard Press of China, 2018. (in Chinese)
[2] 韓仲志, 趙友剛. 利用花生莢果圖像特征識別品種與檢驗種子. 作物學報, 2012, 38(3): 535-540.
HAN Z Z, ZHAO Y G. Variety identification and seed test by peanut pod image characteristics. Acta Agronomica Sinica, 2012, 38(3): 535-540. (in Chinese)
[3] 王紅軍, 熊俊濤, 黎鄒鄒, 鄧建猛, 鄒湘軍. 基于機器視覺圖像特征參數的馬鈴薯質量和形狀分級方法. 農業工程學報, 2016, 32(8): 272-277.
WANG H J, XIONG J T, LI Z Z, DENG J M, ZOU X J. Potato grading method of weight and shape based on imaging characteristics parameters in machine vision system. Transactions of the Chinese Society of Agricultural Engineering, 2016, 32(8): 272-277. (in Chinese)
[4] 姜宏, 于永波, 章翔峰, 陳宇彤. 馬鈴薯外部品質分級方法綜述. 科學技術與工程, 2022, 22(14): 5519-5527.
JIANG H, YU Y B, ZHANG X F, CHEN Y T. Potato external quality grading methods: a review. Science Technology and Engineering, 2022, 22(14): 5519-5527. (in Chinese)
[5] 周竹, 黃懿, 李小昱, 文東東, 汪成龍, 陶海龍. 基于機器視覺的馬鈴薯自動分級方法. 農業工程學報, 2012, 28(7): 178-183.
ZHOU Z, HUANG Y, LI X Y, WEN D D, WANG C L, TAO H L. Automatic detecting and grading method of potatoes based on machine vision. Transactions of the Chinese Society of Agricultural Engineering, 2012, 28(7): 178-183. (in Chinese)
[6] 劉麗, 匡綱要. 圖像紋理特征提取方法綜述. 中國圖象圖形學報, 2009, 14(4): 622-635.
LIU L, KUANG G Y. Overview of image textural feature extraction methods. Journal of Image and Graphics, 2009, 14(4): 622-635. (in Chinese)
[7] 展慧, 李小昱, 王為, 汪成龍, 周竹, 黃懿. 基于機器視覺的板栗分級檢測方法. 農業工程學報, 2010, 26(4): 327-331.
ZHAN H, LI X Y, WANG W, WANG C L, ZHOU Z, HUANG Y. Determination of chestnuts grading based on machine vision. Transactions of the Chinese Society of Agricultural Engineering, 2010, 26(4): 327-331. (in Chinese)
[8] 薄華, 馬縛龍, 焦李成. 圖像紋理的灰度共生矩陣計算問題的分析. 電子學報, 2006, 34(1): 155-158, 134.
BO H, MA F L, JIAO L C. Research on computation of GLCM of image texture. Acta Electronica Sinica, 2006, 34(1): 155-158, 134. (in Chinese)
[9] SINGH K R, CHAUDHURY S. Comparative analysis of texture feature extraction techniques for rice grain classification. IET Image Processing, 2020, 14(11): 2532-2540.
[10] LADDI A, SHARMA S, KUMAR A, KAPUR P. Classification of tea grains based upon image texture feature analysis under different illumination conditions. Journal of Food Engineering, 2013, 115(2): 226-231.
[11] SHAFI U, MUMTAZ R, HAQ I U, HAFEEZ M, IQBAL N, SHAUKAT A, ZAIDI S M H, MAHMOOD Z. Wheat yellow rust disease infection type classification using texture features. Sensors, 2021, 22(1): 146.
[12] 張超, 喬敏, 劉哲, 金虹杉, 寧明宇, 孫海艷. 基于無人機和衛星遙感影像的制種玉米田識別紋理特征尺度優選. 農業工程學報, 2017, 33(17): 98-104.
ZHANG C, QIAO M, LIU Z, JIN H S, NING M Y, SUN H Y. Texture scale analysis and identification of seed maize fields based on UAV and satellite remote sensing images. Transactions of the Chinese Society of Agricultural Engineering, 2017, 33(17): 98-104. (in Chinese)
[13] 謝元澄, 徐煥良, 謝莊. 基于牛肉大理石花紋標準(BMS)圖像的紋理特征分析. 中國農業科學, 2010, 43(24): 5121-5128.doi: 10.3864/j.issn.0578-1752.2010.24.016.
XIE Y C, XU H L, XIE Z. Analysis of texture features based on beef marbling standards (BMS) images. Scientia Agricultura Sinica, 2010, 43(24): 5121-5128. doi: 10.3864/j.issn.0578-1752.2010.24.016. (in Chinese)
[14] 高程程, 惠曉威. 基于灰度共生矩陣的紋理特征提取. 計算機系統應用, 2010, 19(6): 195-198.
GAO C C, HUI X W. GLCM-based texture feature extraction. Computer Systems & Applications, 2010, 19(6): 195-198. (in Chinese)
[15] 劉濤, 仲曉春, 孫成明, 郭文善, 陳瑛瑛, 孫娟. 基于計算機視覺的水稻葉部病害識別研究. 中國農業科學, 2014, 47(4): 664-674.doi: 10.3864/j.issn.0578-1752.2014.04.006.
LIU T, ZHONG X C, SUN C M, GUO W S, CHEN Y Y, SUN J. Recognition of rice leaf diseases based on computer vision. Scientia Agricultura Sinica, 2014, 47(4): 664-674. doi: 10.3864/j.issn.0578- 1752.2014.04.006. (in Chinese)
[16] 黨滿意, 孟慶魁, 谷芳, 顧彪, 胡耀華. 基于機器視覺的馬鈴薯晚疫病快速識別. 農業工程學報, 2020, 36(2): 193-200.
DANG M Y, MENG Q K, GU F, GU B, HU Y H. Rapid recognition of potato late blight based on machine vision. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(2): 193-200. (in Chinese)
[17] GOMES J F S, LETA F R. Applications of computer vision techniques in the agriculture and food industry: A review. European Food Research and Technology, 2012, 235(6): 989-1000.
[18] GUZMáN E, BAETEN V, PIERNA J A F, GARCíA-MESA J A. Determination of the olive maturity index of intact fruits using image analysis. Journal of Food Science and Technology, 2015, 52(3): 1462-1470.
[19] WANG A C, ZHANG W, WEI X H. A review on weed detection using ground-based machine vision and image processing techniques. Computers and Electronics in Agriculture, 2019, 158(2019): 226-240.
[20] LI B, XU X M, ZHANG L, HAN J W, BIAN C S, LI G C, LIU J G, JIN L P. Above-ground biomass estimation and yield prediction in potato by using UAV-based RGB and hyperspectral imaging. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 162: 161-172.
[21] RAZMJOOY N, MOUSAVI B S, SOLEYMANI F. A real-time mathematical computer method for potato inspection using machine vision. Computers & Mathematics with Applications, 2012, 63(1): 268-279.
[22] 紀娜, 何國榮. 基于灰度識別的獼猴桃形狀疤痕圖像紋理特征提取方法. 自動化與儀器儀表, 2019(1): 159-162.
JI N, HE G R. Texture feature extraction method of kiwifruit shape scar image based on gray level recognition. Automation & Instrumentation, 2019(1): 159-162. (in Chinese)
[23] 李祚林, 李曉輝, 馬靈玲, 胡玥, 唐伶俐. 面向無參考圖像的清晰度評價方法研究. 遙感技術與應用, 2011, 26(2): 239-246.
LI Z L, LI X H, MA L L, HU Y, TANG L L. Research of definition assessment based on no-reference digital image quality. Remote Sensing Technology and Application, 2011, 26(2): 239-246. (in Chinese)
[24] 宋鳳菲. 彩色圖像灰度化及其效果的客觀評價方法研究[D]. 泉州: 華僑大學, 2014.
SONG F F. Research on objective evaluation method of color image graying and its effect [D]. Quanzhou: Huaqiao University, 2014. (in Chinese)
[25] 楊衛中, 徐銀麗, 喬曦, 饒偉, 李道亮, 李振波. 基于對比度受限直方圖均衡化的水下海參圖像增強方法. 農業工程學報, 2016, 32(6): 197-203.
YANG W Z, XU Y L, QIAO X, RAO W, LI D L, LI Z B. Method for image intensification of underwater sea cucumber based on contrast-limited adaptive histogram equalization. Transactions of the Chinese Society of Agricultural Engineering, 2016, 32(6): 197-203. (in Chinese)
[26] 孫宏琦, 施維穎, 巨永鋒. 利用中值濾波進行圖像處理. 長安大學學報(自然科學版), 2003, 23(2): 104-106.
SUN H Q, SHI W Y, JU Y F. Image processing with medium value filter. Journal of Chang’an University (Natural Science Edition), 2003, 23(2): 104-106. (in Chinese)
[27] 劉祝華. 圖像去噪方法的研究[D]. 南昌: 江西師范大學, 2005.
LIU Z H. Research on image denoising method [D]. Nanchang: Jiangxi Normal University, 2005. (in Chinese)
[28] DASS A K. Improvising MSN and PSNR for finger-print image noised by GAUSSIAN and SALT & PEPPER. The International Journal of Multimedia & Its Applications, 2012, 4(4): 59-72.
[29] HARALICK R M, SHANMUGAM K, DINSTEIN I. Textural features for image classification. IEEE Transactions on Systems, Man, and Cybernetics, 1973, SMC-3(6): 610-621.
[30] 侯群群, 王飛, 嚴麗. 基于灰度共生矩陣的彩色遙感圖像紋理特征提取. 自然資源遙感, 2013, 25(4): 26-32.
HOU Q Q, WANG F, YAN L. Extraction of color image texture feature based on gray-level co-occurrence matrix. Remote Sensing for Natural Resources, 2013, 25(4): 26-32. (in Chinese)
[31] 蔡葦荻, 張羽, 劉海燕, 鄭恒彪, 程濤, 田永超, 朱艷, 曹衛星, 姚霞. 基于成像高光譜的小麥冠層白粉病早期監測方法. 中國農業科學, 2022, 55(6): 1110-1126.doi: 10.3864/j.issn.0578-1752.2022. 06.005.
CAI W D, ZHANG Y, LIU H Y, ZHENG H B, CHENG T, TIAN Y C, ZHU Y, CAO W X, YAO X. Early detection on wheat canopy powdery mildew with hyperspectral imaging. Scientia Agricultura Sinica, 2022, 55(6): 1110-1126. doi: 10.3864/j.issn.0578-1752.2022. 06.005. (in Chinese)
[32] 李智峰, 朱谷昌, 董泰鋒. 基于灰度共生矩陣的圖像紋理特征地物分類應用. 地質與勘探, 2011, 47(3): 456-461.
LI Z F, ZHU G C, DONG T F. Application of GLCM-based texture features to remote sensing image classification. Geology and Exploration, 2011, 47(3): 456-461. (in Chinese)
[33] 鄭冠楠, 譚豫之, 張俊雄, 李偉. 基于計算機視覺的馬鈴薯自動檢測分級. 農業機械學報, 2009, 40(4): 166-168, 156.
ZHENG G N, TAN Y Z, ZHANG J X, LI W. Automatic detecting and grading method of potatoes with computer vision. Transactions of the Chinese Society for Agricultural Machinery, 2009, 40(4): 166-168, 156. (in Chinese)
[34] 黃辰, 費繼友. 基于圖像特征融合的蘋果在線分級方法. 農業工程學報, 2017, 33(1): 285-291.
HUANG C, FEI J Y. Online apple grading based on decision fusion of image features. Transactions of the Chinese Society of Agricultural Engineering, 2017, 33(1): 285-291. (in Chinese)
[35] 魏永康, 楊天聰, 臧少龍, 賀利, 段劍釗, 謝迎新, 王晨陽, 馮偉. 基于無人機多光譜影像特征融合的小麥倒伏監測. 中國農業科學, 2023, 56(9): 1670-1685.doi: 10.3864/j.issn.0578-1752.2023.09.005.
WEI Y K, YANG T C, ZANG S L, HE L, DUAN J Z, XIE Y X, WANG C Y, FENG W. Monitoring wheat lodging based on UAV multi-spectral image feature fusion. Scientia Agricultura Sinica, 2023, 56(9): 1670-1685. doi: 10.3864/j.issn.0578-1752.2023.09.005. (in Chinese)
[36] 高傳新, 殷勇. 數碼相機ISO感光度的調整對刑事案件中痕跡檢驗照相質量的影響. 影像技術, 2008, 21(3): 33-35.
GAO C X, YIN Y. Influence of digital camera ISO speed setting on the quality of criminological photography for traces detection. Image Technology, 2008, 21(3): 33-35. (in Chinese)
[37] PHAM L H, TRAN D N N, RHIE C H, JEON J W. Analysis of the smartphone camera exposure effect on laser extraction//2021 International Conference on Electronics, Information, and Communication (ICEIC), 2021.
[38] 唐俊, 鄧立苗, 陳輝, 欒濤, 馬文杰. 基于機器視覺的玉米葉片透射圖像特征識別研究. 中國農業科學, 2014, 47(3): 431-440. doi: 10.3864/j.issn.0578-1752.2014.03.003.
TANG J, DENG L M, CHEN H, LUAN T, MA W J. Research on maize leaf recognition of characteristics from transmission image based on machine vision. Scientia Agricultura Sinica, 2014, 47(3): 431-440. doi: 10.3864/j.issn.0578-1752.2014.03.003. (in Chinese)
[39] 楊嘉能. 基于直方圖均衡的圖像增強算法優化研究[D]. 烏魯木齊: 新疆大學, 2021.
YANG J N. Optimization of image enhancement algorithm based on histogram equalization [D]. Urumqi: Xinjiang University, 2021. (in Chinese)
[40] 陳永亮. 灰度圖像的直方圖均衡化處理研究[D]. 合肥: 安徽大學, 2014.
CHEN Y L. Research on histogram equalization processing of gray image [D]. Hefei: Anhui University, 2014. (in Chinese)
[41] 寧媛, 李皖. 圖像去噪的幾種方法分析比較. 貴州工業大學學報(自然科學版), 2005, 34(4): 63-66.
NING Y, LI W. Analysis and comparison of some techniques on image denoising. Journal of Guizhou University of Technology (Natural Science Edition), 2005, 34(4): 63-66. (in Chinese)
[42] 楊光義. 圖像質量評價及其在圖像去噪中的應用研究[D]. 武漢: 武漢大學, 2018.
YANG G Y. Image quality evaluation and its application in image denoising [D]. Wuhan: Wuhan University, 2018. (in Chinese)
[43] 苑麗紅, 付麗, 楊勇, 苗靜. 灰度共生矩陣提取紋理特征的實驗結果分析. 計算機應用, 2009, 29(4): 1018-1021.
YUAN L H, FU L, YANG Y, MIAO J. Analysis of texture feature extracted by gray level co-occurrence matrix. Journal of Computer Applications, 2009, 29(4): 1018-1021. (in Chinese)
[44] 王璨, 李志偉. 利用融合高度與單目圖像特征的支持向量機模型識別雜草. 農業工程學報, 2016, 32(15): 165-174.
WANG C, LI Z W. Weed recognition using SVM model with fusion height and monocular image features. Transactions of the Chinese Society of Agricultural Engineering, 2016, 32(15): 165-174. (in Chinese)
Potato Tuber Skin Roughness Classification Analysis Based on Image Characteristics Recognition
TANG ZhenSan1, YUAN JianLong1, KANG LiangHe2, CHENG LiXiang1, Lü Tai3, YANG Chen3, ZHANG Feng1
1College of Agriculture, Gansu Agricultural University/State Key Laboratory of Aridland Crop Science/Gansu Key Laboratory of Crop Improvement & Germplasm Enhancement, Lanzhou 730070;2College of Information Science and Technology, Gansu Agricultural University, Lanzhou 730070;3Tianshui Institute of Agricultural Sciences, Tianshui 741000, Gansu
【Objective】The classification analysis of potato tuber skin roughness could provide the non-destructive testing methods for tuber appearance quality traits, which would establish the theoretical and practical base for the objective evaluation of tuber quality and high-throughput screening varieties.【Method】Seventy-nine potato varieties (lines) were selected as materials, and the images of tuber skin with and without bud-eyes were taken by camera. The tuber skin images were preprocessed using MATLAB R2016a software. Eight materials were randomly selected to compare the effect of image graying, enhancement and denoising using the correlation function indicators. The image characteristic parameters, angular second moment (ASM), entropy (ENT), contrast (CON) and correlation (COR) were extracted using the gray level co-occurrence matrix (GLCM), and the suitable distance (d) of GLCM were determined. The differences in two types of tuber skin image feature parameters were compared, and the set of tuber skin image features with less difference was selected for statistical analysis and classification recognition. The support vector machine (SVM) and backpropagation neural network (BPNN) models were constructed for tuber skin roughness classification, and the evaluation indexes of model grading accuracy were accuracy, precision, recall and harmonic mean, respectively. 【Result】The texture structure of tuber skin image after grayscale processing using the weighted average method was clear, and the evaluation value of image clarity was 2.5698±0.5959, which was significantly higher than that of the mean method (1.8035±0.4856) and the maximum method (1.0535±0.4088). The gray scale range of tuber skin image after histogram equalization enhancement was expanded from 100-200 to 0-200, which made the gray distribution wider. The salt noise denoising effect of tuber skin images using the median filter under 3×3 sliding windows was obvious, and the peak signal-to-noise ratio (PSNR) was maximum (28.6250±3.9784 Bp), which was significantly higher than that under 3×3 and 5×5 windows. Two types of tuber skin image feature parameters extracted by GLCM (d=4) were significantly different, and the set of tuber skin image features (without bud-eyes) with less difference was selected for statistical analysis and classification recognition. The results indicated that the variation coefficient of these parameters was varied significantly. The variation coefficient of contrast was the largest (0.40), followed by the angular second moment (0.24) and correlation (0.23), and the variation coefficient of entropy was the smallest (0.18). Using the feature set as the input variable of tuber skin classification model, the overall classification performance of SVM was higher than BP neural network, and the accuracy reached 87.5%. Especially, the prediction accuracy and recognizability of SVM for smooth and heavy hemp skins was the highest. The accuracy reached 100%, the recall reached 85.7% and 100%, and the harmonic mean reached 100% and 92.3%, respectively. 【Conclusion】The combination of the image processing techniques presented in this study and the GLCM extracted texture feature parameters could effectively characterize potato tuber skin roughness variations. The tuber skin roughness grading based on machine vision could be achieved by constructing SVM classification model, and the accuracy reached 87.5%.
; tuber skin roughness; image characteristic; machine vision; support vector machine

10.3864/j.issn.0578-1752.2023.22.006
2023-03-17;
2023-07-24
國家重點研發計劃(SQ2022YFD1600328)、甘肅省科技重大專項(21ZD11NA002,21ZD11NA009)
唐振三,E-mail:1316740746@qq.com。通信作者張峰,E-mail:zhangf@gsau.edu.cn
(責任編輯 趙伶俐)