Novel method for selecting the regions of interest in hyperspectral images of apples with random poses on the sorting line

Kangkang Qi, Wenbin Wu, Shuai Wang, Yuanjie Mu, Qian Song, Fengyun Wang, Yangyang Fan, Wenjie Feng, Rui Li, Longsheng Fu

Abstract


Recent approaches to the internal quality inspection of apples with the application of hyperspectral imaging technology are highly cost-intensive because of labor involvement for the data collection on a fixed posture and manual selection of the region of interest (RoI). In addition, several studies have repeated the data acquisition for the same apple. Current methods cannot meet the automation requirements of the sorting line. Therefore, this study proposed a novel method for automatically selecting RoI in hyperspectral images of apples with random poses. Firstly, the preliminary RoI selection of apple hyperspectral image was carried out, followed by the performance of histogram statistics of each pixel with spectral intensity at 700 nm wavelength. The top 40% area of the spectral intensity was reserved to obtain the magnitude relationship of the spectral intensity of each pixel point and a morphological erosion operation. Original apple RoI was acquired and overexposed pixels were removed with spectral intensity greater than 3900 (maximum 4095) in the reserved area at 700 nm. Secondly, the relationship between apple size and prediction accuracy was measured for the in-depth RoI analysis. A partial least square regression (PLSR) model was established between the average spectrum and apple sugar content of RoI with different sizes. Finally, the established model with the top 70% of the spectral intensity achieved the best prediction accuracy. Non-destructive estimation of apple sugar content was performed through hyperspectral imaging technology with reference to the proposed RoI selection method. A competitive adaptive reweighted sampling algorithm along the PLSR (CARS-PLSR) model was established after black-and-white correction and standard normal transformation (SNV) preprocessing and obtained the highest prediction accuracy. The determination coefficient of cross-validation (Rcv) and root mean square error of cross-validation (RMSECV) were 0.9595 and 0.3203°Brix, respectively. The determination coefficient of prediction (Rp) was 0.9308, and the root mean square error of prediction (RMSEP) was 0.4681°Brix. Results proved that the auto-selection of RoI is an efficient and accurate method, which can provide a foundation in practical application for online apple grading systems with hyperspectral imaging technology.

Keywords: apple, hyperspectral imaging, nondestructive detection, region of interest, sugar content
DOI: 10.25165/j.ijabe.20251801.9062

Citation: Qi K K, Wu W B, Wang S, Mu Y J, Song Q, Wang F Y, et al. Novel method for selecting the regions of interest in hyperspectral images of apples with random poses on the sorting line. Int J Agric & Biol Eng, 2025; 18(1): 199–207.

Keywords


apple, hyperspectral imaging, nondestructive detection, region of interest, sugar content

Full Text:

PDF PDF

References


Ferrari C, Foca G, Calvini R, Ulrici A. Fast exploration and classification of large hyperspectral image datasets for early bruise detection on apples. Chemometrics and Intelligent Laboratory Systems, 2015; 146: 108–119.

Chen H Z, Qiao H L, Lin B, Xu G L, Tang G Q, Cai K. Study of modeling optimization for hyperspectral imaging quantitative determination of naringin content in pomelo peel. Computers and Electronics in Agriculture, 2019; 157: 410–416.

Tian H, Wang S, Xu H R, Ying Y B. Modeling method for SSC prediction in pomelo using Vis-NIRS with wavelength selection and latent variable updating. Int J Agric & Biol Eng, 2024; 17(1): 251–260.

Wei Q Q, Zheng Y R, Chen Z Q, Huang Y, Chen C Q, Wei Z B, et al. Nondestructive perception of potato quality in actual online production based on cross-modal technology. Int J Agric & Biol Eng, 2023; 16(6): 280–290.

Chithra P, Henila M. Apple fruit sorting using novel thresholding and area calculation algorithms. Soft Computing, 2021; 25(1): 431–445.

Martins J A, Guerra R, Pires R, Antunes M D, Panagopoulos T, Br´azio A, et al. SpectraNet–53: A deep residual learning architecture for predicting soluble solids content with VIS-NIR spectroscopy. Computers and Electronics in Agriculture, 2022; 197: 106945.

Tian S J, Wang S, Xu H R. Early detection of freezing damage in oranges by online Vis/NIR transmission coupled with diameter correction method and deep 1D-CNN. Computers and Electronics in Agriculture, 2022; 193: 106638.

Wu G S, Fang Y L, Jiang Q Y, Cui M, Li N, Ou Y M, et al. Early identification of strawberry leaves disease utilizing hyperspectral imaging combing with spectral features, multiple vegetation indices and textural features. Computers and Electronics in Agriculture, 2023; 204: 107553.

Xu H L, Sun Y X, Cao X L, Ji C M, Chen L, Wang H Y. Apple quality detection based on photon transmission simulation and convolutional neural network. Transactions of the CSAM, 2021; 52(8): 338–345. (in Chinese)

Gamal E, Ning W, Clément V. Detecting chilling injury in Red Delicious apple using hyperspectral imaging and neural networks. Postharvest Biology and Technology, 2009; 52(1): 1–8.

Guo Z. Nondestructive detection techniques and devices for assessing quality attributes of apples based on NIR spectroscopy and hyperspectral imaging. Beijing: China Agricultural University, 2015.

Mo C, Kim M, Kim G, Lim J, Delwiche S R, Chao K, et al. Spatial assessment of soluble solid contents on apple slices using hyperspectral imaging. Biosystems Engineering, 2017; 159: 10–21.

Lan W J, Jaillais B, Renard C M G C, Leca A, Chen S C, Le Bourvellec C, et al. A method using near infrared hyperspectral imaging to highlight the internal quality of apple fruit slices. Postharvest Biology and Technology, 2021; 175: 111497.

Che W K, Sun L J, Zhang Q, Tan W Y, Ye D D, Zhang D, et al. Pixel based bruise region extraction of apple using Vis-NIR hyperspectral imaging. Computers and Electronics in Agriculture, 2018; 146: 12–21.

Zha Q M. Research on nondestructive testing of hardness, moisture and soluble solids content of apple based on hyperspectral imaging technology. Master dissertation. Nanjing: Nanjing Agricultural University, 2017; 81p. (in Chinese)

Feng D, Ji J W, Zhang L, Liu S J, Tian Y W. Optimal wavelengths extraction of apple brix and firmness based on hyperspectral imaging. Chinese Journal of Luminescence, 2017; 38(6): 799–806. (in Chinese)

Xu L. Detection of soluble solids content of fruit based on Vis-NIR spectroscopy and imaging technology. Master dissertation. Hefei: Anhui University, 2019; 74p. (in Chinese)

Wang F Y, Zheng J Y, Ruan H J, Yuan X L. Research on non-destructive prediction model of sugar content of bagged and non-bagged apples based on hyperspectrum. Shandong Agricultural Sciences, 2020; 52(6): 129–136. (in Chinese)

Ma H L, Wang R L, Cai C, Wang D. Rapid identification of apple varieties based on hyperspectral imaging. Transactions of the CSAM, 2017; 48(4): 305–312. (in Chinese)

Zhou Y, Dai S G, Lyu J, Liu T B, Shi Y. Effect of spectral pretreatment on near infrared spectroscopy for rapid detection of wine alcohol. Opto-Electronic Engineering, 2011; 38(4): 54–58. (in Chinese)

Savitzky A, Golay M J E. Smoothing and differentiation of data by simplified least squares procedures. Analytical Chemistry, 1964; 36(8): 1627–1639.

Isaksson T, Naes T. The effect of multiplicative scatter correction (MSC) and linearity improvement in NIR spectroscopy. Applied Spectroscopy, 1988; 42(7): 1273–1284.

Barnes R J, Dhanoa M S, Lister S J. Standard normal variate transformation and de-trending of near-infrared diffuse reflectance spectra. Applied Spectroscopy, 1989; 43(5): 772–777.

Liu T. New wavelengths selection method for molecular spectra based on Ant Colony optimization and fundamental applications. Master dissertation. Hangzhou: Zhejiang University, 2017; 123p.

Araújo M C U, Saldanha T C B, Galvão R K H, Yoneyama T, Visani V. The successive projections algorithm for variable selection in spectroscopic multicomponent analysis. Chemometrics and Intelligent Laboratory Systems, 2001; 57(2): 65–73.

Wang J X, Liu X M, Liu S X, Quan Z K, Xu C B, Jiang H. Prediction of nitrogen content in apple leaves in each growth period based on combined color characteristics. Transactions of the CSAM, 2021; 52(10): 272–281. (in Chinese)

Liu Y D, Xiao H C, Sun X D, Zhu D N, Han R B, Ye L Y, et al. Spectral feature selection and discriminant model building for citrus leaf Huanglongbing. Transactions of the CSAE, 2018; 34(3): 180–187. (in Chinese)

Shahin M A, Symons S J. Detection of Fusarium damaged kernels in Canada Western Red Spring wheat using visible/near-infrared hyperspectral imaging and principal component analysis. Computers and Electronics in Agriculture, 2011; 75(1): 107–112.

Wang S P, Teng J, Zheng P C, Liu P P, Gong Z M, Gao S W, et al. Optimizing processing pressure of Qingzhuan tea and development of GCG models for near infrared spectroscopy detection. Transactions of the CSAE, 2020; 36(8): 271–277. (in Chinese)

Huang G Q, Duan H W, He J H, Han L J. Rapid quantitative analysis of crop straws’ thermal conductivity based on infrared photoacoustic spectroscopy. Transactions of the CSAM, 2018; 49(7): 342–347. (in Chinese)

Dorigo M, Maniezzo V, Colorni A. Ant system: optimization by a colony of cooperating agents. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 1996; 26(1): 29–41.

Li J B, Peng Y K, Chen L P, Huang W Q. Near-infrared hyperspectral imaging combined with CARS algorithm to quantitatively determine soluble solids content in “Ya” pear. Spectroscopy and Spectral Analysis, 2014; 34(5): 1264–1269. (in Chinese)

Wold S, Ruhe A, Wold H, Dunn I W J. The collinearity problem in linear regression. The partial least squares (PLS) approach to generalized inverses. SLAM Journal on Scientific & Statistical Computing, 1984; 5(3): 735–743.

Martens H, Jensen S A. Partial least squares regression: a new two stage NIR calibration method. Progress in Cereal Chemistry and Technology, 1983; 607–647.

Borràs E, Ferré J, Boqué R, Mestres M, Aceña L, Busto O. Data fusion methodologies for food and beverage authentication and quality assessment-A review. Analytica Chimica Acta, 2015; 891: 1–14.

Wang F Y, Zhao Y M, Zheng J Y, Qi K K, Fan Y Y, Yuan X L, et al. Estimation model of soluble solids content in bagged and non-bagged apple fruits based on spectral data. Computers and Electronics in Agriculture, 2021; 191: 106492.

Liu C L, Hu Y J, Wu S N, Sun X R, Dou S L, Miao Y Q, et al. Outlier sample eliminating methods for building calibration model of near infrared spectroscopy analysis. Journal of Food Science and Technology, 2014; 32(5): 74–79. (in Chinese)

He L L, Fang W T, Zhao G N, Wu Z C, Fu L S, Li R, et al. Fruit yield prediction and estimation in orchards: A state-of-the-art comprehensive review for both direct and indirect methods. Computers and Electronics in Agriculture, 2022; 195: 106812.




Copyright (c) 2025 International Journal of Agricultural and Biological Engineering

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

2023-2026 Copyright IJABE Editing and Publishing Office