Sugar or acidity detection |
Taste is one of the bases for people to choose fruit, thus sugar content and acidity are important factors that affect the taste. In recent years, it has been used as an important reference for fruit taste. |
Wu et al. (2021)Wu, X., Li, G. L., & He, F. Y. (2021). Nondestructive analysis of internal quality in pears with a self-made near-infrared spectrum detector combined with multivariate data processing. Foods, 10(6), 1315. http://dx.doi.org/10.3390/foods10061315. PMid:34200438. http://dx.doi.org/10.3390/foods10061315...
established a partial least squares regression (PLSR) model using a self-made NIRS detector and an improved variable selection algorithm to detect the SSC content of pears. It shows that the prediction model based on GA-BOSS selection variable and GA-VACAA selection variable is the best. |
Brittle or hardness testing |
Fruit texture mainly includes brittleness, hardness, etc., which reflect the physical properties and organizational structure of fruits and affect the taste of eating. Traditional fruit texture testing methods use destructive testing methods such as pressure hardness testers or texture analyzers, which are inefficient and damage the commodity value of apples after testing. |
Sun et al. (2021)Sun, R., Zhou, J. Y., & Yu, D. (2021). Nondestructive prediction model of internal hardness attribute of fig fruit using NIR spectroscopy and RF. Multimedia Tools and Applications, 80(14), 21579-21594. http://dx.doi.org/10.1007/s11042-021-10777-4. http://dx.doi.org/10.1007/s11042-021-107...
proposed a rapid nondestructive testing method for fig hardness based on VIS/NIR. The results show that using VIS/NIR diffuse reflectance spectroscopy combined with sample set partition based on joint X-Y distance (SPXY), RF and PLS algorithms can detect the hardness of figs without destroying them. |
Shelf life testing |
Shelf life is an important index to measure fruit life. Accurate judgment of the shelf life can better grasp the storage life and quality information of fruits, and provide an important reference for sales planning. |
Li et al. (2019)Li, X., Liu, Y. D., Ouyang, A. G., Sun, X. D., Jiang, X. G., Hu, J., & Ouyang, Y. P. (2019). Study on non-destructive testing model of hyperspectral imaging for shelf life of crisp pear. Guangpuxue Yu Guangpu Fenxi, 39(8), 2578-2583. took pears as the research object and used hyperspectral imaging technology combined with partial least squares discriminant (PLS) to determine the shelf life of pears. Through PCA compression on the original images of samples with different shelf-life, the weight coefficient data of three different shelf-life are obtained. The discrimination model is established with the average gray value of the characteristic image as the independent variable and the shelf-life as the dependent variable. The results showed that the method was effective in the determination of pear shelf life. |
External damage detection |
The skin of fruits is bruised or broken due to bumping and extrusion during picking and handling, and some minor damages are difficult to identify with the naked eye, resulting in discoloration and decay. Early detection and elimination are the main measures at present. |
Chen et al. (2018)Chen, S.-Y., Zhang, S.-H., Zhang, S., & Tan, Z.-J. (2018). Detection of early tiny bruises in apples using confocal Raman spectroscopy. Guangpuxue Yu Guangpu Fenxi, 38(2), 430-435. used Raman spectroscopy combined with chemometrics to quickly identify early minor damage to apples. The original Raman spectra were smoothed and denoised by Savitzky-Golay (SG) convolution, baseline corrected by adaptive iterative reweighted penalized least squares (airPLS) algorithm, and the classification discriminant model was established by nonlinear support vector machine (SVM) regression algorithm, with the 97.8% classification accuracy rate. |