There is only you: Actively diminishing people in a scene
- Authors
- Kim, Chanran; Lee, Jaehoon; Lee, Kanghoon; Park, Jong-Il
- Issue Date
- Apr-2018
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Keywords
- Deep Learning; Diminished Reality; Image Inpainting; Object Detection
- Citation
- International Conference on Electronics, Information and Communication, ICEIC 2018, v.2018-January, pp.1 - 4
- Indexed
- SCOPUS
- Journal Title
- International Conference on Electronics, Information and Communication, ICEIC 2018
- Volume
- 2018-January
- Start Page
- 1
- End Page
- 4
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/150325
- DOI
- 10.23919/ELINFOCOM.2018.8330604
- Abstract
- There are various objects in a scene, and some of them are unwanted. In particular, background photographs and portraits contain photographs of unwanted people. It is also problematic to include unwanted objects in terms of portrait rights, trademark exposure, and copyright protection. It is important to diminish these unwanted objects more naturally than to simply erase or mosaic them. We propose a method to actively detect a person and naturally fill that region. The proposed methods perform diminishing people by combining an object detection method based on deep learning and an exemplar-based image inpainting method. To measure the performance accurately, the object to be removed is synthesized with the image. In addition, we constructed the proposed method partially or in whole by deep learning and compared the results.
- Files in This Item
-
Go to Link
- Appears in
Collections - 서울 공과대학 > 서울 컴퓨터소프트웨어학부 > 1. Journal Articles

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.