摘" " 要:【目的】建立一種準確、快速的枇杷果肉褐變抗性檢測方法,實現枇杷種質資源果肉褐變抗性的高效鑒定篩選。【方法】以10份枇杷資源成熟果實為材料,利用MATLAB R2022a函數算法,對相機拍攝的原始照片進行顏色空間轉換,篩選適宜測算枇杷果肉的顏色空間。進一步對枇杷果肉切面圖像進行二值分割,提取切后不同時間果肉圖像像素值,計算褐變指數及褐變面積,并進行褐變分級。【結果】MATLAB轉化的Lab顏色空間能準確識別不同資源果肉褐變表型,與色差儀測定評價結果最接近。根據褐變指數和褐變面積進行隸屬函數排名,可綜合評價10份枇杷資源抗褐變能力。【結論】利用MATLAB圖像分割技術可實現對枇杷果肉褐變抗性的準確快速鑒定,該技術亦適用于枇杷種質資源顏色性狀的鑒定評價。
關鍵詞:枇杷;果肉褐變;圖像分割;鑒定評價
中圖分類號:S667.3 文獻標志碼:A 文章編號:1009-9980(2025)02-0288-12
Research and application of image recognition-based identification for flesh browning of loquat fruits
CHEN Yujia1, DENG Chaojun2#, ZHANG Tingting1, WANG Xiuping1, CHEN Xiuping2, ZHAO Jianing1, MA Cuilan1, JIANG Jimou2*
(1College of Horticulture, Fujian Agriculture and Forestry University, Fuzhou 350002, Fujian, China; 2Fruit Tree Research Institute of Fujian Academy of Agricultural Sciences/Fujian Longan and Loquat Breeding Engineering and Technology Research Center, Fuzhou 350013, Fujian, China)
Abstract: 【Objective】 Loquat [Eriobotrya japonica (Thunb.) Lindl.] is a kind of fruit tree of the genus Loquat in the Rosaceae, maloideae, and its fruit is tasteful, rich in nutrients, and reputed as ‘the first fruit of the early spring’. Browning of flesh can affect the quality of fresh -cut product of the fruit. So far there has been no report on the research of fresh-cut loquat fruit. Exploring the fast and efficient identification and evaluation of the flesh browning of loquat fruit is conducive to the efficient screening of browning-resistant germplasm resources of loquat. 【Methods】 The mature fruits of five white-fleshed loquat resources, including Zhongbai, Sanyuebai, Baixuezao, Guifei, and Guofenben, and five red-fleshed resources, including Zhongshudaxiang, Huangjinkuai, Ruisui, Muluo, and Yanhong collected from the National Loquat Germplasm Resource Nursery (Fuzhou, China), were used as materials. After the loquat flesh was freshly cut, it was placed in a simple soft light photographic light box with fixed light source and temperature. The browning phenotypes of loquat flesh cuts were photographed and recorded in 0 min, 10 min, 30 min and 60 min. And then the Photoshop software was used to pre-process the background purification of the original photos taken by the camera, and the rgb2lab and rgb2hsi function algorithms of the MATLAB R2022a were used to convert the color space of the pre-processed pictures of the cut surface of the fruit flesh, the recognizabilities of the loquat fruit flesh under each color component of the three color spaces of RGB, Lab, and HSI were compared, and the suitable color spaces were accordingly chosen for measuring loquat flesh. Then based on the MATLAB edge detection algorithm, the Sobel operator was used for binary segmentation of the loquat flesh cut image, to extract the change of Lab value of the flesh image pixels at different time points after cutting, and calculate the browning index according to the formula of color change value. Additionally, the MATLAB ROI function was used to select the irregular representative loquat flesh browning areas, extract the color feature value, and complete the browning area segmentation of the original image by using the Euclidean distance. Finally, according to the characteristics of the Lab value change, the browning index and browning area during the browning process of loquat flesh section, the principal components were extracted and ranked by the affiliation function, by which the browning resistance grading of the 10 loquat resources was comprehensively realized. 【Results】 A method based on the MATLAB image segmentation algorithm was established to rapidly identify loquat flesh browning, and the CIE-Lab color space transformed by MATLAB could accurately identify the flesh browning phenotypes of the different resources, which would be mostly close to the results determined by colorimeter. The L value and a value could effectively distinguish the flesh color characteristics of the two major types of red flesh and white flesh, and could be used for the flesh color phenotype identification analysis of the loquat germplasm resources. Using the color difference formula to calculate the browning index (BI) of the 10 resources at different time intervals based on Lab values, the browning indexes of the loquat resources with white flesh were significantly higher than those of the red flesh resources, and the browning indexes of Baixuezao, Guifei, Zhongbai, Zhongshudaxiang, Ruisui, and Yanhong increased with the prolongation of time post cutting, whereas thosed of Sanyuebai, Guofenben, Huangjinkuai, and Muluo loquat reached the threshold for browning after 30 min of fresh-cutting, and then tended to keep stabile. The Euclidean distance algorithm indicated that the percentage of browning area in the white flesh type was significantly higher than that in the red flesh type. Among the 10 resources, the browning process of Guofenben was the fastest and the browning area was the largest, while the browning process of Yanhong was the slowest and the browning area was the smallest 60 min post cutting. The study indicated that splitting the browning area could be possible to distinguish and localize the phenotypic differences of browning between the red and the white flesh types more precisely. According to the membership function ranking by principal component analysis, the browning resistance of the 10 loquat resources from strong to weak was: Yanhong, Ruisui, Huangjinkuai, Zhongshudaxiang, Muluo Loquat, Zhongbai, Guifei, Sanyuebai, Baixuezao, Guofenben. 【Conclusion】 The MATLAB image segmentation algorithm had a wide recognition range and fast computational speed, which would be suitable for quantitative analysis of the color change process of intensive resources. In the evaluation of the loquat flesh browning, the browning index and browning area of the MATLAB algorithm indicated the browning situation from different dimensions, and the combination of the two methods could maximize the characterization of the browning resistance of the loquat resources. The MATLAB image segmentation technique could be used to accurately and rapidly identify the browning resistance of the loquat flesh, and the technique could be also applicable to the identification and evaluation of the other color traits of the loquat germplasm resources.
Key words: Loquat; Fruit flesh browning; Image segmentation; Identification and evaluation
當前,隨著生活節奏的加快,鮮切果因健康、方便、100%可食的特性越來越被消費者接受[1],對鮮切果品質的要求也越來越高,而鮮切果產品的開發與果肉組織褐變抗性直接相關[2]。枇杷[Eriobotrya japonica (Thunb.) Lindl.]是薔薇科蘋果亞科枇杷屬植物,風味甜酸適口,營養豐富,有“早春第一果”的美譽,深受消費者青睞。探索枇杷果肉褐變快速高效的鑒定評價方法,有利于高效篩選耐褐變種質資源,為優異資源的創新利用奠定基礎。
近年來,隨著交叉學科的興起,許多基于計算機視覺快速識別農作物病蟲害及果實品質分級的方法被挖掘[3-5],深度學習在植物病害識別和病蟲害范圍評估等植保領域成為研究熱點[6-9],如柑橘[10]、蘋果[11]、荔枝[12]等植物葉病害檢測分割已有了系統研究。在顏色性狀上,計算機視覺的圖像處理技術亦有廣泛運用[13],劉佳浩等[14]利用機器視覺的邊緣檢測及HSI顏色模型對蘋果品質進行準確分級;高燕萍等[15]利用MATLAB圖像分割技術實現了甘薯耐褐變種質資源的快速鑒定。目前對枇杷種質資源的鑒定評價主要集中在外觀(果形、色澤等)、風味(可溶性固形物、可溶性糖、可滴定酸、維生素C含量等)等品質性狀[16]。對果肉色澤及色澤變化的研究則多基于肉眼觀察判定或利用色差儀測定[17]。預試驗觀察發現,枇杷種質資源間的果肉褐變抗性有明顯差異,且存在不均勻褐變現象,但果肉的褐變抗性尚未開展系統鑒定研究。筆者在本研究中擬應用MATLAB圖像二值分割算法分析枇杷果肉切面顏色值的差異變化,計算果肉褐變指數及褐變面積,根據果肉褐變特性和抗褐變能力對枇杷資源進行分級排序,探索適用于枇杷耐褐變種質資源快速鑒定評價的方法,為準確、批量識別枇杷種質資源顏色表型提供研究新思路。
1 材料和方法
1.1 試驗材料
觀測的10份枇杷資源(表1)均取自國家枇杷種質資源圃(福州)。在果實成熟期,每份資源統一由有經驗的科技人員挑選出大小、色澤和成熟度一致的果實,用不銹鋼刀縱切二等分,一半果肉去除種子后放入光源固定的簡易柔光攝影燈箱內,拍照記錄鮮切0、10、30、60 min時色澤表型(相機參數:光圈值F=5.6,感光度ISO=1000,快門速度640,拍攝背景為灰色,相片保存格式為.jpg),另一半果肉用于色差儀法(D65光源10°視場)測定0、60 min切面Lab及RGB值。觀測環境的溫度保持在25 ℃。單果為一個處理,3次重復。
1.2 枇杷果肉褐變的最適顏色空間篩選
參照包新月等[18]的方法,以白肉資源貴妃和紅肉資源黃金塊鮮切果肉為試驗材料,使用MATLAB R2022a(軟件來源于MathWorks公司)imread函數讀取原始圖片的RGB通道,利用rgb2lab和rgb2hsi函數將原始圖片(0、10、30、60 min時相機拍攝的圖片)從RGB空間轉為Lab空間和HSI空間,以色差儀測試結果為對照,篩選適宜枇杷果肉色澤表型區分的最適顏色空間。
1.3 Lab值提取及褐變指數計算
1.3.1 圖像分割 先使用MATLAB軟件rgb2gray函數將采集的原始圖像(圖1-A)轉化為灰度圖(圖1-B)。以Sobel算子計算分割閾值,應用閾值得到分割后果肉切面的二值掩膜圖像(圖1-C),通過edge函數將原始圖像的邊緣和背景用二值圖像的形式展現出來,達到邊緣檢測分割圖像的目的[19]。二值掩膜顯示圖像中高對比度的線條,但這些線條沒有很好地描繪出果肉切面對象的輪廓,與原始圖像相比,梯度掩膜中對象周圍的線條有間隙。利用imdilate函數對圖像進行形態學膨脹得到果肉切面的輪廓,但內部仍有小孔(圖1-D)。再用imfill函數進行孔隙填充,得到完整的果肉切面圖像(圖1-E)。用imclearborder函數刪除邊界連通對象(圖1-F)。用imerode函數進行平滑處理,得到背景為0、目標區域為1的完整二值分割圖像(圖1-G)[20]。
1.3.2 褐變指數測算 MATLAB算法使用邊緣檢測法對原始圖像進行二值分割,形態學處理后白色區域數值為1,即目標果肉切面區域,黑色區域為背景,數值為0(圖1-G),將數值為1的白色區域映射到原始圖像中的Lab通道,計算得出果肉切面Lab均值。色差儀法則直接測定得到Lab值。根據色差公式計算枇杷果肉褐變指數(BI)。
BI=[(Ln-L0)2+(an-a0)2+(bn-b0)22]" " " "(n=10,30,60)。
1.3.3 歐氏距離褐變面積檢測 以MATLAB ROI函數選擇不規則的代表性枇杷果肉褐變區域,提取顏色特征值,利用歐氏距離完成對原始圖像的褐變面積分割[21]。不同類型的枇杷果肉肉色差異顯著,白肉資源分割閾值以貴妃60 min為例,紅肉資源分割閾值以黃金塊60 min為例,設置不同程度的閾值,觀測分割的相似度與一致性,確定最合適的閾值,計算出枇杷果肉褐變面積,即褐變部分占整個果肉切面的百分比。
枇杷果肉質地較軟,鮮切后不同部位的褐變程度存在差異,在選擇目標ROI區域時,盡量選擇包含不同梯度褐變的區域,以便準確識別褐變區域(圖2-A~B)。白肉類型果肉顏色與褐變色顏色值差異明顯,用于分割的T值較大,在進行褐變面積分割時容易把握褐變區域和褐變閾值的選擇,以不同閾值檢測分割適宜性,其中70T、80T分割區域保守,部分褐變區域未能準確識別,而100T和110T卻過度分割,因此在白肉資源中90T為相對合適的分割閾值(圖2-C~G)。紅肉資源果肉顏色橙紅(黃),褐變色表現為果肉顏色的加深,用于分割的T值較小,在選取紅肉類型的ROI區域時,盡量選擇與果肉顏色差異最顯著的區域(圖2-H~I),根據圖2-J~N的分割適宜性檢測,以25T作為紅肉類型褐變占比計算的分割閾值。
1.4 數據處理
利用Excel 2013整理數據,利用SPSS 26.0進行統計學分析。隸屬函數μ(Xij)=(Xij-Xmin)/(Xmax-Xmin),式中μ(Xij)表示第i個資源第j個指標的隸屬函數值,Xij為指標測定值,Xmax、Xmin分別為所有參試資源中第j個指標測定值的最大值和最小值。
2 結果與分析
2.1 MATLAB圖像識別枇杷果肉褐變的最適顏色空間
利用MATLAB函數對表型差異較大的枇杷資源貴妃和黃金塊進行不同顏色空間轉換,以顯示各分量下的枇杷果肉表型差異。在RGB空間中,兩種色澤表型的R通道值無顯著差異;在HSI空間中,H通道無顯著區分;Lab顏色空間在3個通道同時顯著區分色澤差異明顯的果肉(圖3)。
將使用色差儀測定的RGB值和Lab值,與MATLAB算法提取的RGB值和Lab值對比,結果(圖4)顯示,兩份紅肉、白肉資源鮮切后相同時間點Lab顏色空間的L值、a值、b值均有顯著差異(圖4-A~C);在RGB空間中,色差儀和MATLAB測定的兩份資源的G值和B值均差異顯著(圖4-E~F),R值差異不顯著(圖4-D)。從兩份資源鮮切后不同時間色差值變化比較來看,MATLAB算法提取的Lab值中0 min和60 min時的白肉資源貴妃和紅肉資源黃金塊的L值、a值均有顯著差異,而RGB顏色空間中僅白肉資源貴妃的R值、G值和B值的果肉色澤變化達顯著水平,紅肉資源黃金塊僅G值差異顯著,R值和B值均差異不顯著。綜上認為選用Lab顏色空間對枇杷資源進行顏色值提取及褐變鑒定更適合。
2.2 褐變過程Lab值及褐變指數的變化
圖像分割算法顯示白肉資源的L值高于紅肉資源,a值和b值則較低。在果肉褐變過程中,10份種質資源的L值均呈逐步下降趨勢,0~10 min變化最明顯,30~60 min白肉資源小幅度下降,紅肉資源的L值趨于穩定(圖5-A)。相反,隨著時間的延長,a值呈上升趨勢,30 min后趨于穩定(圖5-B)。值得注意的是,b值在紅肉和白肉類型中表現出不同的變化規律,白肉資源的b值逐步增大,紅肉資源的b值卻逐步降低(圖5-C)。
利用色差公式根據Lab值計算10份資源在不同時間段的褐變指數(BI),如圖6所示,白肉資源的褐變指數高于紅肉資源,白雪早、貴妃、中白、中熟大香、黃金塊、瑞穗、艷紅隨著時間延長,褐變指數增大,而三月白、國芬本、木羅枇杷則在鮮切30 min后達到褐變閾值,而后趨于穩定。
2.3 10份資源不同時間褐變表型及褐變面積
按照果肉顏色的表型將10份枇杷資源分為白肉和紅肉兩大類,由圖7可知,0~60 min,白肉資源褐變表型較紅肉資源更明顯,紅肉資源表現出更強的抗褐變能力。鮮切0~10 min后,白肉類型的資源出現明顯褐變癥狀,紅肉資源無顯著變化。30 min時,白肉資源達到了褐變閾值,與60 min時的褐變表型無顯著差異,而紅肉資源才開始出現明顯褐變。
進一步用歐式距離算法計算10份資源鮮切后不同時間節點的褐變面積。結果表明,國芬本的褐變進程最快,褐變面積最大,艷紅的褐變進程最慢,且60 min時褐變面積最小(圖8)。對白肉資源和紅肉資源分組進行獨立樣本T檢驗,發現不同時間節點白肉資源的褐變面積占比均顯著高于紅肉資源(表2),說明分割褐變面積可更精準地區分定位紅肉和白肉類型的褐變表型差異。
2.4 褐變過程隸屬函數排名及耐褐變能力評價
根據褐變過程Lab值變化、不同時間褐變指數(BI)及褐變面積(S),應用主成分分析和隸屬函數分析計算得出10份資源的褐變隸屬函數排名(表3)。根據隸屬函數排名得到了最抗褐變的紅肉資源艷紅和白肉資源中白,而最易褐變的紅肉類型為木羅枇杷,白肉類型國芬本最不抗褐變。
3 討 論
常用的表色系統包括RGB、Lab、HIS、HSV四種顏色空間,而在果蔬顏色性狀表征時更多使用RGB和Lab兩種顏色空間[22-23],其中Lab顏色空間是一種基于生理特征的顏色系統,以數字化的方法描述人的視覺感應,不受外源光照的影響[24],在果蔬褐變研究中被廣泛使用[25]。在本研究中,枇杷果肉在褐變過程中呈現L值下降而a、b值上升的趨勢,與馬鈴薯褐變Lab值變化特征相同[26]。此外,L值、a值和b值能夠有效區分紅肉和白肉兩大類型[27]的果肉,也可用于枇杷種質資源肉色表型的鑒定分析。
果實顏色性狀的評價分析常采用色差儀法[28-30],已有大量利用色差儀鑒定果蔬褐變表型的研究報道[17,23,26,31]。色差儀光源穩定,識別結果精確,適用于具體品種資源顏色性狀的定性分析[32-33],但色差儀的測量口徑較小,單個點的測量時間從1 s到1.85 s不等[34-35]。筆者在本研究中發現,枇杷果肉褐變部位集中于靠近心皮及切口的部分,存在不同部位褐變程度不同的現象,且當枇杷果肉厚度較薄時,切面與色差儀口徑貼合不當易產生偏差。MATLAB圖像識別算法精度高,精確到每個像素[19,36-37],能很好地彌補色差儀法僅測量局部而非整體褐變情況的不足;MATLAB圖像分割算法識別范圍廣、計算速度快,適用于大批量資源顏色動態變化過程的定量分析。枇杷果實成熟期較短,色差儀法在測定褐變Lab值時耗時較長,很難實現大批量樣品的測定,而圖像分割法僅需對鮮切后的果肉切面進行實時拍照用于后續Lab值提取,計算速度快,因此適用于大批量枇杷種質資源顏色性狀鑒定。色差儀法和圖像識別法在枇杷果肉顏色性狀識別時適用場景不同。
提取果肉切面的Lab值[38]計算褐變指數能精確到每個像素進而量化果肉褐變情況,但如果樣品成熟度、拍攝角度、光源等存在差異易導致計算結果出現偏差[30],因此為了提高計算結果的準確性,在挑選樣品時需保證果實成熟度一致,并盡量選擇更多樣本或進行多次重復試驗,拍攝設備也應盡量穩定,在獲取原始圖像過程中需嚴格控制一致的拍攝光源、角度及相機參數等[39]。歐式距離計算褐變面積不受光源等外界環境的限制,分割閾值及適宜性取決于觀測者的肉眼判斷[40],分割面積與肉眼觀察到的褐變表型高度一致。但由于果肉褐變是一個緩慢發生的過程,褐變的不同程度呈現出不同的褐變色,在選擇分割區域時要兼顧不同褐化程度的區域,閾值的選擇至關重要[15]。在紅肉類型中,較短時間內褐變色與果肉原始顏色的差異小,導致分割閾值更難把握,需要比白肉類型更長的鑒定間隔時間。在本研究中,圖像識別仍受試驗條件限制影響效率的提升,今后可進一步優化取樣方法及拍攝條件,達到高精度快速鑒定枇杷果肉褐變性狀的目的。
4 結 論
基于MATLAB函數的圖像識別算法可對枇杷果肉切面的L、a、b顏色值進行像素級提取并計算褐變指數、分割褐變面積,從不同維度描述果肉的褐變情況,二者結合能最大程度實現對枇杷資源果肉褐變抗性的綜合鑒定評價。該方法亦適用于枇杷種質資源顏色性狀評價。
參考文獻 References:
[1] 石鈺琢,楊松,黃棟,路超,張敏. 鮮切果蔬物理保鮮技術研究進展[J]. 食品科技,2023,48(7):37-42.
SHI Yuzhuo,YANG Song,HUANG Dong,LU Chao,ZHANG Min. Advances on physical preservation technology of fresh-cut fruits and vegetables[J]. Food Science and Technology,2023,48(7):37-42.
[2] 李彩云,李潔,嚴守雷,王清章. 果蔬酶促褐變機理的研究進展[J]. 食品科學,2021,42(9):283-292.
LI Caiyun,LI Jie,YAN Shoulei,WANG Qingzhang. Progress in research on the mechanism of enzymatic browning in fruits and vegetables[J]. Food Science,2021,42(9):283-292.
[3] BHARGAVA A,BANSAL A. Fruits and vegetables quality evaluation using computer vision:A review[J]. Journal of King Saud University - Computer and Information Sciences,2021,33(3):243-257.
[4] 王明,張倩. 我國基于深度學習的圖像識別技術在農作物病蟲害識別中的研究進展[J]. 中國蔬菜,2023(3):22-28.
WANG Ming,ZHANG Qian. Research progress of image recognition technology based on depth learning in identification of pest and disease in crops in China[J]. China Vegetables,2023(3):22-28.
[5] 樊澤澤,柳倩,柴潔瑋,楊曉峰,李海芳. 基于顏色與果徑特征的蘋果樹果實檢測與分級[J]. 計算機工程與科學,2020,42(9):1599-1607.
FAN Zeze,LIU Qian,CHAI Jiewei,YANG Xiaofeng,LI Haifang. Apple detection and grading based on color and fruit-diameter[J]. Computer Engineering amp; Science,2020,42(9):1599-1607.
[6] LI L L,ZHANG S J,WANG B. Plant disease detection and classification by deep learning:A review[J]. IEEE Access,2021,9:56683-56698.
[7] FERENTINOS K P. Deep learning models for plant disease detection and diagnosis[J]. Computers and Electronics in Agriculture,2018,145:311-318.
[8] ARNAL BARBEDO J G. Plant disease identification from individual lesions and spots using deep learning[J]. Biosystems Engineering,2019,180:96-107.
[9] YIN H,LI B,LIU Y D,ZHANG F,SU C T,OU-YANG A G. Detection of early bruises on loquat using hyperspectral imaging technology coupled with band ratio and improved Otsu method[J]. Spectrochimica Acta Part A:Molecular and Biomolecular Spectroscopy,2022,283:121775.
[10] IQBAL Z,KHAN M A,SHARIF M,SHAH J H,UR REHMAN M H,JAVED K. An automated detection and classification of citrus plant diseases using image processing techniques:A review[J]. Computers and Electronics in Agriculture,2018,153:12-32.
[11] JIANG P,CHEN Y H,LIU B,HE D J,LIANG C Q. Real-time detection of apple leaf diseases using deep learning approach based on improved convolutional neural networks[J]. IEEE Access,2019,7:59069-59080.
[12] 謝家興,陳斌瀚,彭家駿,何培華,景庭威,孫道宗,高鵬,王衛星,鄭代德,李君. 基于改進ShuffleNet V2的荔枝葉片病蟲害圖像識別[J]. 果樹學報,2023,40(5):1024-1035.
XIE Jiaxing,CHEN Binhan,PENG Jiajun,HE Peihua,JING Tingwei,SUN Daozong,GAO Peng,WANG Weixing,ZHENG Daide,LI Jun. Image recognition of leaf pests and diseases based on improved ShuffleNet V2 in litchi[J]. Journal of Fruit Science,2023,40(5):1024-1035.
[13] WANG J,XIA D,WAN J Z,HOU X Y,SHEN G H,LI S S,CHEN H,CUI Q,ZHOU M,WANG J,REN R,HU W,LI J,ZHANG Z Q. Color grading of green Sichuan pepper (Zanthoxylum armatum DC.) dried fruit based on image processing and BP neural network algorithm[J]. Scientia Horticulturae,2024,331:113171.
[14] 劉佳浩,高軍偉,張炳星,王建沖. 基于機器視覺的水果分級系統[J]. 食品與機械,2023,39(6):112-118.
LIU Jiahao,GAO Junwei,ZHANG Bingxing,WANG Jianchong. Design of fruit grading system based on machine vision[J]. Food amp; Machinery,2023,39(6):112-118.
[15] 高燕萍,何培文,呂尊富,崔鵬,徐錫明,龐林江,陸國權. 基于圖像分割的甘薯抗褐變種質資源的快速鑒定[J]. 中國農業大學學報,2023,28(7):46-56.
GAO Yanping,HE Peiwen,Lü Zunfu,CUI Peng,XU Ximing,PANG Linjiang,LU Guoquan. Rapid identification of browning resistant sweetpotato germplasm resources based on image segmentation[J]. Journal of China Agricultural University,2023,28(7):46-56.
[16] 蔣際謀,姜帆,陳秀萍,胡文舜,鄧朝軍,鄭少泉. 枇杷主要品質評價指標研究[J]. 園藝學報,2013,40(12):2382-2390.
JIANG Jimou,JIANG Fan,CHEN Xiuping,HU Wenshun,DENG Chaojun,ZHENG Shaoquan. Studies on several quality evaluation indices from loquat germplasm resources[J]. Acta Horticulturae Sinica,2013,40(12):2382-2390.
[17] 范凈,陳啟亮,楊曉平,張靖國,田瑞,胡紅菊. 色差儀在砂梨果肉褐變分析上的應用[J]. 農業與技術,2017,37(18):38.
FAN Jing,CHEN Qiliang,YANG Xiaoping,ZHANG Jingguo,TIAN Rui,HU Hongju. Application of colorimeter to the analysis of flesh browning of sand-pear[J]. Agriculture and Technology,2017,37(18):38.
[18] 包新月,俞磊. 計算機數字圖像處理常用顏色空間及轉換[J]. 電子技術與軟件工程,2021(7):122-123.
BAO Xinyue,YU Lei. Computer digital image processing common color space and conversion[J]. Electronic Technology amp; Software Engineering,2021(7):122-123.
[19] 迪娜·加爾肯. 基于MATLAB的圖像分割算法研究及實現[J]. 科學技術創新,2021(26):84-86.
Dina·Jiaerken. Research and implementation of image segmentation algorithm based on MATLAB[J]. Scientific and Technological Innovation,2021(26):84-86.
[20] 鄭磊. 基于MATLAB軟件的數字圖像處理[J]. 信息記錄材料,2024,25(1):59-62.
ZHENG Lei. Digital image processing based on MATLAB software[J]. Information Recording Materials,2024,25(1):59-62.
[21] LEI L,YANG Q L,YANG L,SHEN T,WANG R X,FU C B. Deep learning implementation of image segmentation in agricultural applications:A comprehensive review[J]. Artificial Intelligence Review,2024,57(6):149.
[22] 任凱麗,孔維萍,唐桃霞,程鴻. 基于Lab表色系統的甜瓜果實顏色多樣性分析[J]. 園藝學報,2022,49(9):2017-2022.
REN Kaili,KONG Weiping,TANG Taoxia,CHENG Hong. Diversity analysis of melon fruit color based on the Lab system[J]. Acta Horticulturae Sinica,2022,49(9):2017-2022.
[23] 路緒強,袁明,何楠,趙勝杰,朱紅菊,劉文革. 利用色差儀快速檢測西瓜番茄紅素含量[J]. 中國瓜菜,2021,34(4):41-45.
LU Xuqiang,YUAN Ming,HE Nan,ZHAO Shengjie,ZHU Hongju,LIU Wenge. Rapid determination of watermelon lycopene content by using chromatic meter[J]. China Cucurbits and Vegetables,2021,34(4):41-45.
[24] 吳慶崗,張衛國,李燦林,吳青娥,朱付保. 自然環境下基于Lab空間的成熟蘋果圖像分割[J]. 江蘇農業科學,2017,45(9):177-179.
WU Qinggang,ZHANG Weiguo,LI Canlin,WU Qing’e,ZHU Fubao. Lab color space-based image segmentation of ripe apples in natural environments[J]. Jiangsu Agricultural Sciences,2017,45(9):177-179.
[25] 蘇艷麗,高曉銘,楊健,王龍,王蘇珂,張向展,薛華柏. 梨果實發育過程中褐變度、酚類物質及相關酶的變化研究[J]. 園藝學報,2022,49(11):2304-2312.
SU Yanli,GAO Xiaoming,YANG Jian,WANG Long,WANG Suke,ZHANG Xiangzhan,XUE Huabai. Dynamic changes of browning degree,phenolics contents and related enzyme activities during pear fruit development[J]. Acta Horticulturae Sinica,2022,49(11):2304-2312.
[26] 羅有中,劉全亮,李珍妮,羅磊,姚晏紅,王娟,滿正行. 基于CIE-Lab及RGB顏色空間的馬鈴薯塊莖酶促褐變程度評價[J]. 農業技術與裝備,2023(11):102-109.
LUO Youzhong,LIU Quanliang,LI Zhenni,LUO Lei,YAO Yanhong,WANG Juan,MAN Zhengxing. Evaluation of enzymatic browning degree of potato tubers based on CIE-Lab and RGB color space[J]. Agricultural Technology amp; Equipment,2023(11):102-109.
[27] 孫淑霞,謝紅江,李靖,涂美艷,陳棟,江國良. 枇杷果肉色澤深淺性狀的分子標記鑒定[J]. 西南農業學報,2012,25(6):2227-2230.
SUN Shuxia,XIE Hongjiang,LI Jing,TU Meiyan,CHEN Dong,JIANG Guoliang. Molecular identification of fragments associated with fruit flesh color in loquat[J]. Southwest China Journal of Agricultural Sciences,2012,25(6):2227-2230.
[28] YAN Y F,PICO J,GERBRANDT E M,DOSSETT M,CASTELLARIN S D. Comprehensive anthocyanin and flavonol profiling and fruit surface color of 20 blueberry genotypes during postharvest storage[J]. Postharvest Biology and Technology,2023,199:112274.
[29] 楊兆甜,李方巍,王震昊,張馨月,曹家蕊,張燕. 食品顏色評價及在食品工業中的應用[J]. 食品工業科技,2021,42(24):417-423.
YANG Zhaotian,LI Fangwei,WANG Zhenhao,ZHANG Xinyue,CAO Jiarui,ZHANG Yan. Food color evaluation and application in food industry[J]. Science and Technology of Food Industry,2021,42(24):417-423.
[30] 黃娟,李新建. 基于色差儀法的庫爾勒香梨果實顏色分級標準[J]. 北方園藝,2018(17):38-44.
HUANG Juan,LI Xinjian. The Korla fragrant pear color grading based on colorimeter[J]. Northern Horticulture,2018(17):38-44.
[31] 趙萍,王莉,蒲育林,王雅,林櫻姬,亓文靜,楊明峰. 不同品種馬鈴薯在不同生長期褐變的規律研究[J]. 食品工業科技,2010,31(11):101-104.
ZHAO Ping,WANG Li,PU Yulin,WANG Ya,LIN Yingji,QI Wenjing,YANG Mingfeng. Study on the law of different varieties of potato’s browning in different growing period[J]. Science and Technology of Food Industry,2010,31(11):101-104.
[32] 郭守鵬,黃昌見,盧緒鵬,杜巖,張文,齊增敏. 色差儀在茄子果色評價中的應用[J]. 中國果菜,2022,42(11):61-65.
GUO Shoupeng,HUANG Changjian,LU Xupeng,DU Yan,ZHANG Wen,QI Zengmin. Application of color difference meter in the evaluation of eggplant color[J]. China Fruit amp; Vegetable,2022,42(11):61-65.
[33] 代祥,梅菊芬,楊亦揚,王玉花. 基于色差儀的茶樹葉色量化研究[J]. 南京農業大學學報,2024,47(2):232-241.
DAI Xiang,MEI Jufen,YANG Yiyang,WANG Yuhua. A quantitative study of leaf colors of tea plants based on the colorimeter[J]. Journal of Nanjing Agricultural University,2024,47(2):232-241.
[34] 溫波,顏昌翔. 便攜式分光測色儀光學設計[J]. 應用光學,2011,32(1):18-22.
WEN Bo,YAN Changxiang. Optical design of portable spectrophotometer for colorimetry[J]. Journal of Applied Optics,2011,32(1):18-22.
[35] 朱紀忠,陳若雷,許士明. 分光測色儀的研制與性能分析[J]. 光學儀器,2003,25(5):31-34.
ZHU Jizhong,CHEN Ruolei,XU Shiming. Researching and analyzing property of spectral color-meter[J]. Optical Instruments,2003,25(5):31-34.
[36] 郭宏杰,馬睿,王佳,趙威,馬德新. 基于卷積神經網絡的蘋果葉部病害圖像識別研究[J]. 中國農機化學報,2024,45(5):239-245.
GUO Hongjie,MA Rui,WANG Jia,ZHAO Wei,MA Dexin. Research on apple leaf disease image recognition based on convolutional neural network[J]. Journal of Chinese Agricultural Mechanization,2024,45(5):239-245.
[37] KUMAR D,KUKREJA V. Image segmentation,classification,and recognition methods for wheat diseases:Two decades’ systematic literature review[J]. Computers and Electronics in Agriculture,2024,221:109005.
[38] 任龍龍,馮濤,翟傳龍,宋月鵬. 基于MATLAB圖像處理的蘋果大小、顏色、圓形度及缺陷度特征融合分級研究[J]. 數字技術與應用,2021,39(7):90-95.
REN Longlong,FENG Tao,ZHAI Chuanlong,SONG Yuepeng. Research on feature fusion grading of apple size,color,roundness and defect based on MATLAB image processing[J]. Digital Technology amp; Application,2021,39(7):90-95.
[39] XIAO F,WANG H B,LI Y X,CAO Y,LV X M,XU G F. Object detection and recognition techniques based on digital image processing and traditional machine learning for fruit and vegetable harvesting robots:An overview and review[J]. Agronomy,2023,13(3):639.
[40] 李娜,安楠,張立杰,姜海勇,陳廣毅,施宇. 自然環境下蘋果點云多維度特征分割方法研究[J]. 河北農業大學學報,2024,47(3):105-112.
LI Na,AN Nan,ZHANG Lijie,JIANG Haiyong,CHEN Guangyi,SHI Yu. Research on apple point cloud segmentation techniques in natural environments[J]. Journal of Hebei Agricultural University,2024,47(3):105-112.
收稿日期:2024-10-25 接受日期:2024-11-29
基金項目:福建省屬公益類科研院所基本科研專項(2024R1027003);“5511 ”協同創新工程(XTCXGC2021006);科技部、財政部國家科技資源共享服務平臺項目(NHGRC2023-NH18-1);福建省農業科學院科技創新團隊(CXTD2021004-1)
作者簡介:陳宇佳,女,在讀碩士研究生,研究方向為果樹栽培生理生態。E-mail:hlacyj99@163.com。#為共同第一作者。
*通信作者Author for correspondence. E-mail:jjm2516@126.com