An Efficient Depth Segmentation Based Conversion of 2d Images to 3d Images
Geethu S S1, Sreeletha S H2
1Geethu S S, M.Tech Scholar, Department of Computer Science and Engineering, LBS Institute of Technology for Women, Poojappura, Trivandrum (Kerala), India.
2Sreeletha S H, Associate Professor, Department of Computer Science and Engineering, LBS Institute of Technology for Women, Poojappura, Trivandrum (Kerala), India.
Manuscript received on 13 August 2016 | Revised Manuscript received on 20 August 2016 | Manuscript Published on 30 August 2016 | PP: 118-120 | Volume-5 Issue-6, August 2016 | Retrieval Number: F4696085616/16©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In the 3D consumer electronics world have a wide increase in demands of more and more 3D technology, so this has led to the conversion of many existing two-dimensional images to three-dimensional images. The depth is an important factor in the conversion process. Determining the depth for a single image is very difficult. There are many techniques widely used for the depth estimation process. In this paper we propose an automatic depth estimation technique. Firstly, we partition the image using graph cut segmentation method. The main goal of segmentation is to simplify or change the representation of an image into something that is more meaningful and easier to analyze. Then we construct a higher order statistics map. The HOS is mainly used for solving detection and classification problems. We can estimate depth map from HOS mean. Finally, creating left view image and right view image and combined with depth map to generate an enhanced stereoscopic image.
Keywords: 2D to 3D, Segmentation, Graph Cut, HOS, Filtering, Stereoscopic Image.
Scope of the Article: Image analysis and Processing