repository
Composition of Foreground and Background Images using Optical Flow
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.advisor | Dong-Yoon Kim | - |
| dc.contributor.author | Dawit Gebreyohannes | - |
| dc.date.accessioned | 2019-10-21T07:24:05Z | - |
| dc.date.available | 2019-10-21T07:24:05Z | - |
| dc.date.issued | 2014-08 | - |
| dc.identifier.other | 17451 | - |
| dc.identifier.uri | https://dspace.ajou.ac.kr/handle/2018.oak/18569 | - |
| dc.description | 학위논문(석사)--아주대학교 Graduate School :컴퓨터공학과,2014. 8 | - |
| dc.description.tableofcontents | 1.Introduction 1 1.1 Objective of the Research 2 1.2 Methodology of Research 3 1.3 Organization of this Thesis 3 2.Related Work 4 3.Proposed Image Composition 6 3.1 Computing optical flow in low-resolution 6 3.2 Foreground object extraction 7 3.3 Composing foreground object into background 9 4.Experimental Results 12 4.1 Computational time with respect to scaling operation 13 4.2 Processing cost relation to merging operation 14 4.3 Visual quality 15 5.Conclusion and Future Work 24 References 26 | - |
| dc.language.iso | eng | - |
| dc.publisher | The Graduate School, Ajou University | - |
| dc.rights | 아주대학교 논문은 저작권에 의해 보호받습니다. | - |
| dc.title | Composition of Foreground and Background Images using Optical Flow | - |
| dc.type | Thesis | - |
| dc.contributor.affiliation | 아주대학교 일반대학원 | - |
| dc.contributor.department | 일반대학원 컴퓨터공학과 | - |
| dc.date.awarded | 2014. 8 | - |
| dc.description.degree | Master | - |
| dc.identifier.localId | 652538 | - |
| dc.identifier.url | http://dcoll.ajou.ac.kr:9080/dcollection/jsp/common/DcLoOrgPer.jsp?sItemId=000000017451 | - |
| dc.description.alternativeAbstract | This thesis proposes a method to compose a foreground object into a background image, where the foreground object is a part (or a region) of an image taken by a front-facing camera and the background image is a whole image taken by a back-facing camera in a smart phone at the same time. Recent high-end cell-phones have two cameras with preview feature before taking photos. The method extracts the foreground object that is moving along with the front-facing camera using the optical flow during the preview. Then, the extracted foreground object is composed into a background image using a simple image composition technique. For better-looking result in the composed image, a border smoothing technique is applied using a weighted-border mask to blend transparency from background to foreground. Since constructing and grouping pixel-level dense optical flow are quite slow even in high-end cell-phones, the computation of a mask to extract the foreground object in low-resolution image is needed to reduce the computational cost greatly. Experimental result shows the effectiveness of our extraction and composition techniques, with much less computational time in extracting the foreground object and better composition quality compared with Poisson image editing technique which is widely used in image composition. The proposed method can improve the color bleeding artifacts observed in Poisson image editing using weighted-border masks. | - |
- Appears in Collections:
- Graduate School of Ajou University > Department of Computer Engineering > 3. Theses(Master)
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
-
- License
- STATISTICS
- Total Visit :3,740,326
- Total Download :1,818
- Today View :17,984
