DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Lee, Heung-Kyu | - |
dc.contributor.advisor | 이흥규 | - |
dc.contributor.author | Kwon, Myung-Joon | - |
dc.date.accessioned | 2022-04-27T19:32:07Z | - |
dc.date.available | 2022-04-27T19:32:07Z | - |
dc.date.issued | 2021 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=948440&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/296145 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전산학부, 2021.2,[iii, 31 p. :] | - |
dc.description.abstract | Detecting and localizing image splicing has become essential to fight against malicious forgery. A major challenge to localize spliced areas is to discriminate between authentic and tampered regions with intrinsic properties such as compression artifacts. We propose CAT-Net, an end-to-end fully convolutional neural network including RGB and DCT streams, to learn forensic features of compression artifacts on RGB and DCT domains jointly. Each stream considers multiple resolutions to deal with spliced object’s various shapes and sizes. The DCT stream is pretrained on double JPEG detection to utilize JPEG artifacts. The proposed method outperforms state-of-the-art neural networks for localizing spliced regions in JPEG or non-JPEG images. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | image manipulation detection▼aimage forensics▼amultimedia forensics▼aimage processing▼aconvolutional neural network | - |
dc.subject | 이미지 변형 탐지▼a이미지 포렌식▼a멀티미디어 포렌식▼a영상 처리▼a합성곱 신경망 | - |
dc.title | CAT-Net: compression artifact tracing network for image splicing detection and localization | - |
dc.title.alternative | 이미지 스플라이싱 탐지와 영역 특정을 위한 압축 흔적 추적 신경망 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전산학부, | - |
dc.contributor.alternativeauthor | 권명준 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.