AbstractJujubes (Ziziphus Mauritiana Lamk) are subjected to bruises during harvesting and post‐harvest processing, which will greatly reduce their commercial values. In this study, bruises on jujube are detected and classified based on thermal imaging and convolutional neural networks. A simple thermal imaging system is constructed that can capture thermal images speedily and clearly. Temperature difference analysis is performed on the collected thermal images and accordingly, the temperature difference of boundary in the bruised area varies between 1.72 and 3.25°C during the storage period. The temperature difference in the bruise boundary area minus the temperature difference in the center area varies between 0.4 and 1.2°C, and the degree of bruise of the jujube is evaluated through temperature difference analysis. The convolutional neural network DenseNet is adjusted to ensure suitability for classification of the thermal image data set collected in this study (the training dataset comprises 5,039 original thermal images, and the test dataset comprises 2,586 original thermal images), and the best prediction accuracy achieved is 99.5%.Practical ApplicationThis study can be used as a reference for the future development of harvest, sorting, storage, and transportation for bruise detection in jujube. Our study makes a significant contribution to the literature because the findings of this study could facilitate the development of an online thermal imaging system for bruise detection and classification in jujube in the future.