Detection of skin defects in Cerasus humilis fruit is a critical process to guarantee its quality and price. This study presents a valid method for the detection of defective features in Cerasus humilis fruits based on hyperspectral imaging. A total of 420 sample images were acquired that included three types of natural defects and undamaged samples. After acquiring hyperspectral images of Cerasus humilis fruits, the spectral data were extracted from the region of interest (ROI). Five spectral preprocessing methods were used to preprocess the original spectral data, including Savitsky–Golay (S-G), standard normal variate (SNV), multiplicative scatter correction (MSC), baseline correction (BC), and de-trending (De-T). Regression coefficient (RC), successive projections algorithm (SPA), and competitive adaptive reweighed sampling (CARS) were conducted to select optimal sensitive wavelengths (SWs); as a result, 11 SWs, 17 SWs, and 13 SWs were selected, respectively. Then, the least squares-support vector machine (LS-SVM) discrimination model was established using the selected SWs. The results showed that the discriminate accuracy of the CARS-LS-SVM method was 91.43%. Based on the characteristics of image information, images corresponding to eight sensitive wavebands (950, 994, 1071, 1263, 1336, 1457, 1542, and 1628 nm) selected by CARS were subjected to principal component analysis (PCA). Then, an effective approach for detecting the defective features was exploited based on the imfill function, canny operator, region growing algorithm, bwareaopen function, and the images of PCA. The location and area of defect feature of 105 Cerasus humilis fruits could be recognized; the detect precision was 88.57%. This investigation demonstrated that hyperspectral imaging combined with an image processing technique could achieve the rapid identification of undamaged samples and natural defects in Cerasus humilis fruit. This provides a theoretical basis for the development of Cerasus humilis fruit grading and sorting equipment.

In this study, our aim is to find an effective method to solve the problem of disease similarity caused by multiple diseases occurring on the same leaf. This study proposes the use of an optimized RegNet model to identify seven common apple leaf diseases. We conducted comparisons and analyses on the impact of various factors, such as training methods, data expansion methods, optimizer selection, image background, and other factors, on model performance. The findings suggest that utilizing offline expansion and transfer learning to fine-tune all layer parameters can enhance the model’s classification performance, while complex image backgrounds significantly influence model performance. Additionally, the optimized RegNet network model demonstrates good generalization ability for both datasets, achieving testing accuracies of 93.85% and 99.23%, respectively. These results highlight the potential of the optimized RegNet network model to achieve high-precision identification of different diseases on the same apple leaf under complex field backgrounds. This will be of great significance for intelligent disease identification in apple orchards in the future.