Non-destructive Detection of Apple Water Core Disease Based on Hyperspectral and X-ray CT Imaging

doi:10.12133/j.smartag.SA202507022

Abstract

Abstract:

[Objective] Apple "sugar-glazed core" (also known as watercore) is a common physiological disorder in apple fruits. Apples with watercore possess a distinctive flavor and are highly favored by consumers. However, severely affected apples are prone to mold growth during storage, posing potential food safety risks. Currently, the primary method for detecting sugar-glazed core in Xinjiang Red Fuji apples relies on manual destructive inspection, which is inefficient for large-scale applications and fails to meet the demands of modern automated and intelligent industrial production. To achieve rapid and non-destructive detection of apples with varying watercore severity levels, this study aims to develop effective grading and soluble solids content (SSC) prediction models. [Methods] This study utilized Xinjiang Aksu Red Fuji apples as the research subject. A total of 230 apple samples were selected, comprising 113 normal, 61 mild, 47 moderate, and 9 severe watercore apples. The watercore severity was quantified through image processing of the apples' cross-sectional images. X-ray computed tomography (X-ray CT) data were acquired, and SSC values were measured. A hyperspectral imaging system was employed to collect reflectance spectra within the 400~1 000 nm range. After performing black-and-white correction and selecting regions of interest (ROI), the Sample Set Partitioning based on joint x-y distances (SPXY) algorithm was applied to divide the dataset into modeling (training) and prediction sets at a 3:1 ratio. Using the iToolbox in MATLAB, discriminant models were constructed based on partial least squares discriminant analysis (PLSDA), support vector machine (SVM), and convolutional neural network (CNN) algorithms using the reflectance spectral data. Regression models for predicting SSC across different watercore severity levels were also established. Feature wavelength selection was carried out using competitive adaptive reweighted sampling (CARS), successive projections algorithm (SPA), and uninformative variable elimination (UVE) methods. [Results and Discussions] The results indicated that as watercore severity increased, the SSC of Red Fuji apples exhibited an upward trend. The average SSC values were 13.4% in normal apples, 14.9% in mild watercore apples, 15.0% in moderate watercore apples, and 16.0% in severe watercore apples. X-ray CT imaging revealed that the average tissue density of watercore-affected regions was higher than that of healthy tissues. Three-dimensional reconstruction algorithms allowed visualization of the internal spatial distribution of watercore tissues at different severity levels. The spatial volume proportions of watercore tissues were 3.92% in mild, 6.11% in moderate, and 10.23% in severe watercore apples. Apples with severe watercore demonstrated higher spectral reflectance. The PLSDA-based grading model achieved accuracies of 98.7% in the training set and 95.9% in the test set. The model based on feature wavelengths selected by the UVE algorithm also showed high precision, with accuracies of 95.67% in the training set and 86.06% in the test set. For SSC regression modeling, the partial least squares regression (PLSR) model performed best, with a correlation coefficient of calibration (Rc²) of 0.962, root mean square error of calibration (RMSEC) of 0.264, correlation coefficient of prediction (Rp²) of 0.879, and root mean square error of prediction (RMSEP) of 0.435. The model based on feature wavelengths selected by the SPA algorithm exhibited further improved prediction performance, yielding Rc² = 0.846, RMSEC = 0.532, Rp²= 0.792, RMSEP = 0.576, correlation coefficient of cross-validation (Rcv²) = 0.781, and root mean square error of cross-validation (RMSECV) = 0.637. [Conclusions] This study leveraged hyperspectral imaging and X-ray CT technologies to analyze differences in optical reflectance and microstructural characteristics of apple tissues across different watercore severity levels. The developed grading model effectively predicted watercore severity in apples, providing critical technical support for the development of intelligent postharvest sorting equipment. The SSC regression model accurately predicted SSC values in apples with varying watercore severity, offering an efficient method for non-destructive detection and quality assessment of watercore-affected apples.

Key words: water core disease, hyperspectral imaging technology, X-ray CT imaging technology, soluble solid content (SSC)

CLC Number:

S436.611.1

YU Xinyuan, WANG Zhenjie, YOU Sicong, TU Kang, LAN Weijie, PENG Jing, ZHU Lixia, CHEN Tao, PAN Leiqing. Non-destructive Detection of Apple Water Core Disease Based on Hyperspectral and X-ray CT Imaging[J]. Smart Agriculture, doi: 10.12133/j.smartag.SA202507022.

Figures/Tables 16

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Table 1

Fig. 6

Fig. 7

Fig. 8

Fig. 9

Fig. 10

Table 2

Fig. 11

Table 3

Table 4

Table 5

References 25

[1]	常汉. 水心病苹果水心程度与可溶性固形物含量在线无损检测方法与分级装备研究[D]. 杭州: 浙江大学, 2021.
	CHANG H. Research and development of on-line non-destructive detecting method and grading equipment of apple watercore and soluble solids content[D]. Hangzhou: Zhejiang University, 2021.
[2]	王菁菁. 新疆红旗坡苹果品牌建设调查研究[D]. 石河子: 石河子大学, 2022.
	WANG J J. Investigation on Apple brand construction in hongqipo, Xinjiang[D]. Shihezi: Shihezi University, 2022.
[3]	姜云斌, 王志华, 贾朝爽. 苹果水心病的发病机理研究进展[J]. 中国果树, 2022(1): 8-14.
	JIANG Y B, WANG Z H, JIA C S. Research progress on pathogenesis of watercore in apple[J]. China fruits, 2022(1): 8-14.
[4]	GUO Z M, WANG M M, AGYEKUM A A, et al. Quantitative detection of apple watercore and soluble solids content by near infrared transmittance spectroscopy[J]. Journal of food engineering, 2020, 279: ID 109955.
[5]	CHANG H, YIN J F, TIAN H, et al. Evaluation of the optical layout and sample size on online detection of apple watercore and SSC using Vis/NIR spectroscopy[J]. Journal of food composition and analysis, 2023, 123: ID 105528.
[6]	张思旭, 徐焕良, 王江波, 等. 基于光学特性参数反演的苹果水心病检测[J]. 南京农业大学学报, 2023, 46(5): 986-994.
	ZHANG S X, XU H L, WANG J B, et al. Detection of watercore disease in apple based on inversion of optical characteristic parameters[J]. Journal of Nanjing Agricultural University, 2023, 46(5): 986-994.
[7]	郭俊先, 马永杰, 田海清, 等. 基于高光谱反透射图像的新疆冰糖心红富士水心鉴别[J]. 食品科学, 2020, 41(6): 278-284.
	GUO J X, MA Y J, TIAN H Q, et al. Identification of watercore in Xinjiang-grown fuji apples based on reflection-transmission hyperspectral imaging[J]. Food science, 2020, 41(6): 278-284.
[8]	MA T, LI X Z, INAGAKI T, et al. Noncontact evaluation of soluble solids content in apples by near-infrared hyperspectral imaging[J]. Journal of food engineering, 2018, 224: 53-61.
[9]	FAN S X, ZHANG B H, LI J B, et al. Prediction of soluble solids content of apple using the combination of spectra and textural features of hyperspectral reflectance imaging data[J]. Postharvest biology and technology, 2016, 121: 51-61.
[10]	CHANG H, WU Q F, TIAN H, et al. Non-destructive identification of internal watercore in apples based on online vis/NIR spectroscopy[J]. Transactions of the asabe, 2020, 63(6): 1711-1721.
[11]	郭志明, 郭闯, 王明明, 等. 果蔬品质安全近红外光谱无损检测研究进展[J]. 食品安全质量检测学报, 2019, 10(24): 8280-8288.
	GUO Z M, GUO C, WANG M M, et al. Research advances in nondestructive detection of fruit and vegetable quality and safety by near infrared spectroscopy[J]. Journal of food safety & quality, 2019, 10(24): 8280-8288.
[12]	WOOD R M, SCHUT D E, BALK P A, et al. Assessing the development of internal disorders in pome fruit with X-ray CT before, during and after controlled atmosphere storage and shelf life[J]. Food control, 2025, 168: ID 110970.
[13]	张丽娟, 夏其乐, 陈剑兵, 等. 近红外光谱的三种蓝莓果渣花色苷含量测定[J]. 光谱学与光谱分析, 2020, 40(7): 2246-2252.
	ZHANG L J, XIA Q L, CHEN J B, et al. Prediction of anthocyanin content in three types of blueberry pomace by near-infrared spectroscopy[J]. Spectroscopy and spectral analysis, 2020, 40(7): 2246-2252.
[14]	LU Y Z, LU R F. Non-destructive defect detection of apples by spectroscopic and imaging technologies: A review[J]. Transactions of the asabe, 2017, 60(5): 1765-1790.
[15]	谢建超, 石旺辉, 贾天泽, 等. 苹果缺陷无损检测技术的研究进展[J]. 食品研究与开发, 2025, 46(1): 210-216.
	XIE J C, SHI W H, JIA T Z, et al. Research progress on non-destructive detection technologies for apple defects[J]. Food research and development, 2025, 46(1): 210-216.
[16]	HERREMANS E, MELADO-HERREROS A, DEFRAEYE T, et al. Comparison of X-ray CT and MRI of watercore disorder of different apple cultivars[J]. Postharvest biology and technology, 2014, 87: 42-50.
[17]	郭志明. 基于近红外光谱及成像的苹果品质无损检测方法和装置研究[D]. 北京: 中国农业大学, 2015.
	GUO Z M. Nondestructive detection techniques and devices for assessing quality attributes of apple based on NIR spectroscopy and hyperspectral imaging[D]. Beijing: China Agricultural University, 2015.
[18]	方莉. 库尔勒香梨采后果实可溶性糖组分和质地变化的光学特性响应规律研究[D]. 南京: 南京农业大学, 2022.
	FANG L. Sugar content and tissue structure indices of 'Korla' pear and their relation to bulk optical properties[D]. Nanjing: Nanjing Agricultural University, 2022.
[19]	于慧春, 娄楠, 殷勇, 等. 基于高光谱技术及SPXY和SPA的玉米毒素检测模型建立[J]. 食品科学, 2018, 39(16): 328-335.
	YU H C, LOU N, YIN Y, et al. Predictive model for detection of maize toxins with sample set partitioning based on joint x-y distance (SPXY) algorithm and successive projections algorithm (SPA) based on hyperspectral imaging technology[J]. Food science, 2018, 39(16): 328-335.
[20]	SUN Y, WANG Y H, XIAO H, et al. Hyperspectral imaging detection of decayed honey peaches based on their chlorophyll content[J]. Food chemistry, 2017, 235: 194-202.
[21]	LUO W, FAN G Z, TIAN P, et al. Spectrum classification of Citrus tissues infected by fungi and multispectral image identification of early rotten oranges[J]. Spectrochimica acta part A: Molecular and biomolecular spectroscopy, 2022, 279: ID 121412.
[22]	WANG Z, KÜNNEMEYER R, MCGLONE A, et al. Potential of Vis-NIR spectroscopy for detection of chilling injury in kiwifruit[J]. Postharvest biology and technology, 2020, 164: ID 111160.
[23]	温云梦, 张冬冬, 王家强. 干旱胁迫对胡杨叶片色素及光谱特征影响的研究进展[J]. 绿色科技, 2022, 24(1): 6-10.
	WEN Y M, ZHANG D D, WANG J Q. Research progress on effects of drought stress on pigment and spectral characteristics of Populus euphratica leaves[J]. Journal of green science and technology, 2022, 24(1): 6-10.
[24]	苏亚拉其其格, 张振鑫, 李卓凌, 等. 基于高光谱特征参数的马铃薯块茎形成期叶片含水量定量监测模型[J]. 光谱学与光谱分析, 2025, 45(3): 774-783.
	SU Y, ZHANG Z X, LI Z L, et al. Quantitative monitoring models of potato leaf water content in Tuber formation period based on hyperspectral characteristic parameters[J]. Spectroscopy and spectral analysis, 2025, 45(3): 774-783.
[25]	史兴秀, 冯贝贝, 闫鹏, 等. '王林'苹果早期水心病发生过程中的相关生理变化[J]. 园艺学报, 2025, 52(1): 171-184.
	SHI X X, FENG B B, YAN P, et al. Physiological changes associated with early watercore in'orin'Apples[J]. Acta horticulturae sinica, 2025, 52(1): 171-184.

模型	样本集合	总体/%	正常组/%	轻度水心组/%	中度水心组/%	重度水心组/%
PLS	训练集	98.7	99.2	95.8	100.0	100.0
PLS	测试集	95.9	95.9	100.0	87.5	100.0
SVM	训练集	99.6	100.0	100.0	97.8	100.0
SVM	测试集	82.8	100.0	57.1	75.0	25.0
CNN	训练集	94.2	97.9	94.9	80.4	100.0
CNN	测试集	77.3	97.2	83.3	52.4	33.3

特征波段筛选方法	样本集合	总体/%	正常组/%	轻度水心组/%	中度水心组/%	重度水心组/%
CARS	训练集	90.25	95.08	91.49	74.42	100.00
CARS	测试集	86.06	95.92	73.33	75.00	100.00
SPA	训练集	77.92	83.61	65.96	72.09	90.00
SPA	测试集	82.87	89.8	66.67	75.00	100.00
UVE	训练集	95.67	98.36	93.62	90.70	100.00
UVE	测试集	86.06	95.92	73.33	75.00	100.00

模型	校正集		预测集
模型	R _C ²	RMSEC	R _P ²	RMSEP
PLSR	0.962	0.264	0.879	0.435
SVR	0.998	0.057	0.771	1.057
CNN	0.930	0.355	0.822	0.539

方法	校正集		测试集		交叉验证
方法	R _C ²	RMSEC	R _P ²	RMSEP	R _CV ²	RMSECV
CARS	0.653	0.799	0.615	0.779	0.626	0.830
SPA	0.846	0.532	0.792	0.576	0.781	0.637
UVE	0.448	1.007	0.498	0.884	0.423	1.031