The present application relates to the technical field of facial recognition, and provided therein are an eye bag detection method and device. The method comprises: acquiring an image to be tested, said image comprising an eye bag region of interest (ROI); testing the eye bag ROI by means of a preset convolutional neural network model so as to obtain an eye bag detection score and eye bag position detection information; and when the eye bag detection score is within a preset score range, marking said image on the basis of the eye bag detection score and the eye bag position detection information so as to obtain eye bag marking information. In the technical solution provided by the present application, the position and score of eye bags can be accurately identified, thus significantly improving the accuracy of identifying eye bags.
展开▼