3D Integral Imaging Reconstruction of Occluded Objects Using Independent Component Analysis-Based K-Means Clustering

We explore algorithms of independent component analysis and K-means applied to 3D reconstruction of occluded objects using integral imaging. 3D reconstruction of occluded objects is implemented using the elemental images of the separated objects from occlusion. Experimental and theoretical results are presented. We show that the 3D reconstructed images using the proposed method may perform better than those using the conventional method in terms of contrast, sharpness and average normalized rms error (RMSE) metrics.