한국지능시스템학회:학술대회논문집 (Proceedings of the Korean Institute of Intelligent Systems Conference)
- 한국퍼지및지능시스템학회 2003년도 ISIS 2003
- /
- Pages.407-410
- /
- 2003
EXTRACTION OF WATERMARKS BASED ON INDEPENDENT COMPONENT ANALYSIS
- Thai, Hien-Duy (University of the Ryukyus) ;
- Zensho Nakao (University of the Ryukyus) ;
- Yen- Wei Chen (University of the Ryukyus)
- 발행 : 2003.09.01
초록
We propose a new logo watermark scheme for digital images which embed a watermark by modifying middle-frequency sub-bands of wavelet transform. Independent component analysis (ICA) is introduced to authenticate and copyright protect multimedia products by extracting the watermark. To exploit the Human visual system (HVS) and the robustness, a perceptual model is applied with a stochastic approach based on noise visibility function (NVF) for adaptive watermarking algorithm. Experimental results demonstrated that the watermark is perfectly extracted by ICA technique with excellent invisibility, robust against various image and digital processing operators, and almost all compression algorithms such as Jpeg, jpeg 2000, SPIHT, EZW, and principal components analysis (PCA) based compression.
키워드