Title :
Virtual out of focus with single image to enhance 3D perception
Author :
Han, Heechul ; Jeong, Jingu ; Arai, Emi
Author_Institution :
DMC R&D Center, Samsung Electron., Yongin, South Korea
Abstract :
The color, contrast and detail of an object in focus are accentuated, whereas those of a background are attenuated based on the estimated depth map with a face detection and segmentation method for enhancing a 3D perception. Considering the human perception and a real out of focused image taken with wide aperture lens, we suggest a boundary gradation for the estimated depth map to handle blurring errors. To make a blurred background, we perform a modified Gaussian pyramid by scaling up and blending all of images.
Keywords :
image colour analysis; image enhancement; image segmentation; object detection; 3D perception image enhancement; aperture lens; face detection; human perception; image color analysis; image segmentation method; modified Gaussian pyramid; virtual out of focus; Apertures; Cameras; Face; Image color analysis; Lenses; Photography; Three dimensional displays; 3D perception; Digital Camera; Out of focusing;
Conference_Titel :
3DTV Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON), 2011
Conference_Location :
Antalya
Print_ISBN :
978-1-61284-161-8
DOI :
10.1109/3DTV.2011.5877188
