Printed Autostereoscopic Image Detection Method With Viewpoint Self-Matching

Abstract

A method for detecting printed autostereoscopic image with viewpoint self-matching is proposed. The proposed method consists of a viewpoint self-matching image acquisition system and a printing quality detection algorithm. The viewpoint self-matching image acquisition system contains a position-designed camera array, which ensures that the arbitrarily arranged parallax images can be captured successfully. The printing quality detection algorithm uses feature comparison to detect printing defects such as crosstalk and color leakage. A prototype has been developed, and the experimental results show that the proposed method can effectively identify printing quality.