Pepper suffers from bacterial leaf spot and yellow leaf curl, which substantially reduce crop yield and fruit quality. Traditional manual diagnosis suffers from delayed response, subjective bias and heavy labor consumption, while existing intelligent detection pipelines lack standardized preprocessing workflows, quantitative feature screening and systematic model comparison. To fill these research gaps, we built a pepper leaf dataset with 1260 samples (healthy, bacterial spot, yellow leaf curl). Three segmentation algorithms (Lab b-channel, RGB super-green, Otsu-ACWE) were quantitatively assessed to select the optimal preprocessing scheme. We extracted 32 fused visual features (27 RGB/HSV/Lab color moments + five gray-level co-occurrence matrix (GLCM) texture metrics) and adopted a random-forest classifier to eliminate seven low-contribution redundant features, retaining 25 discriminative variables. Three representative models, namely convolutional neural network (CNN), logistic regression (LR), and genetic-algorithm-optimized back-propagation neural network (GA-BP), were constructed for parallel comparison via 20 independent repeated trials, with accuracy, precision, recall, F1-score and area under the receiver operating characteristic curve (AUC) as evaluation indicators. The results verified that Lab b-channel segmentation achieved superior background separation and intact lesion edge retention. CNN yielded the best performance, with an average test accuracy of 97.67% and an average AUC of 0.999, accompanied by minimal metric standard deviations and outstanding stability. LR exhibits low computational cost and fast training, which is promising for applications with limited computing resources. In contrast, GA-BP shows weak nonlinear fitting ability and severe prediction fluctuations, making it unsuitable for high-precision diagnosis. This study proposes a standardized experimental framework to offer theoretical guidance and algorithmic references for intelligent vegetable leaf disease identification. All experiments were conducted on a dataset collected under standardized indoor single-illumination conditions; therefore, the conclusions of this study are only applicable to such controlled scenarios.

This study investigated how detection distance affects spectral models for soluble solids content (SSC) and firmness evaluation in Korla fragrant pears and provides a reference for calibrating standardized indoor non-destructive detection equipment. Two hundred visually intact fruit samples at the early-ripening stage were collected from the Korla production area in Xinjiang. An FS-640 multispectral camera system equipped with a VS-SWR fixed-focus industrial lens (16 mm focal length, F1.8 maximum aperture, 1/2-inch sensor format) was used to acquire fruit reflectance spectra at seven vertical lens-to-fruit-surface distances of 90, 100, 110, 120, 130, 140, and 150 cm. A 625-pixel region of interest (ROI) was selected using ENVI at an undamaged equatorial or near-equatorial position of each fruit, and the regional mean spectrum was used as the spectral feature of one fruit sample. The sample-set partitioning based on joint X–Y distances (SPXY) algorithm was used to divide the calibration and prediction sets at a 3:1 ratio after outlier removal via a residual-threshold method. Four preprocessing methods, namely LOESS smoothing, standardization, vector normalization, and Savitzky–Golay (SG) smoothing, were compared. Competitive adaptive reweighted sampling (CARS) was performed with 50 Monte-Carlo sampling runs, a maximum of 30 principal components, and 10-fold cross-validation, yielding 99 characteristic wavelengths. Partial least squares regression (PLSR), support vector regression (SVR), random forest (RF), and artificial neural network (ANN) models were then established using identical input variables and sample partitions. Model performance was evaluated using the coefficient of determination for calibration ($R_c^2$), coefficient of determination for prediction ($R_P^2$), root-mean-square error of calibration (RMSEC), root-mean-square error of prediction (RMSEP), relative prediction deviation (RPD), and ratio of performance to interquartile distance (RPIQ). Under the static laboratory acquisition conditions in this work, the SSC model achieved the best prediction performance at 110 cm with SG smoothing ($R_P^2$) = 0.8949, RPD = 3.0633, RPIQ = 5.8661), whereas the firmness model obtained optimal prediction performance at 140 cm with standardization ($R_P^2$) = 0.7460, RPD = 1.9425, RPIQ = 3.2867). Changes in detection distance altered illumination uniformity, effective reflected signal, photon-scattering paths, and background-noise proportion. These effects may partially explain why the chemical-absorption-dominated SSC index and the tissue-scattering-dominated firmness index responded differently to detection distance. The results provide a reference for setting spectral detection parameters for Korla fragrant pears; however, samples were obtained from only a single producing region, harvest season, and maturity stage, and no independent external validation dataset was used. Therefore, the generalization ability of the developed models needs to be further verified using cross-season and cross-orchard sample sets.

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.