Abstract：Apples have a unique flavor, crisp and delicious, and are widely loved by consumers worldwide. Soluble solid content (SSC) is an important internal quality indicator of apples. Hyperspectral imaging (HSI) has been widely used as a non-destructive tool to predict SSC in apples because it can simultaneously acquire spatial and spectral information. However, the widespread application of HSI is hindered due to expensive equipment and time-consuming operations. Spectral super-resolution (SSR) is an efficient way to acquire HSI images by establishing a mapping relationship from low spectral resolution images to corresponding high spectral resolution images. Hence, this study aims to adopt SSR to obtain HSI images from apples RGB images and use the hyperspectral data to predict the SSC of apples. Firstly, the apples of uniform size are selected as samples. Each apple is marked using the black grid matte paper to label the region of interest (ROI), and RGB and HSI images of apples are measured. Then, the global thresholding method generates 220 ROI image pairs of RGB and HSI. Secondly, a dense connection network, a multi-scale hierarchical regression network, and a Transformer network are used to achieve SSR of Apple RGB images to gain HSI images. Finally, the reflectance spectra of HSI images were extracted, and a competitive adaptive reweighted sampling algorithm was applied to obtain the spectra of effective wavelengths (EWs). Partial least squares regression (PLSR), random forest (RF), and extreme learning machine (ELM) are used to predict the SSC of apples by using the full spectra and spectra of EWs. The results show that the Transformer network achieves the best SSR with the mean relative absolute error (MRAESP) of 0.135 9 and the root mean square error (RMSESP) of 0.026 2 in the SSR prediction set, and the spectra obtained after SSR are most consistent with the ground truth. As for the full spectra, ELM provides the best prediction performance for SSC analysis with the coefficient of determination (R2P) of 0.925 5 and root mean square error (RMSEP) of 0.003 in the prediction set. The prediction results of PLSR were relatively poor, and RF performed the worst. When the spectra of EWs are used, tELM obtains the optimal performance R2P=0.960 9 and RMSEP=0.002 2. In contrast, PLSR obtains a slightly poor result and the worst result of estimating SSC is acquired by RF. In conclusion, based on the Transformer image SSR, this article has accomplished the accurate detection of sugar content in apples, offering a low-cost and efficient method for obtaining HSI images. It has realized a rapid and convenient new sugar content detection method, expanding the imaging application scenarios in fruit quality analysis. This provides a theoretical basis for promoting the development of smart agriculture and the food industry.
翁士状，潘美静，谭羽健，张巧巧，郑 玲. 基于图像光谱超分辨率的苹果糖度检测[J]. 光谱学与光谱分析, 2024, 44(11): 3095-3100.
WENG Shi-zhuang, PAN Mei-jing, TAN Yu-jian, ZHANG Qiao-qiao, ZHENG Ling. Prediction of Soluble Solid Content in Apple Using Image Spectral Super-Resolution. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(11): 3095-3100.
[1] Lee A, Shim J, Kim B, et al. Journal of Food Engineering, 2022, 321: 110945.
[2] GAO Sheng, WANG Qiao-hua(高 升，王巧华). Chinese Optics(中国光学), 2021, 14(3): 566.
[3] Ma T, Xia Y, Inagaki T, et al. Postharvest Biology and Technology, 2021, 174: 111440.
[4] Sharma N, Hefeeda M. Hyperspectral Reconstruction from RGB Images for Vein Visualization. Proceedings of the 11th ACM Multimedia Systems Conference, 2020: 77.
[5] ZHANG Shi-peng, WANG Li-zhi, FU Ying, et al(张仕鹏，王立志，付 莹，等). Chinese Journal of Computers(计算机学报), 2020, 43(1): 151.
[6] LI Yong, JIN Qiu-yu, ZHAO Huai-ci，et al(李 勇，金秋雨，赵怀慈，等). Acta Optica Sinica(光学学报), 2021, 41(7): 0730001.
[7] Shi Z, Chen C, Xiong Z, et al. HSCNN+: Advanced CNN-Based Hyperspectral Recovery from RGB Iamges. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2018: 939.
[8] Zhao Y, Po L M, Yan Q, et al. Hierarchical Regression Network for Spectral Reconstruction from RGB Images. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020: 422.
[9] Cai Y, Lin J, Lin Z, et al. MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconsturction. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022: 745.
[10] XU Li-jia, CHEN Ming, WANG Yu-chao, et al(许丽佳，陈 铭，王玉超，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2021, 41(7): 2188.
[11] Tian S, Liu W, Xu H. Food Research International, 2023, 170: 112988.
[12] Cheng J, Sun J, Yao K, et al. Journal of the Science of Food and Agriculture, 2023, 103: 2690.
