A study on pseudo stereoscopic vision from a piece of human group picture: Face recognition, segmentation, and depth estimation

A method of pseudo stereoscopic vision from a piece of human picture is proposed. Faces from a group photo are detected using face recognition systems and the distance from camera lens called “depth” of each person is estimated using each face size. We propose a method of segmenting each person using super pixels. To generate our pseudo stereoscopic vision, we create two images for right-eye and left-eye as each region of the person is moved according to its depth, and convert to an anaglyph image. In this paper, we describe our method and show the pseudo stereoscopic results.