Human eye iris detection method and device

The invention discloses a human eye iris detection method and a device, and the method comprises the steps: receiving a face data set, and training a key point positioning neural network; carrying outcoarse positioning on the face key points by using a key point positioning neural network to obtain corresponding face key points, and selecting human eye region key points according to the obtainedface key points; calculating the angle of the iris not shielded by eyelids and the upper bound of the radius of the outer boundary of the iris of the human eye according to the key points of the humaneye area; and performing iterative optimization on the key points of the human eye area according to the angle of the iris which is not shielded by the eyelids and the upper bound of the radius of the outer boundary of the human eye iris, thereby realizing fine positioning of the key points and fine positioning of the outer boundary of the iris. According to the method, precise positioning of human eye key points and iris