3D-Interactive-depth generation and object segmentation from Holoscopic image

Abstract

Holoscopic 3D Imaging is a technique for producing natural 3D objects that exist in our world without the need for wearing specific eyewear. An Auto-Feature-Edge (AFE) descript-tor algorithm is used to simplify the edge detection of objects that uses a Multi-Quantize Adaptive Local Histogram Analysis (MQALHA) algorithm. This paper presents an exploitation of available depth estimation and Feature Edge (FE) segmentation techniques when generating a 3D-Interactive-Map (3DIM). The robustness and efficiency of the proposed method is successfully illustrated in the paper and compared with the current state-of-the-art techniques. © 2014 IEEE.