Intelligent judgment method and device for dark eye circles and computer readable storage medium

Abstract

The invention relates to an artificial intelligence technology and discloses an intelligent judgment method for dark eye circles. The method comprises the steps of receiving a face image set and a label set, and preprocessing the face image set; taking the label set as an input value of a loss function of a dark eye judgment model; carrying out direction gradient straight square operation on the data of the face image set, inputting the data into a support vector machine module of the black eye circle judgment model, carrying out primary classification on the face image set by the support vector machine module, and inputting the data into a convolutional neural network module of the black eye circle judgment model for training; and receiving a test set of a user, carrying out direction gradient squareness operation on the test set, inputting the test set into the dark eye circle judgment model to judge whether a dark eye circle exists, and outputting a result. The invention further provides an intelligent judgment device for the dark eye circles and a computer readable storage medium. According to the invention, an accurate intelligent dark eye circle judgment function can be realized.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a method, device and computer-readable storage medium for automatically judging dark circles based on human face data input. Background technique [0002] Dark circles under the eyes are due to staying up late, mood swings, eye fatigue, and aging, which lead to slow blood flow in the blood vessels of the eye skin, resulting in stagnation, insufficient oxygen supply to the tissues, and excessive accumulation of metabolic waste in the blood vessels, resulting in eye pigmentation. As people get older, the subcutaneous fat around the eyes becomes thinner, so dark circles become more obvious. In today's society, many people have dark circles without knowing it. Therefore, it is necessary to judge whether there are dark circles. However, there are still many problems in the accurate identification of dark circles. For example, the application scenarios are mostl...

AI Technical Summary

Problems solved by technology

In today's society, many people have dark circles without knowing it. Therefore, it is necessary to judge whether there are dark circles. However, there are still many problems in the accurate identification of dark circles. For example, the application scenarios are mostly complicated, and the local dynamics of the background Changes and target shadows caused by uneven lighting will increase the difficulty of recognition. In addition, the face is a non-rigid target with rich posture features. Different postures of the same face are often very different in detection and recognition.

Images