Volume 23, Issue 2, May 2016, Pages 372–379
A. Shenbagarajan1, P. Elamparithi2, and C. Karuppasamy3
1 Department of CSE, AAA College of Engineering & Technology, Sivakasi, Tamilnadu, India
2 Department of CSE, AAA College of Engineering & Technology, Sivakasi, Tamilnadu, India
3 Department of EEE, AAA College of Engineering & Technology, Sivakasi, Tamilnadu, India
Original language: English
Copyright © 2016 ISSR Journals. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
In this paper, the method was proposed a solution for the problem of an image inpainting method for missing parts or corrupted by noise of a video sequence recorded by a moving or stationary camera. The region to be inpainted may be still or moving, in the background or in the foreground, it may occlude one object or may be occluded by some other objects. This method was approached by a simple preprocessing stage and two steps of video inpainting. In the preprocessing stage, the corrupted video sequence images is extracted into multiple frames, then roughly segment each frame into foreground and background using Expectation Maximization algorithm. In segmentation, it builds three image mosaics that help to produce time consistent results and also improve the performance of the algorithm by reducing the search space. In the first video inpainting step, it reconstructs the corrupted video images of the moving objects in the foreground that are occluded. At the end of this first video inpainting, fill the gap as much as possible by copying information from the moving foreground in other frames, using a priority-based scheme. In the second step, the remaining regions are inpainted with the background. To accomplish this, first align the frames and directly copy when possible. The remaining pixels are filled in by extending spatial texture synthesis techniques to the spatiotemporal domain. This proposed framework has several advantages such as, it is simple to implement, fast and does not require statistical models of background or foreground. Works well in the presence of rich and cluttered backgrounds.
Author Keywords: Camera motion, Expectation-Maximization (EM), optical flow, texture synthesis, video inpainting, digital image, Partial Differential Equations (PDEs), video sequence, blurring operator, space variant.
A. Shenbagarajan1, P. Elamparithi2, and C. Karuppasamy3
1 Department of CSE, AAA College of Engineering & Technology, Sivakasi, Tamilnadu, India
2 Department of CSE, AAA College of Engineering & Technology, Sivakasi, Tamilnadu, India
3 Department of EEE, AAA College of Engineering & Technology, Sivakasi, Tamilnadu, India
Original language: English
Copyright © 2016 ISSR Journals. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
In this paper, the method was proposed a solution for the problem of an image inpainting method for missing parts or corrupted by noise of a video sequence recorded by a moving or stationary camera. The region to be inpainted may be still or moving, in the background or in the foreground, it may occlude one object or may be occluded by some other objects. This method was approached by a simple preprocessing stage and two steps of video inpainting. In the preprocessing stage, the corrupted video sequence images is extracted into multiple frames, then roughly segment each frame into foreground and background using Expectation Maximization algorithm. In segmentation, it builds three image mosaics that help to produce time consistent results and also improve the performance of the algorithm by reducing the search space. In the first video inpainting step, it reconstructs the corrupted video images of the moving objects in the foreground that are occluded. At the end of this first video inpainting, fill the gap as much as possible by copying information from the moving foreground in other frames, using a priority-based scheme. In the second step, the remaining regions are inpainted with the background. To accomplish this, first align the frames and directly copy when possible. The remaining pixels are filled in by extending spatial texture synthesis techniques to the spatiotemporal domain. This proposed framework has several advantages such as, it is simple to implement, fast and does not require statistical models of background or foreground. Works well in the presence of rich and cluttered backgrounds.
Author Keywords: Camera motion, Expectation-Maximization (EM), optical flow, texture synthesis, video inpainting, digital image, Partial Differential Equations (PDEs), video sequence, blurring operator, space variant.
How to Cite this Article
A. Shenbagarajan, P. Elamparithi, and C. Karuppasamy, “An Innovative approach of EM Algorithm for Restoration of Noisy Video Frame Images in a Video Sequence,” International Journal of Innovation and Scientific Research, vol. 23, no. 2, pp. 372–379, May 2016.
