SYSTEM FOR FACE RECOGNITION AND IRIS POSITION RECOGNITION BASED ON DEEP-LEARNING IMAGE ANALYSIS

摘要

Various embodiments of the present invention relate to a system for face recognition and iris position recognition based on deep-learning image analysis. According to various embodiments of the present invention, the system for iris position recognition based on deep-learning image analysis comprises: a measurement terminal which acquires a measurement image which captures a user; a holder to and from which the measurement terminal can be attached and detached; and an analysis device which calculates progressive multifocal design information by analyzing the acquired measurement image based on deep learning. The analysis device may detect an eyeball from the acquired measurement image; detect the pupil, iris, and sclera by extracting an iris boundary and a sclera boundary from the detected eyeball; track movements of the detected pupil, iris, and sclera; compare eyeball track information obtained as a result of tracking with eyeball learning data obtained by conducting machine learning in advance using a deep-learning technique; and calculate progressive multifocal design information based on the comparison results. Other embodiments are possible. According to the present invention, it is possible to accurately calculate a rotation distance and rotation angle of the eyeball.;COPYRIGHT KIPO 2020