Nondestructive detection and grading of flesh translucency in pineapples with visible and near-infrared spectroscopy.
Xu, Sai; Ren, Jinchang; Lu, Huazhong; Wang, Xu; Sun, Xiuxiu; Liang, Xin
Rapid, accurate, and nondestructive internal quality detection for large and rough surface fruit, such as translucency in pineapples, is challenging. In this paper, a visible and near infrared (VIS/NIR) spectrum-based platform is proposed for optimized detection of pineapple translucency. The internal quality of three batches of samples harvested at the same maturity but on different dates (early, middle, and mid to late harvest stage) were acquired with different spectral settings: VIS to shortwave NIR(400–1100 nm), NIR (900–1700 nm) and VIS/NIR (400–1700 nm). The pineapple samples were manually cut open and divided into three translucency degrees (no, slight, and heavy), according to marketing standards. The Savitzky Golay (SG) and standard normal variate (SNV) were applied to remove jitter and scattering noise, respectively. The successive projections algorithm, principal component analysis and Euclidean distance were combined for feature extraction and measurement, followed by data modeling using the partial least squares regression and probabilistic neural network (PNN). Data correction, data supplementation, and a combination of these were applied for model updating. Experimental results showed that the optimal solution for pineapple translucency detection was to use 400–1100 nm spectrum with SG, SNV, PNN and data supplementation for model updating. With only the first and second batch of samples used for modeling (validation set accuracy 91.2 %) and updating (validation set accuracy 100 %), the detection accuracy on the third batch samples was 100 %. The proposed methodologies therefore can be used as rapid, nondestructive, and cost-effective tools to detect pineapple translucency to guarantee the marketing of high-quality fruit, which can also guide the postharvest treatment for the pineapple industry to improve market competitiveness as well as to benefit nondestructive quality assessment of other large fruit.
XU, S., REN, J., LU, H., WANG, X., SUN, X. and LIANG, X. 2022. Nondestructive detection and grading of flesh translucency in pineapples with visible and near-infrared spectroscopy. Postharvest biology and technology [online], 192, article 112029. Available from: https://doi.org/10.1016/j.postharvbio.2022.112029
|Journal Article Type||Article|
|Acceptance Date||Jul 5, 2022|
|Online Publication Date||Jul 14, 2022|
|Publication Date||Oct 31, 2022|
|Deposit Date||Aug 1, 2022|
|Publicly Available Date||Jan 15, 2024|
|Journal||Postharvest biology and technology|
|Peer Reviewed||Peer Reviewed|
|Keywords||Pineapple; Translucency; Visible and near infrared spectroscopy; Nondestructive detection|
This file is under embargo until Jan 15, 2024 due to copyright reasons.
Contact firstname.lastname@example.org to request a copy for personal use.
You might also like
A music cognition-guided framework for multi-pitch estimation.