메뉴 건너뛰기
소속 기관 / 학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
고객센터 ENG
주제분류

논문 기본 정보

저자정보
저널정보
한국멀티미디어학회 한국멀티미디어학회 국제학술대회 MITA 2006
오류 신고하기

피인용 0

검색

    초록·키워드

    In this paper, we propose an adaptive image wavelet-based watermarking with SOM(Self-organizing Map) neural networks, in which a pseudo-random sequence is embed into wavelet LL2 sub-band. The LL2 area is not suitable for embedding because of severe visual degradation. We overcome the degradation problem by embedding watermarks into visually insensitive locations using HVS and adapting suitable watermark strength and length using SOM.
    Experimental results show that our proposed method has good perceptual invisibility and robustness for various attacks. About two different watermark, we can know that the binary watermark sequence has more invisible and robust than a sequences of real random number with a normal distribution N(0, 1) in comparison about different watermark.

    최근 본 자료 전체보기

      UCI(KEPA) : I410-ECN-0101-2012-004-004247522