Hyperspectral Imaging for Non-Destructive Assessment of Pear Fruit Quality: Scope, Methods, Robustness, and Industrial Readiness—Mini Review

Pear fruit quality determines postharvest grading, storage management, and market value. Conventional destructive analytical methods for soluble solids content, firmness, titratable acidity, and other quality traits deliver accurate results yet suffer from low-throughput performance and are poorly suited for in-line sorting. Hyperspectral imaging (HSI) integrates spatial and spectral information and has therefore become a promising tool for the non-destructive evaluation of pear fruit quality. Addressing the scope ambiguity and insufficient critical synthesis identified in the pre-review process, this review strictly restricts its research object to Pyrus spp. fruits, with the typical research varieties including Korla fragrant pear, Ya pear, Nanguo pear, Dangshan pear and Huangyu pear, excluding general research on all fruit types and non-spectral machine vision detection technologies. This paper adopts a narrative review framework with transparent literature retrieval and screening standards. The work systematically compares the research results of HSI in detecting pear external defects, fungal diseases, soluble solids content (SSC), flesh firmness, titratable acidity (TA) and fruit maturity; it further carries out a comparative analysis from the dimensions of applicable wavelength bands, spectral/image preprocessing strategies, feature screening algorithms, multivariate modeling approaches, model-validation schemes and industrial application potential. Existing research proves that the 400–1000 nm visible–near infrared band is suitable for identifying peel color changes, surface mechanical damage and fungal lesions, while the 900–1700 nm near-infrared band provides high-dimensional spectral features that are associated with the internal water, sugar and tissue structure. However, the reported detection accuracy of all the models is strongly affected by pear cultivar, sample size, image acquisition geometry, preprocessing mode, calibration-test partitioning mode and whether independent external verification samples are adopted. At present, HSI has been verified as feasible for pear quality detection under laboratory environments, yet large-scale commercial promotion still requires multi-season and multi-variety standardized datasets, unified reporting standards of detection indicators and units, strict independent external verification, interpretable modeling systems and real conveyor line in-line detection experiments.