Flesh texture is an important quality trait and is related to people’s preference for fruit, especially for crisp pears. Puncture tests were carried out on 156 crisp pear fruit germplasm samples to analyze the diversity level of texture traits, to clarify the correlation between sensory description evaluation and instrumental traits, and to explore the effects of fruit ripening, size, and shelf life on the change in flesh texture. The results showed that puncture parameters were significantly different between crisp pear cultivars, and the work associated with the flesh limit compression force had the highest coefficient of variation (0.281). There was a significant correlation between puncture parameters and sensory evaluation scores. The correlation between sensory score and flesh firmness was the highest, with a correlation coefficient of 0.708, indicating that hardness can significantly influence the sensory evaluation of texture. Cluster analysis based on sensory evaluation and puncture determination could divide the germplasm resources of crisp pear into five texture categories: loosen, crunchy, crisp, tight–crisp, and dense. A comprehensive texture score model, constructed by principal component analysis, showed consistency with sensory evaluation scores and proved that the combination of a puncture test and sensory evaluation is the best way to identify and evaluate the texture of crisp pear. Further analysis of the influencing factors of flesh texture showed that fruit maturity and shelf life had significant effects on flesh quality. This study provides an important reference for the standardization, evaluation, and utilization of crisp pear variety resources.

The accurate and efficient identification of pear varieties is paramount to the intelligent advancement of the pear industry. This study introduces a novel approach to classifying pear varieties by recognizing their leaves. We collected leaf images of 33 pear varieties against natural backgrounds, including 5 main cultivation species and inter-species selection varieties. Images were collected at different times of the day to cover changes in natural lighting and ensure model robustness. From these, a representative dataset containing 17,656 pear leaf images was self-made. YOLOv10 based on the PyTorch framework was applied to train the leaf dataset, and construct a pear leaf identification and classification model. The efficacy of the YOLOv10 method was validated by assessing important metrics such as precision, recall, F1-score, and mAP value, which yielded results of 99.6%, 99.4%, 0.99, and 99.5%, respectively. Among them, the precision rate of nine varieties reached 100%. Compared with existing recognition networks and target detection algorithms such as YOLOv7, ResNet50, VGG16, and Swin Transformer, YOLOv10 performs the best in pear leaf recognition in natural scenes. To address the issue of low recognition precision in Yuluxiang, the Spatial and Channel reconstruction Convolution (SCConv) module is introduced on the basis of YOLOv10 to improve the model. The result shows that the model precision can reach 99.71%, and Yuluxiang’s recognition and classification precision increased from 96.4% to 98.3%. Consequently, the model established in this study can realize automatic recognition and detection of pear varieties, and has room for improvement, providing a reference for the conservation, utilization, and classification research of pear resources, as well as for the identification of other varietal identification of other crops.